600 commits

Author	SHA1	Message	Date
Danny Avila	46a86d849f	🛂 fix: Skip Inherited / Mark Skill Files Read-Only in Code-Env Pipeline (#12866) ... * 🛂 fix: Skip Re-Download of Inherited Code-Env Files (No More 403 Storms) When a bash/code-interpreter call lists or operates on inputs the user already owns (skill files primed via primeInvokedSkills, files inherited from a prior session), codeapi echoes those files back in the tool result with `inherited: true`. We were treating every entry as a generated artifact and calling processCodeOutput on each, which: 1. Hit `/api/files/code/download/<session_id>/<file_id>` with the user's session key. Skill files are uploaded under the skill's entity_id, so every download 403'd — producing dozens of "Unauthorized download" log lines per turn. 2. Surfaced those inputs as ghost file chips in the UI even though they were never generated by the run. 3. Wasted a download round-trip even when no auth boundary was crossed — the file is already persisted at its origin. Fix: skip files where `file.inherited === true` in all three artifact-files loops (`tools.js`, `createToolEndCallback`, and `createResponsesToolEndCallback`). Skill files remain available to subsequent calls via primeInvokedSkills / session inheritance — we just don't redundantly re-download them. Pairs with codeapi-side change that adds the `inherited` flag. * 🔒 feat: Mark Skill Files as `read_only` During Code-Env Priming Pairs with codeapi `read_only` upload flag (ClickHouse/ai#1345). When LibreChat primes a skill into the code-env, every file in the batch (SKILL.md plus all bundled scripts/schemas/docs) is now uploaded with `read_only: true`. Codeapi seals these inputs at the filesystem layer (chmod 444) and the walker echoes the original refs as `inherited: true` regardless of whether sandboxed code modified the bytes on disk. Without this, the previous PR's `inherited` skip handled only the unchanged case. A modified skill file (pip writing pyc near a .py, a script accidentally truncating LICENSE.txt, etc.) still flowed through the modified-input branch on codeapi, got a fresh user-owned file_id, uploaded as a "generated" artifact, and surfaced in the UI as a chip the user couldn't actually authorize a download for. Changes: - `api/server/services/Files/Code/crud.js`: `batchUploadCodeEnvFiles({ ..., read_only })` forwards the flag as a multipart form field. Default `false` preserves existing behavior for user-attached files and prior-session inheritance. - `packages/api/src/agents/skillFiles.ts`: type signature gains `read_only?: boolean`; `primeSkillFiles` passes `true`. - `packages/api/src/agents/skillFiles.spec.ts`: assert the upload call carries `read_only: true`. The flag is intentionally not skill-specific. Any future infrastructure-input flow (system fixtures, cached datasets, etc.) can opt in the same way.	2026-04-29 08:26:25 +09:00
Danny Avila	c9dee962e7	📂 fix: Preserve Nested Folder Paths for Code-Execution Artifacts (#12848) ... * 📂 fix: Preserve Nested Folder Paths for Code-Execution Artifacts When codeapi reports a generated file at a nested path (`a/b/file.txt`), `processCodeOutput` was running it through `sanitizeFilename` — which calls `path.basename()` and then collapses `/` to `_`. The DB row ended up with `filename: "file.txt"`, `primeFiles` shipped that flat name back to the next sandbox session, and `cat /mnt/data/a/b/file.txt` 404'd. Fix: split the sanitizer into two helpers in `packages/api/src/utils/files.ts`: - `sanitizeArtifactPath` — segment-wise sanitize while preserving `/`. Falls back to basename on `..` traversal, absolute paths, and other malformed inputs. The DB record uses this so the next prime() can recreate the nested path in the sandbox. - `flattenArtifactPath` — encode `/` as `__` for the local `saveBuffer` strategies, which key by single-component filename and would otherwise create unintended subdirectories under uploads/. `process.js` is updated to use both: DB filename keeps the path, storage key flattens. `claimCodeFile` is also keyed on `safeName` so the (filename, conversationId) compound key stays consistent with the record `createFile` writes. Tests: +13 unit tests in `files.spec.ts` (sanitizeArtifactPath table, flattenArtifactPath round-trip). +1 integration test in `process.spec.js` asserting the DB-row vs storage-key split for a nested path. Updated `process-traversal.spec.js` to mock the new helpers. 64 pass / 0 fail across `Files/Code/`; 36 pass / 0 fail in `packages/api/src/utils/files.spec.ts`. Companion: ClickHouse/ai#1327 — the codeapi-side counterpart that stops phantom file IDs from reaching this code path in the first place. These two are independent but the matplotlib bug is most cleanly resolved when both ship. * 🛡️ fix: Re-add 255-char per-segment cap in sanitizeArtifactPath (codex review P2) `sanitizeArtifactPath` dropped the 255-char basename cap that `sanitizeFilename` enforces. Long artifact names then flowed unbounded into `processCodeOutput`'s storage key (`${file_id}__${flatName}`) and tripped `ENAMETOOLONG` on filesystems that enforce `NAME_MAX` — saveBuffer fails, and the file falls back to a download URL instead of persisting / priming. This was a regression specifically for flat filenames that the original `sanitizeFilename` would have truncated safely. Re-add the cap as a per-path-component limit so it applies cleanly to both flat and nested paths: - Leaf segment: extension-preserving truncation, matching `sanitizeFilename`'s shape (`<truncated-stem>-<6 hex>.<ext>`). - Non-leaf (directory) segments: plain truncate-and-disambiguate (`<truncated-name>-<6 hex>`); directory names don't carry semantic extensions worth preserving. - Defensive fallback when `path.extname` returns a pathologically long "extension" (e.g. `_.aaaa…aaa` after the dotfile underscore prefix rewrite turns a long hidden file into a non-dotfile with a 300-char "extension"): collapse to whole-segment truncation rather than leaving the cap unmet. +6 unit tests covering: long leaf (regression case), long leaf under a preserved directory, long non-leaf segment, deeply nested mixed-length, exact-255 boundary (no truncation), and the dotfile + truncation interaction. * 🛡️ fix: Cap flattened storage key against NAME_MAX in processCodeOutput (codex review P1) Per-segment caps on the path-preserving form aren't enough. Once segments are joined with `__` for the storage key, deeply-nested or moderately long paths can still produce a flat form that overflows once `${file_id}__` is prepended — `${file_id}__a__b__c.csv` for a 3-level 100-char-each path is ~344 chars, well past filesystem NAME_MAX (255). saveBuffer then trips ENAMETOOLONG and falls back to a download URL, and the artifact never persists / primes. `flattenArtifactPath` gets an optional `maxLength` parameter. When set, the function truncates the flat form to fit, preserving the leaf extension with the same disambiguating-hex-suffix shape sanitizeFilename uses. Default (`undefined`) keeps existing call sites uncapped — the cap is opt-in for callers that are actually building a filesystem key. Pathologically long "extensions" from `path.extname` (e.g. `.aaaa…aaa`) fall back to whole-key truncation rather than leaving the cap unmet. processCodeOutput composes the storage key after `file_id` is known and passes `255 - file_id.length - 2` as the budget so the full `${file_id}__${flatName}` string fits in one filesystem path component. +7 unit tests in files.spec.ts: - Pass-through when no maxLength supplied (cap is opt-in). - Pass-through when flat form fits within maxLength. - Truncation with leaf extension preserved (the regression case). - Leaf-only overflow with extension preservation. - Pathological long-extension fallback (whole-key truncation). - No-extension stem truncation. - Boundary equality (off-by-one guard). +1 integration test in process.spec.js: processCodeOutput passes the file_id-aware budget (`255 - file_id.length - 2`) to flattenArtifactPath. 114/114 across files.spec.ts + Files/Code (49 + 65). * 🛡️ fix: Determinize + clamp artifact-path truncation (codex review P2 ×2) Two follow-ups to Codex review on the path/flat-key cap: 1. **Deterministic truncation suffixes**. The previous helpers used `crypto.randomBytes(3)` for the disambiguator, mirroring `sanitizeFilename`'s shape. That made the truncated form non- deterministic: a re-upload of the same long filename would compute a *different* storage key, orphaning the previous on-disk file under the reused `file_id` returned by `claimCodeFile`. New `deterministicHexSuffix(input)` helper hashes the input with SHA-256 and takes the first 6 hex chars. Same input → same suffix (storage key stable across re-uploads); different inputs sharing a truncation prefix still get different suffixes (collision avoidance). 24 bits ≈ 16M values is collision-safe for our scale (single-digit artifacts per turn per (filename, conversationId) bucket). Applied to `truncateLeafSegment`, `truncateDirSegment`, and `flattenArtifactPath` — every truncation site in the new helpers. `sanitizeFilename` (pre-existing) is intentionally left alone; its tests rely on the random-bytes mock and it's outside this PR's scope. 2. **Final clamp on flattenArtifactPath result**. The old `Math.max(1, maxLength - ext.length - 7)` floor could let the result slip past `maxLength` when the extension was nearly as large as the budget (e.g. `maxLength=5`, `ext=".txt"`: budget computed as 0, but result was `-<6 hex>.txt` = 11 chars). Drop the `Math.max(1, …)` floor and add a final `truncated.slice(0, maxLength)` so the contract holds for any input. Also short-circuit `maxLength <= 0` to `''` for pathological budgets. Tests updated to compute the expected hash inline (the existing `randomBytes` mock doesn't apply to the new code path), plus 4 new regression tests: - sanitizeArtifactPath: same input → same output, different inputs → different outputs (determinism + collision avoidance). - flattenArtifactPath: same input → same output, different inputs sharing a truncation prefix → different outputs. - flattenArtifactPath: clamp holds when ext.length > maxLength - 7. - flattenArtifactPath: returns '' for maxLength <= 0. 53 unit tests pass. 65 integration tests pass. * 🛡️ fix: Total-path cap + basename for classifier (codex P2 + comprehensive review) Four follow-ups from the latest reviews on this PR: 1. **Codex P2: total-path cap in sanitizeArtifactPath**. Per-segment caps weren't enough — a deeply nested path (3+ at-cap segments) can still produce a joined form past Mongo's 1024-byte indexed-key limit (4.0 and earlier reject; later versions configurable). Added `ARTIFACT_PATH_TOTAL_MAX = 512` and a leaf-only fallback when the joined form exceeds it. Same shape as the absolute-path / `..`-traversal fallbacks above; the leaf is already segment-capped to ≤255, so the final result stays within bounds. 2. **Codex P2: pass basename to classifier/extractor in process.js**. With the path-preserving sanitizer, `safeName` can now be a nested string like `reports.v1/Makefile`. The classifier's `extensionOf` reads that as `v1/Makefile` (the slice after the dot in the directory name) and the bare-name branch rejects because it sees a `.` anywhere. Result: extensionless artifacts under dotted folders (Makefile, Dockerfile, etc.) get misclassified as `other` and skip text extraction. Pass `path.basename(safeName)` to both `classifyCodeArtifact` and `extractCodeArtifactText` so classification matches what the old flat-name flow produced. 3. **Review nit: drop dead `sanitizeFilename` mock in process.spec.js**. process.js no longer imports `sanitizeFilename`; the mock was misleading dead code. 4. **Review nit: rename misleading `'embedded parent traversal'` test**. `path.posix.normalize('a/../escape.txt')` resolves to `escape.txt` which goes through the normal segment-split path, not the `sanitizeFilename` fallback. Test name now says "resolves embedded parent traversal via path normalization" to match the actual code path. +3 regression tests: - sanitizeArtifactPath falls back to leaf-only when joined > 512. - sanitizeArtifactPath keeps nested path within the 512 budget. - process.spec: passes basename (`Makefile` from `reports.v1/Makefile`) to classifyCodeArtifact + extractCodeArtifactText. Existing "caps every segment in a deeply-nested path" test now uses 2 segments (not 3) so the joined form stays under the new total cap; the 3-segment scenario is covered by the new fallback test instead. 55 unit + 66 integration = 121/121 pass. * 📝 docs: Correct sanitizeArtifactPath JSDoc to match actual schema index Two doc-only fixes from the latest comprehensive review (both NIT): 1. **Index field list was wrong**. JSDoc claimed the compound unique index was `{ file_id, filename, conversationId, context }`. The actual index in `packages/data-schemas/src/schema/file.ts:92-95` is `{ filename, conversationId, context, tenantId }` with a partial filter for `context: FileContext.execute_code`. The cap rationale (Mongo 4.0 indexed-key limit) is correct and unchanged; just the field list was wrong. Added the schema file path so future readers can find the source of truth. 2. **Trade-off acknowledgement**. The reviewer noted that the leaf-only fallback loses directory structure, which means the model's `cat /mnt/data/<deep>/<path>/file.txt` would 404 on the pathological-depth case — partially re-introducing the original flat-name bug for >512-char paths. This is intentional (DB write failure is strictly worse than losing structure), but the trade-off wasn't called out explicitly in the JSDoc. Added a paragraph acknowledging it and noting that the cap is monotonically better than the pre-PR behavior, where ALL artifacts were treated this way regardless of depth. No code or test changes — pure JSDoc correction. Tests still 55/0. * 🛡️ fix: Disambiguate sanitized artifact names to keep claimCodeFile keys unique (codex P2) `sanitizeArtifactPath` is not injective — multiple raw inputs can collapse onto the same regex-and-normalize output. Codex's example: `reports 2026/out.csv` and `reports_2026/out.csv` both sanitize to `reports_2026/out.csv`. `claimCodeFile` is keyed on the schema's compound unique `(filename, conversationId, context, tenantId)` index, so the later upload silently matches the earlier record and overwrites the first artifact's bytes via the reused `file_id` — a single conversation can drop files when both names are valid in the sandbox. This collision space isn't strictly new — pre-PR `sanitizeFilename` (basename-only) had the same property — but the path-preserving form gives us enough information to fix it for the first time. **Fix.** When character-level sanitization changed something (regex replacement, path normalization, dotfile prefix, empty-segment collapse), embed a deterministic SHA-256 prefix of the **raw input** in the leaf segment via the new `embedDisambiguatorInLeaf` helper. Same raw input → same safe form (idempotent for re-uploads); different raw inputs that would have collided → different safe forms. **Why "character-level"** specifically: - The disambiguator fires when `preCapJoined !== inputName` (post-regex + dotfile + empty-segment, BUT pre-truncation). - Truncation alone is already disambiguated by `truncateLeafSegment`'s own seg-hash; firing the input-hash branch on truncation would just stack a second hash for no collision-avoidance benefit and clutter human-readable filenames. **Three known collision shapes covered:** 1. `out 1.csv` vs `out_1.csv` (and `out@1.csv` vs `out#1.csv`, etc.) 2. `dir//file.txt` vs `dir/file.txt` (empty-segment collapse) 3. `.x` vs `_.x` (dotfile-prefix step) **Disambiguator + truncation interaction:** for very long mutated leaves, `truncateLeafSegment` caps at 255 first, then `embedDisambiguatorInLeaf` re-trims to insert the input hash. The seg-hash from the first pass is replaced by the input-hash from the second pass — that's intentional (input-hash is the load-bearing collision-avoidance suffix; seg-hash was only ever decorative once the input-hash exists). Final clamp ensures the result never exceeds `ARTIFACT_PATH_SEGMENT_MAX` regardless of input. **Disambiguator + total-cap fallback:** when joined > 512, we fall back to the leaf-only form. The leaf has already had the disambiguator embedded, so collision avoidance survives the pathological-depth case. **`embedDisambiguatorInLeaf`** uses `dot <= 1` to detect "no real extension" (covers extensionless names AND dotfile-prefixed leaves like `_.hidden` — without this, `_.hidden` would split as stem `_` + ext `.hidden` and produce the awkward `_-<hash>.hidden`). **Updated 5 existing tests** that asserted the old collision-prone outputs — they now verify the disambiguator-included form. The character-level-only firing rule was load-bearing here: tests for "clean inputs (no mutation)" and "long inputs (truncation only)" still pass without any disambiguator clutter. **+7 regression tests** in a new `collision avoidance (Codex review P2)` describe block: 1. Different raw inputs sanitizing to the same form get distinct safes 2. Whitespace-vs-underscore in directory segment 3. Dotfile-prefix collision 4. Idempotency: same raw → same safe across calls 5. Clean inputs skip the disambiguator (cosmetic guarantee) 6. Disambiguator survives leaf truncation (long mutated leaf) 7. Disambiguator survives total-cap fallback (pathological depth) 62 unit + 66 integration = 128/128 pass.	2026-04-28 12:52:04 +09:00
Danny Avila	24e29aa8cb	🌱 fix: Inject Code-Tool Files Into Graph Sessions on First Call (+ read_file Sandbox Fallback) (#12831) ... * 🌱 fix: Seed Code Tool Files Into Graph Sessions on First Call Files attached to an agent's `tool_resources.execute_code` (user uploads or generated artifacts from a prior turn) were silently dropped on the first `execute_code` invocation of a turn. The agents-side `ToolNode` populates `_injected_files` only when its `sessions` map already has an `EXECUTE_CODE` entry — but that entry is only written by a previous successful execution, so call #1 had nothing to inject. CodeExecutor then fell back to a `/files/{session_id}` fetch, but `session_id` was also empty on call #1, leaving the sandbox without the primed files. Mirror the existing skill-priming pattern (`primeInvokedSkills` → `initialSessions`) for code-resource files: eagerly call `primeFiles` before `createRun` and merge the result into `initialSessions` via a new `seedCodeFilesIntoSessions` helper. Skill files and code-resource files now share the same `EXECUTE_CODE` entry; the prior representative `session_id` is preserved on merge. * 🔬 chore: Add Diagnostic Logging for Code-Files Seeding Temporary debug logs to diagnose why first-call file injection is not firing in real agent runs. Logs `wantsCodeExec`, available tool-resource keys, primed file count, and the seeded EXECUTE_CODE entry. Will revert once the failure mode is identified. * 🪛 refactor: Capture primedCodeFiles per-agent at init, merge across run Replace the client.js eager `primeFiles` call with a per-agent capture at initialization time so every agent in a multi-agent run (primary + handoff + addedConvo) contributes its `tool_resources.execute_code` files to the shared `Graph.sessions` seed. - handleTools.js (eager loadTools): the `execute_code` factory closes over a `primedCodeFiles` slot and surfaces it in the return. - ToolService.js loadToolDefinitionsWrapper (event-driven): captures `files` from the existing `primeCodeFiles` call (was dropping them while only keeping `toolContext`) and surfaces them. - packages/api initialize.ts: the loadTools callback contract now includes `primedCodeFiles`, threaded onto `InitializedAgent`. - client.js: iterate `[primary, ...agentConfigs.values()]` and merge each agent's `primedCodeFiles` into `initialSessions`. Drop the primary-only `primeCodeFiles` call and diagnostic logs from the prior attempt — wrong layer (single-agent), wrong gate (`agent.tools` contained Tool instances after init, so the `.includes("execute_code")` string check always failed). * 🔬 chore: Add per-agent diagnostic logs for code-files seeding Logs `tool_resources` keys + file counts inside loadToolDefinitionsWrapper and per-agent `primedCodeFiles` + final initialSessions inside AgentClient. Will revert once the failure mode is confirmed. * 🔬 chore: Add file-lookup diagnostics inside initializeAgent Logs the inputs and intermediate counts of the conversation-file lookup chain (convo file ids, thread message ids, code-generated and user-code file counts) so we can pinpoint why `tool_resources.execute_code` is arriving empty at `loadToolDefinitionsWrapper` despite the agent having `execute_code` in its tools list. * 🔬 chore: Probe execute_code files without messageId filter Adds a relaxed `getFiles({conversationId, context: execute_code})` probe that runs only when `getCodeGeneratedFiles` returns empty. Lists what's actually in the DB for this conversation so we can confirm whether the file is missing entirely or whether the messageId filter is rejecting it. * 🔬 chore: Fix probe getFiles arg order (sort vs projection) Probe was passing a projection object as the sort arg, which mongoose rejected with `Invalid sort value`. Move it to the third arg (selectFields) so the probe actually runs. * 🪢 fix: Preserve Original messageId on Code-Output File Update Each `processCodeOutput` call was overwriting the persisted file's `messageId` with the *current* run's id. When a turn re-creates an existing file (filename + conversationId match → `claimCodeFile` returns the existing record, `isUpdate=true`), the file's link to the assistant message that originally produced it gets clobbered. `initializeAgent` later runs `getCodeGeneratedFiles({messageId: $in: <thread>})` to seed `tool_resources.execute_code` from prior-turn artifacts. With a stale `messageId` (e.g. from a failed read attempt that re-shelled the same filename), the file no longer matches the parent-walk thread, so `tool_resources` arrives empty at agent init, the new `primedCodeFiles` channel has nothing to seed, and the LLM can't see its own prior-turn artifacts on the next turn — defeating the just-added Graph-sessions seeding fix. Preserve the existing `claimed.messageId` on update; first-creation behavior is unchanged. The runtime return value still includes the current run's `messageId` (via `Object.assign(file, { messageId })`) so the artifact is correctly attributed to the live tool_call. * 🧹 chore: Remove diagnostic logs from code-files seeding path Drops the temporary debug logs added to trace the empty-tool_resources failure mode. Production code paths (loadToolDefinitionsWrapper, client.js seed loop, initializeAgent file lookup) are left as the permanent shape: capture primedCodeFiles, merge across agents, seed initialSessions before run start. * 🪛 feat: read_file Sandbox Fallback for /mnt/data + Non-Skill Paths When the model called `read_file` with a code-execution path (e.g. `/mnt/data/sentinel.txt`), the handler returned a misleading `Use format: {skillName}/{path}` error. Adds a sandbox-aware fallback: - Short-circuit `/mnt/data/...` (can never be a skill reference) → route to a sandbox `cat` via the new host-provided `readSandboxFile` callback, which POSTs to the codeapi `/exec` endpoint. - Skip the skill resolver entirely when `accessibleSkillIds` is empty — the resolved-output of `resolveAgentScopedSkillIds` already collapses the admin capability + ephemeral badge + persisted `skills_enabled` chain, so an empty value is the authoritative "skills aren't in scope for this agent" signal. - For `{firstSegment}/...` paths, consult the catalog-derived `activeSkillNames` Set (no DB read) to detect non-skill names and fall through to the sandbox before the model has to retry with `bash_tool`. `activeSkillNames` is captured from `injectSkillCatalog`, threaded onto `InitializedAgent`, into `agentToolContexts`, then through `enrichWithSkillConfigurable` into `mergedConfigurable` for the handler. The host implementation of `readSandboxFile` lives in `api/server/services/Files/Code/process.js` and shells `cat <path>` through the seeded sandbox session — `tc.codeSessionContext` (emitted by ToolNode for `read_file` calls in `@librechat/agents` v3.1.72+) provides the `session_id` + `_injected_files` so the read lands in the same sandbox that holds prior-turn artifacts. When the seeded context isn't available (older agents version, no codeapi configured), the handler returns a model-visible error pointing at `bash_tool` instead of silently failing. Tests: 8 new `handleReadFileCall` cases cover the new short-circuits, the skills-not-enabled gate, the activeSkillNames lookup, the sandbox-fallback success path, and the bash_tool retry hint on fallback failure. Existing `read_file` tests now opt into "skills are in scope" via a `skillsInScope()` fixture (production wouldn't reach the skill lookup with empty `accessibleSkillIds`). * 🔧 chore: Update @librechat/agents dependency to version 3.1.72 Bumps the version of the @librechat/agents package across package-lock.json and relevant package.json files to ensure compatibility with the latest features and fixes. * 🪛 refactor: Centralize Tool-Session Seed in buildInitialToolSessions Helper Addresses review feedback on the per-agent merge in client.js: - **Run-wide semantics, named explicitly.** The merge into a single `Graph.sessions[EXECUTE_CODE]` was a deliberate match to the agents-library design (`Graph.sessions` is shared across every `ToolNode` in the run), but the inline `for (const a of agents)` loop in `AgentClient.chatCompletion` made it look per-agent. Move the logic to a TS helper `buildInitialToolSessions` that documents the run-wide-by-design contract in one place. The CJS controller now contains a single call site, no business logic. - **Subagent walk (P2).** The previous loop only iterated `[primary, ...agentConfigs.values()]`. Pure subagents are pruned out of `agentConfigs` after init and retained on each parent's `subagentAgentConfigs`, so their primed code files were silently dropped from the seed. The helper now walks recursively, with a visited-Set keyed on object identity that terminates safely on a malformed agent graph (cycle). - **`jest.setup.cjs` polyfill for undici `File`.** Reviewer hit `ReferenceError: File is not defined` running the targeted spec on WSL — a known Node 18 issue where `globalThis.File` from `node:buffer` isn't auto-exposed. Polyfill it inside a Jest setup file so the suite boots regardless of Node patch version. Helper test coverage (8 new): skill-only / agent-only / both, recursive subagent walk, cycle-safe walk, primary+subagent deduplication, undefined/null entries in the agents iterable, and representative session_id preservation across the merge. 16 tests pass total in `codeFilesSession.spec.ts` (8 prior + 8 new). No behavior change vs. the previous commit for the existing primary+agentConfigs case — subagent inclusion is the only new behavior, and it matches what the existing seeding logic would have done if subagents had been in `agentConfigs`. * 🪛 fix: FIFO Walk Order in buildInitialToolSessions (P3 review) The traversal used `Array.pop()` (LIFO), which visited the LAST top-level agent first. The docstring says "primary first"; the code contradicted it. When no skill seed exists the first-visited agent's first file supplies the representative `session_id` written to `Graph.sessions[EXECUTE_CODE]` — so a LIFO walk silently flipped which agent that came from. `ToolNode` ultimately uses per-file `session_id`s for runtime injection (so behavior was indistinguishable for current callers), but the discrepancy was a footgun for any future consumer that read the representative. Switch to FIFO via `Array.shift()` to match both the docstring and the existing `loadSubagentsFor` walk pattern in `Endpoints/agents/initialize.js`. Add a regression test that asserts the primary's `session_id` is the representative (and that all three agents' files still contribute, with per-file `session_id`s preserved). * 🔬 test: Lock In Code-Files Bug Fixes Per Comprehensive Review Addresses MAJOR + MINOR + NIT findings from the multi-pass review: **Finding #4 (MINOR) — empty relativePath misses sandbox fallback.** A model calling `read_file("output/")` where "output" isn't a skill name dead-ended with `Missing file path after skill name` instead of being routed to the sandbox like every other malformed-path branch. Add the same `codeEnvAvailable → handleSandboxFileFallback` pattern, plus two regression tests. **Finding #7 (NIT) — duplicate `skillsInScope()` helper.** Hoist the identical helper out of two nested describe blocks to module scope. Single source of truth. **Finding #1 (MAJOR) — `persistedMessageId` had zero test coverage.** The fix preserves a file's original `messageId` on update so `getCodeGeneratedFiles` can still match it on subsequent turns. A regression in the `isUpdate ? (claimed.messageId ?? messageId) : messageId` ternary would silently re-introduce the original cross-turn priming bug. Five new tests cover: - UPDATE preserves `claimed.messageId` in the persisted record - UPDATE falls back to current run id when `claimed.messageId` is absent (legacy records predating the field) - CREATE uses current run id (no claimed record exists) - The runtime return value uses the LIVE id (artifact attribution) even when the persisted record kept the original - The image branch follows the same contract (would silently regress if the ternary diverged across the two file-build branches) The tests use a `snapshotCreateFileArgs()` helper because `processCodeOutput` mutates the file object after `createFile` returns (`Object.assign(file, { messageId, toolCallId })`) and a naive `createFile.mock.calls[0][0]` would reflect the post-mutation state instead of what was actually persisted. **Finding #2 (MAJOR) — `readSandboxFile` had no direct tests.** The model-controlled `file_path` flows through a POSIX single-quote escape into a shell `cat` command, making this a security boundary. A quoting regression would let a malicious filename break out of the quoted argument and inject arbitrary shell. 20 new tests across: - Shell quoting (7): plain filenames, embedded `'`, `$()`, backticks, newlines, shell metachars, multiple consecutive single-quotes - Payload shape (6): /exec URL, bash language, conditional session_id / files inclusion, dedicated keepAlive:false agents - Response handling (6): `{content}` on success, null on missing base URL or absent stdout, throws on stderr-only, partial-success returns stdout, transport errors are logged then rethrown - Timeout (1): matches processCodeOutput's 15s SLA Audited findings #5 (acknowledged tech debt — readSandboxFile in JS workspace), #6 (pre-existing positional-args debt on enrichWithSkillConfigurable), and #8 (cosmetic JSDoc style) — no action taken per the reviewer's own assessment. Audited finding #3 (walk order vs docstring) — already addressed in commit 007f32341 which converted to FIFO via `queue.shift()` plus a regression test. The audit was performed against an earlier PR head. Tests: 152 packages/api + 195 api JS = 347 pass. Typecheck clean. * 🪛 fix: Pure-Subagent codeEnv + Primed-Skill Routing + ToolService Early Returns Three findings from the second-pass review: **P2 — Pure subagents missed `codeEnvAvailable`** (initialize.js). The pure-subagent init path didn't forward the endpoint-level `codeEnvAvailable` flag to `initializeAgent`, unlike the primary, handoff, and addedConvo paths. A code-enabled subagent loaded only through `subagentAgentConfigs` initialized with `codeEnvAvailable: false`, so even though the recursive seed walk found its primed code files, the subagent's own `bash_tool` / `read_file` sandbox fallback were silently gated off. Forward the flag and add `codeEnvAvailable: config.codeEnvAvailable` to the `agentToolContexts.set` for symmetry with the other paths. **P2 — Primed skills outside the catalog cap were misrouted to sandbox** (handlers.ts). Manual ($-popover) and always-apply primes are intentionally resolved off the wider `accessibleSkillIds` ACL set BEFORE catalog injection — see `resolveManualSkills` for why a skill outside the `SKILL_CATALOG_LIMIT` cap can still be authorized for direct manual invocation. The `activeSkillNames` shortcut ran before reading `skillPrimedIdsByName`, so a primed skill not in the catalog would fall through to the sandbox instead of resolving via the pinned `_id`. Read the primed map first and bypass the shortcut for primed names. New regression test asserts a primed-but-not- cataloged skill resolves through the existing skill path with `getSkillByName` invoked and `readSandboxFile` NOT called. **P3 — `loadAgentTools` early returns dropped `primedCodeFiles`** (ToolService.js). The non-`definitionsOnly` path captures the field correctly, but two early-return branches (no-action-tools fast path, no-action-sets fast path) omitted it. Any traditional `loadAgentTools(..., definitionsOnly: false)` caller using execute_code without action tools would have its first-call session seed silently empty. Add `primedCodeFiles` to both early returns for consistency with the final return shape. Tests: 153 packages/api + 195 api JS = 348 pass. * 🧹 chore: Document jest.mock arrow-indirection pattern in process.spec.js Per the second-pass review's Finding #2 (NIT, "would help future readers"): the mock setup mixes direct `jest.fn()` references with arrow-function indirection (`(...args) => mockX(...args)`). The indirection isn't stylistic — it's required because `jest.mock(...)` is hoisted above the outer `const` declarations at parse time, so a direct reference would capture `undefined`. Inline comment explains the pattern so the next reader doesn't have to reverse-engineer it or accidentally "simplify" the mocks and break per-test `mockReturnValueOnce` / `mockImplementationOnce` overrides. * 🪛 fix: Five Issues from Pass-N + Codex Review (incl. 404 root cause) Five real bugs surfaced by another review pass + Codex PR comments + the codeapi-side logs we collected during manual testing: **1) `processCodeOutput` 404 root cause (`callbacks.js`).** The codeapi worker emits TWO distinct `session_id`s on a tool result: - `artifact.session_id` is the EXEC session — the sandbox VM that ran the bash command. Files don't live there; it's torn down post-execution. - `file.session_id` is the STORAGE session — the file-server bucket prefix where artifacts actually live. `callbacks.js` was passing the EXEC id to `processCodeOutput`, which builds `/download/{session_id}/{id}` and 404s because the file-server doesn't know about that path. This explains every "Error downloading/processing code environment file" we saw during testing. Use `file.session_id ?? output.artifact.session_id` (per-file id with artifact-level fallback for older worker payloads). **2) `primeFiles` reupload pushed STALE sandbox ids (`process.js`).** When `getSessionInfo` returns null (file expired/missing in sandbox), `reuploadFile` re-uploads via `handleFileUpload`, gets a NEW `fileIdentifier`, and persists it on the DB record. But `pushFile` was a closure capturing the OLD `(session_id, id)` parsed at the top of the loop, so the in-memory `files[]` array (now consumed by `buildInitialToolSessions` to seed `Graph.sessions`) silently referenced a sandbox object that no longer existed. The first tool call would 404 trying to mount it; only the next turn's metadata re-read would correct course. Parameterize `pushFile` with optional `(session_id, id)` overrides; in `reuploadFile` parse the new identifier and pass through. 2 regression tests. **3) Codex P2 — Cap sandbox fallback output before line-numbering (`handlers.ts`).** The new `handleSandboxFileFallback` returned `addLineNumbers(result.content)` without a size guard, so reading a multi-MB `/mnt/data/*` artifact materialized the file twice in memory (raw + line-numbered) before downstream truncation. Match the existing skill-file path's `MAX_READABLE_BYTES` (256KB): truncate raw first, then number, surface the truncation to the model so it can use `bash_tool` (`head` / `tail`) for the rest. 2 tests (oversized truncates with hint, in-cap doesn't). **4) Codex P2 — Dedupe seeded code files by `(session_id, id)` (`codeFilesSession.ts`).** Multiple agents in a run commonly carry the same primed execute-code resources (shared conversation files); without dedupe, `_injected_files` grows proportionally to agent count and bloats every `/exec` POST. Use a `(session_id, id)` identity key so first-seen wins (preserves source ordering); name alone isn't sufficient because two distinct primed uploads can share a filename across different sessions. 4 tests covering dedup across iterations, against pre-existing entries, name-collision distinct-session preservation, and the multi-agent realistic case in `buildInitialToolSessions`. **5) Pass-N P2 — Polyfill `globalThis.File` in api Jest setup (`api/test/jestSetup.js`).** `packages/api/jest.setup.cjs` had the polyfill; the legacy api workspace's Jest config has its own `setupFiles` that didn't, so on Node 18 / WSL the api focused tests still failed at import time with `ReferenceError: File is not defined` from undici. Mirror the polyfill. Tests: 159 packages/api + 206 api JS = 365 pass. Typecheck clean. * 🔧 chore: Update @librechat/agents dependency to version 3.1.73 Bumps the version of the @librechat/agents package across package-lock.json and relevant package.json files to ensure compatibility with the latest features and fixes.	2026-04-27 08:56:39 +09:00
Danny Avila	8c073b4400	📄 feat: Auto-render Text-Based Code Execution Artifacts Inline (#12829) ... * 📄 feat: Auto-render Text-Based Code Execution Artifacts Inline Eagerly extract text content from non-image artifacts produced by code execution tools and render it inline in the message instead of behind a click-to-download file card. Reuses the SkillFiles binary-detection helper and the existing parseDocument dispatcher so docx, xlsx, csv, html, code, and other text-renderable formats land directly under the tool call. PPTX is intentionally classified but not yet extracted — follow-up. * 🌐 chore: Remove unused com_download_expires locale key Removed in en/translation.json so the detect-unused-i18n-keys CI check passes. The only reference was a commented-out localize() call in LogContent.tsx that was deleted in the previous commit. * 🩹 fix: Address PR review on code artifact text extraction - extract.ts: build the temp document path from a randomUUID and pass path.basename(name) as originalname so a malicious artifact name cannot escape os.tmpdir() (P1 traversal flagged by codex/Copilot). - process.js: classify and extract using safeName, not the raw name — defense in depth alongside the temp-path fix. - classify.ts: add a bare-name lookup so extensionless text artifacts (Makefile, Dockerfile, …) classify as utf8-text instead of falling through to other. - Attachment.tsx: wire aria-expanded / aria-controls on the show-all toggle for screen reader support. - LogContent.tsx: restore a download chip (LogLink) on inline-text attachments so users can still pull down the underlying file. - Tests: cover extensionless filenames and the temp-path traversal invariant. * 🩹 fix: Address comprehensive PR review on code artifact extraction - extract.ts: walk back to a UTF-8 code-point boundary before truncating so cuts cannot land mid-multibyte and emit U+FFFD (CJK/emoji concern). truncate() now accepts the original buffer to skip a redundant encode. - extract.ts: add an 8s timeout around parseDocument via Promise.race so a pathological docx/xlsx cannot stall the response path. - process.js: always set `text` (string or null) on the file payload — createFile uses findOneAndUpdate with $set semantics, so omitting the field leaves a stale value behind when an artifact's content changes. - Attachment.tsx: switch the show-all toggle from char-count threshold to a useLayoutEffect ref measurement on scrollHeight, and use overflow-hidden when collapsed (overflow-auto when expanded) so the collapsed box has a single clear interaction model. - Attachment.tsx + LogContent.tsx: lift `isImageAttachment` / `isTextAttachment` into a shared attachmentTypes module. LogContent keeps its looser image check (no width/height required) because the legacy log surface receives attachments without dimensions. - Tests: cover multi-byte boundary, the always-set-text contract on updates, and the new shared predicates. * 🧪 test: Component test for TextAttachment + direct withTimeout coverage - Attachment.tsx: re-order local imports longest-to-shortest per AGENTS.md (attachmentTypes ahead of FileContainer/Image). - extract.ts: export withTimeout so it can be unit-tested directly (it's also used internally — exporting carries no runtime cost). - extract.spec.ts: three small unit tests on withTimeout that cover resolve, propagated rejection, and timeout rejection paths with real timers. - TextAttachment.test.tsx: ten cases for the new React component — text rendering in <pre>, download chip presence/absence, ref-based collapse measurement (with scrollHeight stubbed via prototype), aria-expanded toggle, fall-through to FileAttachment for missing and empty text, and AttachmentGroup routing. * 🩹 fix: Canonicalize document MIME by extension before parseDocument When the classifier puts a file on the document path via its extension (.docx, .xlsx, …) but the buffer sniffer returned a generic value like application/zip or application/octet-stream, we previously forwarded that generic MIME to parseDocument, which dispatches strictly by MIME and silently rejected it — exactly defeating the extension-first classification this PR added. extractDocument now remaps the MIME from the extension (falling back to the original sniffed MIME if the extension is unrecognized, so files that reached the document branch via MIME detection still work). Adds a parameterized test across docx/xlsx/xls/ods/odt against zip/octet sniffs to guard the regression. * 🩹 fix: Reuse existing withTimeout from utils/promise The previous commit's local withTimeout export collided with the already-exported `withTimeout` from `~/utils/promise`, breaking the @librechat/api tsc job (TS2308 ambiguous re-export). Drops the duplicate, imports from `~/utils/promise`, and removes the now-redundant unit tests (the helper has its own coverage in utils/promise.spec.ts). The third argument shifts from a label to the fully-formed timeout error message that the existing helper expects. * 🧹 chore: TextAttachment test polish (NITs) - Use the conventional `import Attachment, { AttachmentGroup }` form rather than `default as Attachment`. - Save the original `scrollHeight` property descriptor and restore it in afterAll, so the prototype patch never leaks past this suite.	2026-04-26 02:04:00 -07:00
Danny Avila	596f806f60	🛡️ fix: Strict Opt-In Skills Activation per Agent (#12823) ... * 🛡️ fix: Strict opt-in skills activation per agent Skills were activating on every agent run that had the capability + RBAC enabled, regardless of whether the user (ephemeral) or author (persisted) had opted in. `scopeSkillIds(undefined)` fell through to "full accessible catalog" whenever `agent.skills` was unset, which is the default state for any agent created before skills existed and for every ephemeral agent. Activation now requires an explicit signal: - Ephemeral agent → per-conversation skills badge toggle. - Persisted agent → new `skills_enabled` master switch on the agent doc, surfaced as a toggle in the Agent Builder skills section. Enabled + empty/undefined allowlist = full accessible catalog; enabled + non-empty allowlist = narrow to those ids; disabled (or undefined) = no skills available, even if an allowlist is set. Centralised the predicate in `resolveAgentScopedSkillIds` so the primary-agent path, handoff/discovery, the subagent loop, and both OpenAI controllers all share one source of truth. Frontend `$` popover scope mirrors the same logic so the UI never offers skills the backend would refuse to activate. * test: mock resolveAgentScopedSkillIds in agent controller specs * refactor: address review findings on skills opt-in PR - AgentConfig: associate skills label with toggle via htmlFor for click/keyboard affordance; simplify Switch handler to Boolean(value). - skills: mark scopeSkillIds as @internal so runtime callers continue to route through resolveAgentScopedSkillIds and inherit the activation predicate (ephemeral toggle, persisted skills_enabled). * fix(agents): include skills_enabled in agent list projection Without this field, agents loaded via the list endpoint hydrate into the client agentsMap with skills_enabled === undefined, causing the `$` skill popover to hide every skill on a fresh page load even when the agent was saved with skills_enabled: true. * fix(skills): fail closed for persisted agents during agentsMap hydration Returning undefined while the agents map loads let the popover render the full catalog for a persisted agent before we could read its skills_enabled flag, so the user could pick a skill the backend would then refuse for the turn. Match the strict opt-in contract by returning [] until the map is authoritative. * refactor(skills): extract skillsHintKey for readability Replaces the nested ternary in the skills section JSX with a pre-computed constant so the activation -> hint key mapping reads top-down. * refactor(skills): unflatten skillsHintKey to remove nested ternary	2026-04-25 04:02:01 -04:00
Danny Avila	d83cb84f59	🪆 feat: Subagent configuration in Agent Builder (#12725) ... * 🪆 feat: Subagents configuration (isolated-context child agents) Surfaces the new @librechat/agents `SubagentConfig` primitive in the Agent Builder. Subagents let a supervisor delegate a focused subtask to a child graph running in an isolated context window: verbose tool output stays in the child, only a filtered summary returns to the parent. Data model: new `subagents: { enabled, allowSelf, agent_ids }` on Agent, wired through the Zod, Mongoose, and form schemas plus a new `AgentCapabilities.subagents` capability (enabled by default). Backend: `initialize.js` loads explicit subagent configs alongside handoff agents, and drops subagent-only references from the parallel/handoff maps so they don't leak into the supervisor's graph. `run.ts` emits `SubagentConfig[]` on the primary `AgentInputs` — a self-spawn entry when `allowSelf` is enabled plus one entry per configured agent. UI: an "Advanced" panel section with an enable toggle, a self-spawn toggle, and an agent picker (capped at 10). Enabling without adding agents still yields self-spawn; disabling self-spawn with no agents shows a warning. A capability flag gates the whole section. * 🪆 feat: Stream subagent progress to UI (dialog + inline ticker) Pairs with the @librechat/agents SDK change that forwards child-graph events through the parent's handler registry (danny-avila/agents#107): - Self-spawn and explicit subagents can now use event-driven tools, because child `ON_TOOL_EXECUTE` dispatches reach our ToolService via the parent's registered handler. - The same forwarding path wraps the child's run_step / run_step_delta / run_step_completed / message_delta / reasoning_delta dispatches in a new `ON_SUBAGENT_UPDATE` envelope, with start/stop/error bookends. Backend: `callbacks.js` registers an `ON_SUBAGENT_UPDATE` handler that forwards each envelope straight to the SSE stream. Frontend: - `useStepHandler` consumes `ON_SUBAGENT_UPDATE` events and merges them into a per-tool_call Recoil atom (`subagentProgressByToolCallId`). First-seen `subagentRunId` claims the most-recent unclaimed `subagent` tool call in the active response message — a temporal mapping, no SDK wire-format change needed to correlate child runs with parent tool calls. - New `SubagentCall` part component replaces the default `ToolCall` rendering when `toolCall.name === Constants.SUBAGENT`: compact status ticker showing the 3 most recent update labels, clickable to open a dialog with the full activity log + final markdown-rendered result. - Adds `Constants.SUBAGENT`, `StepEvents.ON_SUBAGENT_UPDATE`, and `SubagentUpdateEvent` type in data-provider. Tests: - `packages/api npx jest run-summarization` — 23 pass - `api npx jest initialize` — 16 pass - `npm run build` — clean Dependency note: bumps `@librechat/agents` to `^3.1.67-dev.1` — requires the SDK PR (danny-avila/agents#107) to be merged to dev and published before this PR merges. `ON_SUBAGENT_UPDATE` is absent from dev.0, so the handler registration would be a no-op with the older SDK but would not crash. * 🪆 fix: address Codex review and review audit on subagents Stacks on top of the SDK change in danny-avila/agents#107 (bumped to `^3.1.67-dev.2`). - **P1 (`initialize.js`)**: subagent-only agents were being deleted from both `agentConfigs` AND `agentToolContexts`. The tool-execute handler resolves execution context (agent, tool_resources, skill ACLs) from `agentToolContexts`, so explicit subagents would run without their configured resources and skip action tools. Now only `agentConfigs` is pruned — tool context stays intact. - **P2 (`AgentSubagents.tsx`)**: toggling subagents off set the form field to `undefined`; `removeNullishValues` stripped it from the PATCH, leaving the server copy enabled. Now it persists an explicit `{ enabled: false, ... }` so the update actually clears state. - **Finding 1 (MAJOR)** — `agent_ids` Zod schema gains `.max()` via a new `MAX_SUBAGENTS` export from `data-provider` (shared with the UI cap). Crafted payloads can't trigger hundreds of `processAgent` calls. - **Finding 2 (MAJOR)** — `subagentProgressByToolCallId` atomFamily atoms are now tracked in a ref and reset from `clearStepMaps` via a `useRecoilCallback({ reset })`. No monotonic growth across a session. - **Finding 3 (MAJOR)** — early-arriving `ON_SUBAGENT_UPDATE` events whose parent `tool_call_id` is not yet mapped are now buffered in `pendingSubagentBuffer` (keyed by `subagentRunId`) and replayed in arrival order once correlation completes. Mirrors the existing `pendingDeltaBuffer` pattern. - **Finding 4 (MAJOR)** — switched to deterministic correlation via the new `parentToolCallId` that SDK `3.1.67-dev.2` threads through from `ToolRunnableConfig.toolCall.id`. Temporal fallback now iterates oldest-unclaimed-first (forward), matching tool-call creation order, so concurrent spawns map correctly. - **Finding 6 (MINOR)** — `agent_ids` are deduped on the backend via `new Set(...)` before the load loop. Duplicates no longer produce duplicate `SubagentConfig` entries visible to the LLM. - **Finding 7 (MINOR)** — events array inside each Recoil atom is capped at 200 entries. Long-running subagents no longer replay O(n) spreads on every update; the dialog log still shows the cap window. - **Finding 8 (MINOR)** — documented: subagents are loaded only for the primary agent this release (handoff children get self-spawn but not explicit sub-subagents). In-code comment added so the next maintainer doesn't wonder. - **Finding 9 (NIT)** — removed `{!isSubmitting && null}` dead code and the misleading announce-polite comment in `SubagentCall`. - New `validation.spec.ts` — 9 tests covering the cap on `agent_ids.length` at the subagent schema, agent-create, and agent-update layers. - `run-summarization` — 23 pass, `initialize` — 16 pass, total backend package: 103 pass across touched areas. Findings 5 (component tests) and 10 (micro-allocation) are tracked but deferred; the former needs a Recoil-RenderHook harness that isn't in this PR's scope, and the latter has negligible impact (one `Array.from` per subagent run). * 🧪 test: integration coverage for subagent correlation + backend loading Addresses the follow-up audit on #12725 with real-code tests (no mock handlers, only the existing setMessages/getMessages spies and the standard mongodb-memory-server harness). Six new tests under a dedicated `describe('subagent loading')`: - loads a configured subagent, populates `subagentAgentConfigs`, keeps it out of `agentConfigs` - **P1 regression guard**: drives the real `toolExecuteOptions.loadTools` closure with the subagent id and asserts `loadToolsForExecution` is called with `agent: <subagent>`, `tool_resources`, `actionsEnabled`. If anyone deletes `agentToolContexts` again, this fails. - dedup: three copies of the same id load the agent once - overlap: agent referenced both as handoff target and subagent stays in `agentConfigs` - capability gate: admin disabling `subagents` suppresses loading even when the agent has a config - per-agent disable: `subagents.enabled: false` skips loading entirely Five new tests under `describe('on_subagent_update event')` using a real `RecoilRoot` and a companion `useRecoilCallback` reader so writes from the hook are observable: - deterministic correlation via `parentToolCallId` (happy path with SDK dev.2+) - fallback: oldest-unclaimed tool call wins for concurrent spawns without `parentToolCallId` - early-arrival buffer: updates with no mapping get buffered and replayed once the tool call appears - event cap: 205 updates collapse to 200 retained, oldest dropped - `clearStepMaps` resets tracked atoms back to their null default - F2 — added explicit `// TODO` marker for handoff-subagent-loading extension (matches the comment that referenced it). - F3 — dropped the unnecessary `MAX_SUBAGENTS as MAX_SUBAGENTS_CAP` alias; just import the constant directly. - Bumped `@librechat/agents` to `^3.1.67-dev.3` to pick up the SDK's paired test additions. - `api/server/services/Endpoints/agents/initialize.spec.js` — 22 pass (6 new + 16 existing) - `packages/api/src/agents/validation.spec.ts` + `run-summarization.test.ts` — 103 pass - `client/src/hooks/SSE/__tests__/useStepHandler.spec.ts` — 48 pass (5 new + 43 existing) * 🪆 fix: strip parent run summary + discovered tools from subagent inputs Codex P1 on #12725: `buildSubagentConfigs` reused the shared `buildAgentInput` factory for each explicit child, and that factory always stamps the parent run's `initialSummary` (cross-run conversation summary) and `discoveredTools` (tool names the parent's LLM searched earlier) onto every `AgentInputs` it returns. When subagents were enabled on a conversation that had already been summarized, every child inherited that summary — silently defeating the isolated-context contract and burning extra tokens on unrelated prior chat. Fix in `run.ts`: after `buildAgentInput(child)`, explicitly clear `childInputs.initialSummary` and `childInputs.discoveredTools` before attaching to the `SubagentConfig`. The parent keeps both — that's how the supervisor receives cross-turn context — but the child starts fresh. Paired with danny-avila/agents#107 (bumped to `^3.1.67-dev.4`), which adds the equivalent strip inside `buildChildInputs` to cover the self-spawn path where the SDK clones parent `_sourceInputs` directly and LibreChat never sees the intermediate shape. Belt and suspenders. Regression test (new): - `does NOT leak the parent run initialSummary into an explicit child (Codex P1 regression)` — sets `initialSummary` on the run, enables subagents with an explicit child, asserts the parent still has the summary but `childConfig.agentInputs.initialSummary` is `undefined`. Same for `discoveredTools`. 24 pass. * 🪆 fix: capability gate applies to handoff agents + parallel subagent test ### Codex P2 — handoff agents kept `subagents` after capability disabled The endpoint-level `AgentCapabilities.subagents` gate only cleared `subagents` on `primaryConfig`. Handoff agents loaded into `agentConfigs` retained their persisted `subagents.enabled: true`, and because `run.ts` calls `buildSubagentConfigs` for every agent input, self-spawn would still fire on a handoff target even when the admin had disabled the capability globally. Fix in `initialize.js`: after the subagent loading block, when the capability is off, iterate `agentConfigs.values()` and clear `subagents` + `subagentAgentConfigs` on every loaded config. Regression test: `clears subagents on handoff agents too when capability is disabled (Codex P2 regression)` — seeds a handoff target with its own `subagents.enabled: true`, disables the capability at the endpoint, asserts both primary AND handoff have `subagents` undefined in the client args. 23 init tests pass. ### Parallel subagent correlation — user-requested verification Added `keeps parallel subagent streams independent when events interleave` to `useStepHandler.spec.ts`. Two `subagent` tool calls seeded side by side, 6 interleaved `ON_SUBAGENT_UPDATE` envelopes dispatched (a-start, b-start, a-step, b-step, a-stop, b-step), each carrying its own `parentToolCallId`. Asserts each `tool_call_id`'s Recoil bucket accumulates only its own run's events, statuses reflect each run independently (`call_a` → stop, `call_b` → run_step), no cross-contamination. 49 step-handler tests pass. * 🪆 fix: SubagentCall detects cancelled / errored states (Codex P2) Codex P2 on #12725: the old `running` check only consulted `initialProgress` and the subagent's phase. A user stop, dropped stream, or backend crash before a terminal `stop`/`error` envelope arrived would leave the ticker permanently stuck on "working…". Other *Call components (ToolCall.tsx) already model this via `!isSubmitting && !finished` → cancelled. Mirror that pattern. Re-introduce `isSubmitting` on `SubagentCallProps` (the prop was dropped earlier as 'unused' — that was a bug) and resolve status as a tri-state: - `finished` — initialProgress >= 1, or subagent `stop`/`error` - `cancelled` — `!isSubmitting && !finished` - `running` — neither New locale keys `com_ui_subagent_cancelled` + `com_ui_subagent_errored` swap in the right header text per state. Tests: new `SubagentCall.test.tsx` covers all four states with a real `RecoilRoot` and a `useRecoilCallback` seeder — no mocked store — 5/5 pass. Includes an explicit P2 regression test that simulates the `isSubmitting=false, progress.status='run_step', initialProgress<1` scenario and asserts the cancelled label renders. * 🪆 feat: semantic ticker + aggregated content-part dialog for subagents Two rounds of feedback on #12725: ### Ticker — user-readable lines, not raw event names The old ticker showed \`on_run_step\`, \`on_message_delta\`, etc. — not meaningful to users. Replaced with \`buildSubagentTickerLines\`, a pure helper that walks the \`SubagentUpdateEvent\` stream and emits: - message/reasoning deltas → a single live "Writing: <last 60 chars>" (or "Reasoning: …") line that updates in place as chunks arrive - run_step with tool_calls → "Using calculator(expression=42*58)" for a single call, "Using tool: a, b" for parallel (args dropped when multiple so the line stays short) - run_step_completed → "calculator → 42*58 = 2436" (output truncated to 48 chars; falls back to "Tool X complete" when output is empty) - error → "Error: <message>" - start / stop / run_step_delta → suppressed (too granular / lifecycle-only) Args and output pass through \`summarizeArgs\` / \`summarizeOutput\` which flatten JSON to \`key=value\` pairs and head-truncate long strings so a 200-line tool output never bloats the ticker. ### Dialog — aggregated content parts via leaf renderers \`aggregateSubagentContent\` folds the raw event stream into \`TMessageContentParts[]\` — text/reasoning delta streaks collapse into single \`TEXT\` / \`THINK\` parts, tool calls become \`TOOL_CALL\` parts, and \`run_step\` boundaries correctly break text runs around tool calls. The dialog iterates those parts through a \`SubagentDialogPart\` renderer that delegates to the existing \`Text\`, \`Reasoning\`, and \`ToolCall\` leaf components — the same sub-components \`<Part />\` uses — wrapped in a minimal \`MessageContext\` so reasoning expand state and cursor animation work. Leaf components are used directly rather than importing \`<Part />\` itself to avoid a module cycle (Part → Parts/index → SubagentCall → Part) and to sidestep a hypothetical nested-subagent rendering. ### Tests - \`subagentContent.test.ts\` — 19 pure-function tests covering the aggregator (text concat, reasoning concat, tool call lifecycle, interleaving, phase suppression, late-arriving completions) and the ticker builder (live preview truncation, args/output snippets, parallel-call handling, output truncation, i18n formatter override). - \`SubagentCall.test.tsx\` — 9 component tests: 5 status-resolution (existing) + 2 ticker (semantic text, delta collapse) + 2 dialog (aggregated parts routed to leaf renderers, raw-output fallback). ### Locale keys New: \`com_ui_subagent_ticker_writing\`, \`…_reasoning\`, \`…_error\`, \`…_using\`, \`…_using_with_args\`, \`…_tool_complete\`, \`…_tool_output\`. Preserves i18n at the display layer while the helper stays pure. * chore: drop unused com_ui_subagent_activity_log locale key The dialog no longer renders an "Activity log" section — the new content-parts renderer replaced it. Also tweaks the dialog description copy to match. * 🪆 fix: subagent dialog order, persistence, auto-scroll, width Follow-up pass addressing the four issues observed in real runs against a live subagent-using parent. ### Aggregator ordering (reasoning appearing after text it preceded) Reproducible pattern: LLM emits reasoning → text → tool call in that order, but the dialog rendered text BEFORE reasoning in the content array. Root cause: `aggregateSubagentContent` maintained `currentText` and `currentThink` buffers in parallel and only flushed them at a `run_step` boundary in a fixed (text, think) order, losing the actual arrival order. Fix: when a text chunk arrives, close any open think buffer first (pushes it into the content array right then); symmetric for think → text. Two new regression tests cover the exact reasoning → text → tool_call sequence from the screenshot and the repeated reasoning ↔ text flow across a turn. ### Content persists after completion (markdown not rendering when done) `clearStepMaps` was calling `resetSubagentAtoms()` at stream end, which wiped every `subagentProgressByToolCallId` entry. Once reset, `contentParts.length === 0` and the dialog fell back to rendering the raw `output` string with plain text — hence the literal `##`/`**` in the completed-state screenshot. Stopped resetting; the atoms are bounded per-call (200-event cap) and per-conversation (one per subagent spawn) so growth matches the rest of the conversation state. `resetSubagentAtoms` is kept for a future conversation-switch caller. Also: routed the raw-`output` fallback (older subagent runs recorded before the event forwarder existed) through the same `SubagentDialogPart` → `Text` leaf that content parts use, so its markdown renders the same way. ### Auto-scroll to bottom while running Added a `scrollRef` on the dialog body and a `useEffect` that pins `scrollTop = scrollHeight` while the dialog is open AND the subagent is running. Triggers on `contentParts.length` (new tool calls / part boundaries) and `events.length` (intra-part deltas) so the cursor tracks text streaming. Disabled post-completion so re-opening a finished run doesn't yank to the bottom. ### Wider dialog Went from `max-w-2xl` (42rem / 672px — too cramped on maximized laptop windows) to `w-[min(95vw,64rem)] max-w-[min(95vw,64rem)]`. Narrow on phones, scales up to 64rem on desktop, always leaves a bit of margin from the viewport edge. Bumped `max-h-[65vh]` on the scroll area to give the extra width room to breathe vertically too. ### Tests - `subagentContent.test.ts` — 21 pass (2 new ordering regressions). - `useStepHandler.spec.ts` — 49 pass (1 updated to assert atoms are *preserved* on clearStepMaps). - `SubagentCall.test.tsx` — 9 pass (unchanged; aggregator-level tests cover the ordering). * 🪆 feat: persist subagent_content via SDK createContentAggregator Per-request map of createContentAggregator instances keyed by the parent's tool_call_id. ON_SUBAGENT_UPDATE handler feeds each event into the matching aggregator (phase → GraphEvent mapping); AgentClient harvests contentParts onto the subagent tool_call at message save so the child's reasoning / tool calls / final text survive a page refresh. Reusing the SDK's battle-tested aggregator instead of a bespoke one keeps the persisted shape identical to the parent graph's output and drops ~100 lines of custom aggregation code. * 🪆 fix: incremental subagent aggregation + dialog render parity **Disappearing tool_calls**: the Recoil atom trimmed events to a 200-long rolling window, so verbose subagents could shed the `run_step` that originally created a tool_call part — rebuilding content from the trimmed window then produced only the surviving text/reasoning. Fix: fold each envelope into `contentParts` incrementally in the atom as it arrives (new `foldSubagentEvent` + cursor state). Event trim window now affects only the ticker, never the dialog. **Render parity**: dialog now applies `groupSequentialToolCalls` and renders single parts through `Container` + grouped batches through `ToolCallGroup` — same spacing and "Used N tools" collapsing the main message view uses. **Width**: `min(96vw, 80rem)` — wider on big screens, still responsive. **Labels**: "Subagent: X" is jargon. Named subagents render as `Running "{name}" agent` / `Ran "{name}" agent` (past tense on completion); self-spawns use `Running subtask` / `Ran subtask` since `Running "self" agent` reads badly. * 🪆 polish: subagent dialog parity + agent avatar in header **Labels**: drop "subtask" framing. Self-spawn shows `Running agent` / `Ran agent` (past tense on completion); named subagents stay `Running "X" agent` / `Ran "X" agent`. **Dialog render parity**: stop wrapping every part in `Container`. TEXT keeps its `Container` (gap-3 + `mt-5` sibling margin), THINK and TOOL_CALL render bare so their own wrappers set the full-column width the regular message view gives them — matches the main `<Part>` dispatch. Outer scroll region now uses `px-4 py-3` padding and a `max-w-full flex-grow flex-col gap-0` inner wrapper, mirroring the `MessageParts` container the main conversation uses. **Avatar**: header icon now renders the subagent's configured avatar via `MessageIcon` when `useAgentsMapContext()` has the child agent, falling back to the `Users` SVG (which keeps its running-state pulse). Same icon-left-of-label pattern the tool UI uses. * 🪆 polish: subagent group label, ticker throttle + tail-ellipsis, scroll button **Grouped label**: ToolCallGroup now detects all-subagent batches and labels them "Running N agents" / "Ran N agents" instead of "Used N tools". Mixed batches keep the existing label. The tool-name summary is suppressed for all-subagent groups (every entry dedupes to "subagent", which adds nothing). **Ticker width + tail-ellipsis**: raise the preview cap to 300 chars so wide containers aren't half-empty, and flip the ticker `<li>` to `dir="rtl"` so `text-overflow: ellipsis` clips the *oldest* characters (visually the left edge) — the newest tokens stay pinned to the right regardless of container width. Bidi lays out the Latin text LTR internally, the rtl only affects which side gets the ellipsis. **Throttle**: `useThrottledValue` hook (trailing-edge, 1.2s) smooths the live `Writing: …` preview so tokens no longer strobe past the eye faster than they can be read. Ref-based internals (not `useState`) avoid infinite-update loops when the upstream value is a new-reference each render; `NEGATIVE_INFINITY` sentinel ensures the very first value passes through synchronously so tests and first paint aren't delayed. **Scroll-to-bottom**: dialog tracks `isAtBottom` with a 120px threshold; auto-scroll only engages when the user is already following along, and a persistent jump-to-latest button appears whenever they scroll up — no more fighting the auto-scroll to read back. * 🪆 polish: snappier ticker, prefix-safe labels, agents icon, readable lines **Ticker lines are now incrementally aggregated in the atom** — same pattern as contentParts. The raw-events rolling window is gone; event volume no longer caps what the ticker can display. Verbose subagents that used to drop early tool_call lines out of the window now keep the full 3-line history (using_tool, tool_complete, writing). **Discriminated-union ticker lines** split a constant prefix (e.g. "Writing:") from a tail-truncatable body. The prefix lives in a `shrink-0` span so it never gets clipped when the body overflows; the body uses `dir="rtl"` only on itself — scoped so non-streaming lines (e.g. "Waiting for first update…") can't get their trailing ellipsis flipped by bidi. **Content-aware throttle**: 800ms interval (down from 1200ms), skipped entirely while the live buffer is below 120 chars. Early tokens now appear immediately — no more "Reasoning: I" sitting blank for a full second before the next heartbeat. Once the preview is long enough to fill the container, throttling kicks in at the tighter interval. **Header label** is now a constant verb + optional muted sub-label. Base reads "Running agent" / "Ran agent" / "Cancelled agent" / "Agent errored" for every subagent; named subagents get the configured agent name rendered to the right in secondary text (self-spawns and unresolved names omit it — "Running self agent" is nonsense). **ToolCallGroup** now detects `allSubagents` and swaps `StackedToolIcons` for a single `Users` glyph — otherwise the group header shows a wrench ("tool") icon next to "Ran 5 agents", which reads wrong. * 🪆 feat: delimiter-aware tool labels in ticker + full-width tool lines New shared `parseToolName` helper in `client/src/utils/toolLabels.ts` — single source of truth for splitting `<tool>_mcp_<server>` ids and mapping native tool names (web_search, execute_code, …) to their friendly translation keys. `ToolCallGroup` drops its inline copy and pulls from this helper. Ticker tool lines now use the shared parser + a new `ToolIdentifier` sub-renderer so the live log reads like the main tool UI: - MCP tool → `<server> · <code-badge:tool>` (e.g. "github · `search_code`") - Native → friendly name from `TOOL_FRIENDLY_NAME_KEYS` - Unknown → bare `<code>` badge of the raw id The `using_tool` / `tool_complete` rows now render with a `flex w-full items-baseline gap-1 overflow-hidden` layout matching the writing/reasoning rows — they take the full container width instead of collapsing to content size. Output snippets on `tool_complete` get the same tail-side `dir="rtl"` ellipsis so the newest characters stay flush-right when the container is narrow. Dropped the now-unused template i18n keys (`com_ui_subagent_ticker_using_with_args`, `com_ui_subagent_ticker_tool_complete`, `com_ui_subagent_ticker_tool_output`) in favor of tokens the JSX composes structurally. Only English is touched per the project rule; other locales follow externally. * 🪆 fix: dialog scroll button + auto-scroll during streaming deltas Two race/trigger bugs in the dialog's scroll behavior: **Button never showed**: `addEventListener('scroll', …)` in a `useEffect` ran before Radix's portal had actually committed the scroll container, so `scrollRef.current` was still null — the listener never attached, `isAtBottom` stayed stuck at its initial `true`, and the jump-to-latest button was never rendered. Swap to React's `onScroll` prop on the element itself so the handler wires up as part of DOM commit, not a post-commit effect. **Auto-scroll stalled during text streaming**: the pin-to-bottom effect only re-fired on `contentParts.length` changes. Message/reasoning deltas extend the last TEXT/THINK part's `.text` without changing the array length — so the view would drift up as tokens piled in and never catch back up. Replace the length-dep effect with a `ResizeObserver` on the inner content div; every height change (new part or in-place growth) triggers a scroll-pin when the user is still at the bottom. * 🪆 fix: drop leading ellipsis from ticker body truncatePreview was prepending ... to the tail when the buffer exceeded 300 chars. The component's CSS already produces a left-side ellipsis for overflow via dir=rtl + text-overflow: ellipsis — stacking a data-level ellipsis on top renders a stray dot character right after the Writing: / Reasoning: label (Writing: .Sure!), which looks like a typo to the reader. Data now returns just the last 300 chars when truncating; CSS handles the visual cue whenever the body actually overflows its container. * 🪆 fix: Codex review — subagent isolation + concurrent-safe throttle Three findings from the @codex review pass, all valid: **P1 — buildAgentInput leaks parent discovered-tool state into subagent children.** `buildAgentInput` mutates `agent.toolRegistry` (`overrideDeferLoadingForDiscoveredTools` flips `defer_loading:true→false` on tools the parent previously searched for) and appends those tools' definitions to the returned `toolDefinitions` before the function returns. `buildSubagentConfigs` was clearing the reported `initialSummary` / `discoveredTools` fields on the returned AgentInputs, but that happened post-return — the registry writes and extra tool definitions persisted on the child, silently defeating context isolation and inflating the child's prompt. Fix: `buildAgentInput` now takes an `isSubagent` flag that gates the registry-mutation block and omits `initialSummary` / `discoveredTools` at the source. `buildSubagentConfigs` passes `{ isSubagent: true }` for every explicit child; no post-hoc cleanup needed. **P2 — ToolCallGroup labels a finished subagent group as still running when the child returned no output.** `getToolMeta` computed `hasOutput` as `!!tc.output`, which is `false` for a completed subagent that returned empty text (the UI already has an "empty result" fallback for that case). `allCompleted` would stay `false` and the group header stuck on "Running N agents" forever. Fix: treat `tc.progress === 1` as completion too — progress is the authoritative lifecycle signal, output is just content. **P2 — useThrottledValue schedules `setTimeout` during render.** Discarded renders under Strict Mode / Concurrent rendering would leave orphan timers firing against stale trees. Fix: move `setTimeout` into a `useEffect` keyed on `[value, intervalMs, enabled]`. Render-time still mutates refs (idempotent), but timer scheduling lives post-commit. Cleanup on unmount and on passthrough transitions is preserved. * 🪆 fix: Codex P2 — wipe subagent atoms on conversation switch `clearStepMaps()` intentionally doesn't reset `subagentProgressByToolCallId` so a user can reopen a completed subagent's dialog mid-conversation, but `resetSubagentAtoms` was defined and never exposed / called — so each completed run's aggregated `contentParts` + `tickerState` stayed resident in the `atomFamily` for the whole app session. Unbounded growth across multi-conversation sessions. Expose `resetSubagentAtoms` from `useStepHandler` and fire it from `useEventHandlers` whenever the URL's `conversationId` changes. That's the correct cleanup boundary: historical subagent dialogs rehydrate from persisted `subagent_content` on each `tool_call` at message-save time, so wiping live atoms on switch doesn't lose any viewable history — it just releases per-tool-call state that the old conversation's components no longer subscribe to. * 🪆 fix: Codex round 3 — subagent registry isolation + post-run label Two more valid findings. **P1 — parent-order registry mutation leaks into subagent inputs.** `overrideDeferLoadingForDiscoveredTools` mutates `agent.toolRegistry` in place (the Map *and* the LCTool objects inside it). When an agent appears both as a handoff target (normal graph node) AND an explicit subagent child, a subagent build that ran before the parent's build captures a reference to the same registry — the parent's later mutation leaks through to the child. Fix: for subagent children (`isSubagent`), clone the `toolRegistry` Map and shallow-clone each LCTool inside before returning the inputs. `defer_loading` flips on parent-graph registry mutations can't propagate across the clone boundary. `toolDefinitions` also gets a shallow-copy pass so the same isolation holds for definitions the child carries directly. **P2 — "Running N agents" label stuck after cancel/error.** ToolCallGroup's all-subagent label was gated only on `allCompleted`, which requires every child to have `hasOutput || progress === 1`. A subagent that gets cancelled (stream ends, no `stop` phase, no output) never satisfies that — so even after `isSubmitting` flips false, the header stays on "Running N agents" while each individual card correctly shows "Cancelled agent". Fix: derive a `subagentsDone` flag as `allCompleted || !isSubmitting` and gate the past-tense label on that. Matches the tri-state each SubagentCall card already resolves (finished / cancelled / running). * 🪆 fix: Codex P2 — ACL-check subagents.agent_ids on create/update Codex flagged that `subagents.agent_ids` was accepted as arbitrary strings on the create/update routes while `edges` got a `validateEdgeAgentAccess` pass — so users could save subagent references to agents they can't VIEW. At runtime `initializeClient`'s `processAgent` ACL gate silently drops those, so the persisted configuration and the actual behavior diverged in a way that is difficult to diagnose. Refactor: extract the id-set → unauthorized-ids check into a shared `collectUnauthorizedAgentIds`, wrap it with a dedicated `validateSubagentAccess`, and plumb the same 403-on-failure response the edge path already returns. Applied on both POST /agents and PATCH /agents/:id. * 🪆 fix: Codex round 5 — ACL-disable escape hatch + ticker order Two valid findings. **P1 — can't disable subagents after losing access to a child.** The subagent ACL check ran on every create/update that echoed back the `agent_ids` list, even when the user was explicitly disabling the feature. The UI keeps the list intact when toggling `enabled: false`, so a user who subsequently lost VIEW on any child would be locked in a 403 loop — every edit (including the one that turns subagents off) bounces. Fix: gate the ACL check on `subagents.enabled !== false` at both the POST /agents and PATCH /agents/:id handlers. Empty list stays a no-op. Disabling the feature is always permitted. **P2 — ticker fold merges out-of-order previews across delta switches.** `foldSubagentEventIntoTicker` carried `textLineIdx` / `thinkLineIdx` across a reasoning → text → reasoning transition, so the second reasoning chunk appended to the original reasoning line instead of starting a new chronological one. Fix: close the opposite buffer + cursor when a delta-type switch is detected (same rule the content-parts reducer already applies). Added a regression test. * 🪆 fix: Codex round 6 — preserve mid-stream atoms + honor sequential suppression Two valid findings. **P2 — atom reset fires on initial chat URL assignment.** `useEventHandlers` initialized `lastConversationIdRef` from the URL's current `paramId`, then reset subagent atoms whenever the ref and `paramId` disagreed. For a brand-new conversation the URL stamp goes from `undefined → "abc123"` while the first response is still streaming, which used to drop subagent ticker/content state mid-run and leave dialogs missing earlier updates. Fix: only reset when *both* the old and new IDs are non-null and differ — i.e. a user-initiated switch between two established conversations. The initial assignment passes through without clearing. **P2 — ON_SUBAGENT_UPDATE bypassed `hide_sequential_outputs`.** Every other streaming handler in `callbacks.js` (`ON_RUN_STEP`, `ON_MESSAGE_DELTA`, etc.) gates emission on `checkIfLastAgent` + `metadata?.hide_sequential_outputs`, but the subagent forwarder did an unconditional `emitEvent` — so intermediate agents in a sequential chain were leaking their children's activity to the client even when the chain was configured to suppress intermediates. Fix: accept `metadata` and apply the same `isLastAgent || !hide_sequential_outputs` gate. Aggregation still runs regardless of visibility (persistence + dialog depend on it); only the SSE forward is suppressed. * 🪆 fix: Codex P2 — gate subagent ACL check on endpoint capability `validateSubagentAccess` ran on every create/update where `subagents.enabled !== false`, regardless of the endpoint-level `subagents` capability. When the capability is off at the appConfig level, `initializeClient` already strips the `subagents` block at runtime — so persisted `agent_ids` are inert — but the validation could still 403 on a legacy record whose referenced child is no longer viewable, blocking unrelated edits. Fix: add `isSubagentsCapabilityEnabled(req)` that reads the agents endpoint's capabilities from `req.config` and gate both the create and update ACL checks on it. Capability-off environments can update agents with stale `subagents` data freely; capability-on keeps the full ACL protection. * 🪆 fix: Codex P2 — reset subagent atoms on id→null navigation too Previous guard (both-established) skipped the reset whenever `paramId` became null/undefined, so navigating from an existing chat to a "new chat" route left stale subagent progress resident in the `atomFamily` until the user picked a specific different chat. Swap the both-established check for a one-time flag: skip only the very first `undefined → id` transition (the brand-new-chat URL stamp that happens mid-stream), then reset on any subsequent change — id→id, id→null, null→id-after-reset. If the user started on an established chat the flag is true at mount, so the guard is a no-op and every navigation resets normally. * 🪆 fix: Codex round 9 — subagent persistence gate + handoff children Two valid findings. **P1 — hide_sequential_outputs also gates persistence.** The previous fix gated the SSE forward on `isLastAgent || !hide_sequential_outputs` but still ran the per-tool-call `createContentAggregator` aggregation unconditionally. `finalizeSubagentContent` would then attach the hidden intermediate agent's child reasoning / tool output to the saved message, so a page refresh could reveal activity that was intentionally suppressed live. Move the visibility gate to the top of the handler — hidden agents now skip both aggregation and emission, so "hide_sequential_outputs" is a consistent "don't record" rule for subagent traces. **P2 — handoff agents' explicit subagents were silently dropped.** `initializeClient` only resolved `subagentAgentConfigs` for the primary config, so an agent used via handoff that had its own `subagents.agent_ids` saved in the builder would get self-spawn only; every explicit child was quietly ignored, creating a saved-config / runtime mismatch the user couldn't diagnose. Extract the resolution into a shared `loadSubagentsFor(config)` helper and invoke it for the primary and every handoff agent in `agentConfigs`. The `edgeAgentIds` precomputation stays outside the helper (it's loop-invariant). Capability-off shortcuts return empty early so the existing strip-on-capability-off path still holds. * 🪆 fix: Codex P2 — recursive subagent build for multi-level delegation Previously only the outer `agents[]` loop attached `subagentConfigs` to its inputs, so a child used as a subagent (invoked via the `subagent` tool) lost every explicit spawn target of its own. A user-valid configuration like A → B → C would only run the top layer; B could never actually delegate to C from inside A's run. Recursively build `subagentConfigs` for each child inside `buildSubagentConfigs`, passing the child's freshly-constructed `childInputs` down so its own `subagents.enabled` children get resolved too. Added cycle protection via an `ancestors` Set — a configuration like A → B → A is safely cut off at the second encounter of A rather than recursing forever (the existing `child.id === agent.id` guard already prevents the direct self-loop). * 🪆 fix: Codex P2 — reset subagent atoms on useEventHandlers unmount The effect that resets subagent atoms only fired on `paramId` change, so unmounting the chat container (route change away from /c) never flushed the atoms. `knownSubagentAtomKeys` lives in a ref inside `useStepHandler` — once the hook unmounts the ref is gone, so a subsequent remount can't clean atoms it never registered. Added a second `useEffect` that only runs cleanup on unmount (empty deps aside from the stable `resetSubagentAtoms` callback). Keeps `atomFamily` bounded across full route teardowns too. * 🪆 fix: Codex round 13 — cyclic subagent guard + prefer persisted Two valid findings. **P1 — cyclic subagent ref reloads the primary.** A configuration like `A ↔ B` (B lists A as its own subagent) would send `loadSubagentsFor` down a path that couldn't find A in `agentConfigs` (the primary isn't stored there), so it called `processAgent(A)` a second time. That inserts a fresh config for the primary id, which downstream duplicates in `[primary, ...agentConfigs.values()]` and can replace the primary's tool context with the reloaded copy. Fix: short-circuit when a subagent ref points back at `primaryConfig.id` — reuse the already-loaded primary config. Primary is always an edge id so no pruning bookkeeping needed. **P2 — live atom preferred over canonical persisted trace.** The dialog picked `progress.contentParts` ahead of `persistedContent`, but the Recoil bucket is best-effort — after a disconnect/reconnect it can be stale or partial. The server's `subagent_content` on the `tool_call` is the canonical record refreshed on sync. Preferring live could hide completed tool/reasoning history that was actually persisted. Fix: flip the preference order. Persisted wins when it's non-empty; live covers the mid-stream window (before the parent message saves, persisted is empty) and the older-runs fallback. Updated the test that enforced the old order to lock the new semantics in (separate mid-stream live-fallback assertion kept). * 🪆 fix: Codex P2 — subagent atom reset rule simplified to 'leaving established id' The `hasEstablishedConversationRef` + check for initial undefined→id covered the first navigation but missed the equivalent mid-stream URL stamp when a user goes from an existing chat to a new chat and sends a message there (`id → null → newId`). The null → newId transition was still hitting the reset branch and wiping the in-flight subagent ticker/content for that first turn. Simpler rule: only reset when the PREVIOUS paramId is an established id. Every transition AWAY from an established chat clears (id→id2, id→null, id→undefined); every transition FROM null/undefined passes through (initial mount, new-chat URL stamp mid-stream). Drop the `hasEstablishedConversationRef` machinery in favor of that single condition. * 🪆 fix: Codex P2 — match runtime's strict subagent enable check in ACL Runtime (`initializeClient` + `run.ts`) treats `subagents?.enabled` as a truthy predicate — `undefined`, `null`, missing, and `false` all short-circuit. The ACL gate was using `!== false` which accepted `undefined` / missing as "enabled" and could 403 a payload whose subagent tool would be inert at runtime. Swap both create and update to `enabled === true`. Only a strictly- enabled payload triggers the ACL check; the disable path (`false`) still passes through so a user who lost VIEW on a child can still save the disable edit. * 🪆 fix: Codex P2 — reject missing subagent references with 400 `validateSubagentAccess` collapsed through `collectUnauthorizedAgentIds`, which returns an empty list for ids with no DB record — so typos and references to deleted agents passed validation silently, and `initializeClient` later dropped them at runtime. Saved config would then list spawn targets that the backend never honored, a hard-to- diagnose drift. Refactor the helper into `classifyAgentReferences(ids, …)` which returns `{ missing, unauthorized }` separately. `validateEdgeAgentAccess` keeps its old semantics (missing is intentional — a self-referential `from` names the agent being created). `validateSubagentReferences` surfaces both buckets so the create/update handlers can 400 on missing and 403 on unauthorized with distinct error messages and `agent_ids` lists. * 🪆 polish: tighten subagent dialog grid gap to gap-2 OGDialogContent's grid default is `gap-4`, which renders the title, description, and scroll area as three visually separated panels. Drop to `gap-2` so they read as one block. * 🪆 polish: swap Subagents above Handoffs in Advanced panel Subagents is the more common knob users reach for, so show it first. Handoffs keep the same Controller wiring, just move below.	2026-04-25 04:02:01 -04:00
Danny Avila	35bf04b26c	🧰 refactor: Unify code-execution tools (#12767) ... * 🛠️ feat: Add registerCodeExecutionTools helper Idempotently registers `bash_tool` + `read_file` in the run's tool registry and tool-definition list via a registry `.has()` dedupe. Sets up the single code-execution tool path shared by: - `initializeAgent` (when an agent has `execute_code` in its tools and the capability is enabled for the run) - `injectSkillCatalog` (when skills are active; unconditional read_file, bash_tool follows `codeEnvAvailable`) Both callers reach the helper in the same initialization sequence, so the second call becomes a no-op and exactly one copy of each tool reaches the LLM — no more double registration for agents that combine `execute_code` capability with active skills. Unit-tested on a fresh run, idempotence (second call, overlap with prior tooldefs, partial overlap), and the no-registry variant. * 🔀 refactor: Route injectSkillCatalog bash_tool + read_file through registerCodeExecutionTools The `skill` tool is still registered inline (it's skill-path-specific), but `bash_tool` + `read_file` now flow through the shared idempotent helper so a prior registration from the execute_code path doesn't produce a duplicate copy later in the same run. Behavior preserved: - `read_file` always registers when any active skill is in scope — manually-primed `disable-model-invocation: true` skills still need it to load `references/*` from storage. - `bash_tool` follows `codeEnvAvailable` exactly as before. Adds a test pinning the cross-call dedupe: when `injectSkillCatalog` runs AFTER `registerCodeExecutionTools` has already seeded the registry + tool definitions with bash_tool/read_file, the resulting `toolDefinitions` still contains exactly one copy of each. * 🪄 feat: Expand `execute_code` tool name into bash_tool + read_file at initialize-time When an agent's `tools` include `execute_code` and the `execute_code` capability is enabled for the run, `initializeAgent` now registers `bash_tool` + `read_file` via `registerCodeExecutionTools` before `injectSkillCatalog`. The legacy `execute_code` tool definition is no longer handed to the LLM — `execute_code` remains on the agent document as a capability-trigger marker, but the runtime expands it into the skill-flavored tool pair. Call ordering matters: the `execute_code` registration runs BEFORE `injectSkillCatalog`, so the skill path's own `registerCodeExecutionTools` call inside `injectSkillCatalog` becomes a no-op via the registry's `.has()` check. Exactly one copy of each tool reaches the LLM whether the agent has: - only `execute_code` (legacy path) - only skills - both No data migration needed — `agent.tools: ['execute_code']` stays in the DB unchanged; the expansion is a runtime operation. Three tests cover the matrix: execute_code + capability on → bash_tool + read_file registered; execute_code + capability off → neither registered; no execute_code + capability on → neither registered. * 🗑️ refactor: Drop CodeExecutionToolDefinition from the builtin registry Removes the legacy `execute_code` entry from `agentToolDefinitions` and the corresponding import. With the initialize-time expansion in place, nothing consults `getToolDefinition('execute_code')` for a tool schema any more — the capability gate still filters on the string `execute_code`, but the actual tool definitions the LLM sees come from `registerCodeExecutionTools` (i.e. `bash_tool` + `read_file`). `loadToolDefinitions` in `packages/api/src/tools/definitions.ts` silently drops `execute_code` when it no longer resolves in the registry — that's the expected path and is now covered by an updated test. No caller of `getToolDefinition('execute_code')` expects a non-undefined result after this change. * 🔌 refactor: Read CODE_API_KEY from env for primeCodeFiles + PTC Finishes the Phase 4 server-env-keyed rollout on the two remaining `loadAuthValues({ authFields: [EnvVar.CODE_API_KEY] })` sites in `ToolService.js`: - `primeCodeFiles` (user-attached file priming on execute_code agents) - Programmatic Tool Calling (`createProgrammaticToolCallingTool`) Both now read `process.env[EnvVar.CODE_API_KEY]` directly, matching `bash_tool`'s pattern. The per-user plugin-auth path is no longer consulted for code-env credentials anywhere in the hot path — the agents library owns the actual tool-call execution and also reads the env var internally. Priming still fires for existing user-file workflows so the legacy `toolContextMap[execute_code]` hint ("files available at /mnt/data/...") stays in the prompt; only the key lookup changed. * 🔧 fix: Type the pre-seeded dedupe-test tools as LCTool CI TypeScript type checks caught `{ parameters: {} }` in the new cross-call dedupe test: `LCTool.parameters` is a `JsonSchemaType`, not `{}`. Use `{ type: 'object', properties: {} }` and type the local registry Map through the parameter-derived shape so the pre-seeded values match what `toolRegistry.set` expects. * 🛡️ fix: Run execute_code expansion before GOOGLE_TOOL_CONFLICT gate Codex review caught a latent regression: the original Phase 8 placement ran `registerCodeExecutionTools` after `hasAgentTools` was computed, so an execute-code-only agent on Google/Vertex with provider-specific `options.tools` populated would no longer trip `GOOGLE_TOOL_CONFLICT` — the legacy `CodeExecutionToolDefinition` used to populate `toolDefinitions` before the guard, but after dropping it from the registry, `toolDefinitions` stayed empty until my expansion ran downstream of the guard. Mixed provider + agent tools would silently flow through to the LLM. Fix moves the `execute_code` expansion to BEFORE `hasAgentTools` computation. `bash_tool` + `read_file` now contribute to the check the same way the legacy `execute_code` def did. Covered by a new test that pins the Google+execute_code+provider-tools scenario — the `rejects.toThrow(/google_tool_conflict/)` path would have silently passed on the prior placement. * 🔗 fix: Thread codeEnvAvailable through handoff sub-agents Round-2 codex review caught the other half of the execute_code expansion gap: `discoverConnectedAgents` omitted `codeEnvAvailable` from its forwarded `initializeAgent` params, so handoff sub-agents with `agent.tools: ['execute_code']` lost the `bash_tool` + `read_file` registration (pre-Phase 8 the legacy `CodeExecutionToolDefinition` would have landed in their `toolDefinitions` via the registry). - Add `codeEnvAvailable?` to `DiscoverConnectedAgentsParams` and forward it verbatim on every sub-agent `initializeAgent` call. - Update the three JS call sites that construct the primary's `codeEnvAvailable` (`services/Endpoints/agents/initialize.js`, `controllers/agents/openai.js`, `controllers/agents/responses.js`) to pass the same flag into `discoverConnectedAgents` — one authoritative source per request. - Two regression tests in `discovery.spec.ts` pin the true/false passthrough so a future refactor that drops the param-forwarding surfaces immediately. Left intentionally unchanged: `packages/api/src/agents/openai/service.ts` (public API helper with no in-repo caller). External consumers of `createAgentChatCompletion` who want code execution should pass a `codeEnvAvailable`-aware `initializeAgent` via `deps` — documenting the full public-API surface is out of scope for this Phase 8 PR. * 🔗 fix: Thread codeEnvAvailable through addedConvo + memory-agent paths Round-3 codex review caught the last two production `initializeAgent` callers missing the Phase-8 capability flag: - `api/server/services/Endpoints/agents/addedConvo.js` (multi-convo parallel agent execution). Added `codeEnvAvailable` to `processAddedConvo`'s destructured params and forwarded it into the per-added-agent `initializeAgent` call. Caller in `api/server/services/Endpoints/agents/initialize.js` passes the same `codeEnvAvailable` it computed for the primary. - `api/server/controllers/agents/client.js` (`useMemory` — memory extraction agent). Computes its own `codeEnvAvailable` from `appConfig?.endpoints?.[EModelEndpoint.agents]?.capabilities` and forwards into `initializeAgent`. Memory agents rarely list `execute_code`, but if one does, pre-Phase 8 they got the legacy `execute_code` tool registered unconditionally — the passthrough restores parity. With this, every production caller of `initializeAgent` explicitly resolves the capability: main chat flow (primary + handoff), OpenAI chat completions (primary + handoff), Responses API (primary + handoff), added convo parallel agents, and memory agents. The one remaining caller, `packages/api/src/agents/openai/service.ts::createAgentChatCompletion`, is a public API helper with no in-repo consumer (external callers must pass a capability-aware `initializeAgent` via `deps`). * 🪤 fix: Remove duplicate appConfig declaration causing TDZ ReferenceError The Responses API controller had TWO `const appConfig = req.config;` bindings inside `createResponse`: one at the top of the function (added by the Phase 4 `bash_tool` decouple) and one inside the try block (added by the polish PR #12760). Because `const` is block-scoped with a temporal dead zone, the inner redeclaration put `appConfig` in TDZ for the entire try block, so any earlier reference inside the try — notably `appConfig?.endpoints?.[EModelEndpoint.agents]?.allowedProviders` at line 348 — threw `ReferenceError: Cannot access 'appConfig' before initialization`. The error was silently swallowed by the outer try/catch, leaving `recordCollectedUsage` unreached and the six `responses.unit.spec.js` token-usage tests failing. Removing the inner redeclaration fixes the six failing tests (verified: 11/11 pass locally post-fix, 0 regressions elsewhere). The outer function-scoped binding already provides `appConfig` to every downstream reference. * 🔗 fix: Thread codeEnvAvailable through the OpenAI chat-completion public API Round-4 codex review (legitimate on the type-safety angle, even though the runtime concern was already covered): the `createAgentChatCompletion` helper defines its own narrower `InitializeAgentParams` interface locally, and the type was missing `codeEnvAvailable`. External consumers who supply a capability-aware `deps.initializeAgent` couldn't route `codeEnvAvailable` through without a type-cast workaround. - Widen the local `InitializeAgentParams` interface to include `codeEnvAvailable?: boolean` (matches the real `packages/api/src/agents/initialize.ts` type). - Derive `codeEnvAvailable` inside `createAgentChatCompletion` from `deps.appConfig?.endpoints?.agents?.capabilities` (the same source the in-repo controllers use) and forward to `deps.initializeAgent`. Uses a string literal `'execute_code'` lookup so this file stays free of a `librechat-data-provider` import — keeping the dependency surface of the public helper minimal. With this, external consumers of `createAgentChatCompletion` who pass `appConfig` with the agents capabilities get `bash_tool` + `read_file` registration automatically; consumers who don't pass `appConfig` retain the existing "explicit opt-in" semantics (the flag stays `undefined`, expansion is skipped). * 🧹 chore: Review-driven polish — observability log, JSDoc DRY, test gaps, no-op allocation Addresses the comprehensive review of PR #12767: - **Finding #1** (MINOR, observability): `initializeAgent` now emits a debug log when an agent lists `execute_code` in its tools but the runtime gate is off (`params.codeEnvAvailable` !== true). The event-driven `loadToolDefinitionsWrapper` path doesn't log capability-disabled warnings, so without this the tool silently vanishes from the LLM's definitions with zero trace. Operators debugging "why isn't code interpreter working?" now get a signal at the initialize layer. - **Finding #5** (NIT, allocation): `registerCodeExecutionTools` now returns the input `toolDefinitions` array by reference on the no-op path (both tools already registered by a prior caller in the same run) instead of allocating a fresh spread array every time. The common dual-call scenario — `initializeAgent` then `injectSkillCatalog` — saves one O(n) copy per request. - **Finding #4** (NIT, DRY): Collapsed the duplicated 6-line JSDoc comment in `openai.js`, `responses.js`, and `addedConvo.js` into either a one-line `@see DiscoverConnectedAgentsParams.codeEnvAvailable` pointer (the two JS call sites) or a compact 3-line block referring back to the canonical source (addedConvo's @param). - **Finding #2** (MINOR, test gap): Added `api/server/services/Endpoints/agents/addedConvo.spec.js` with three cases covering `codeEnvAvailable=true`, `codeEnvAvailable=false`, and omitted (undefined) passthrough. A future refactor that drops the param from destructuring now surfaces here instead of silently regressing multi-convo parallel agents with `execute_code`. - **Finding #3** (MINOR, test gap): Added `api/server/controllers/agents/__tests__/client.memory.spec.js` pinning the capability-flag derivation that `AgentClient::useMemory` uses — six cases covering present/absent/null/undefined config shapes plus an enum-literal pin (`'execute_code'` / `'agents'`). Catches enum renames or config-path shifts that would otherwise silently strip `bash_tool` + `read_file` from memory agents. Finding #7 (jest.mock scoping, confidence 40) left as-is: the reviewer's own risk assessment noted `buildToolSet` doesn't touch the mocked exports, and restructuring a file-level `jest.mock` to `jest.doMock` + dynamic `import()` introduces more complexity than the speculative risk justifies. The existing mock is scoped to the test file and contains the same stubs the adjacent `skills.test.ts` already uses. Finding #6 (PR description commit count) addressed out-of-band via PR description update. All existing tests pass, typecheck clean, lint clean across touched files. New tests: 9 cases across 2 new spec files. * 🧽 refactor: Replace hardcoded 'execute_code' string with AgentCapabilities enum in service.ts Follow-up review (conf 55) caught that `openai/service.ts`'s Phase 8 `codeEnvAvailable` derivation used the literal `'execute_code'` while every in-repo controller uses `AgentCapabilities.execute_code` from `librechat-data-provider`. The file deliberately uses local type interfaces to keep the public API helper's type surface small, but that pattern was never a ban on single-value imports from the data provider — `packages/api` already depends on it. Importing the enum value means a future rename of `AgentCapabilities.execute_code` propagates to this file automatically, matching the in-repo controllers' behavior. Other follow-up findings left as-is per the reviewer's own verdict: - #2 (memory spec mirrors the production expression rather than calling `AgentClient::useMemory` directly): reviewer flagged as "not blocking" / "design-philosophy observation." The test file's JSDoc already explicitly documents the tradeoff and pins the enum literals to catch the most likely drift vector. Standing up `AgentClient` + all its mocks for a one-line regression guard is disproportionate. - #3 (`addedConvo.spec.js` mock signature vs. underlying `loadAddedAgent` arity): reviewer's own confidence 25 noted the mock matches the wrapper's actual call pattern in the production file. Not a real gap. - #4 was self-retracted as a false alarm. * 🗑️ refactor: Fully deprecate CODE_API_KEY — remove all LibreChat-side references The code-execution sandbox no longer authenticates via a per-run `CODE_API_KEY` (frontend or backend). Auth moved server-side into the agents library / sandbox service, so LibreChat drops every reference: **Backend plumbing:** - `api/server/services/Files/Code/crud.js`: `getCodeOutputDownloadStream`, `uploadCodeEnvFile`, `batchUploadCodeEnvFiles` no longer accept `apiKey` or send the `X-API-Key` header. - `api/server/services/Files/Code/process.js`: `processCodeOutput`, `getSessionInfo`, `primeFiles` drop the `apiKey` param throughout. - `api/server/services/ToolService.js`: stop reading `process.env[EnvVar.CODE_API_KEY]` for `primeCodeFiles` and PTC; the agents library handles auth internally. Remove the now-dead `loadAuthValues` + `EnvVar` imports. Drop the misleading "LIBRECHAT_CODE_API_KEY" hint from the bash_tool error log. - `api/server/services/Files/process.js`: remove the `loadAuthValues` call around `uploadCodeEnvFile`. - `api/server/routes/files/files.js`: code-env file download no longer fetches a per-user key. - `api/server/controllers/tools.js`: `execute_code` is no longer a tool that needs verifyToolAuth with `[EnvVar.CODE_API_KEY]` — the endpoint always reports system-authenticated so the client skips the key-entry dialog. `processCodeOutput` called without `apiKey`. - `api/server/controllers/agents/callbacks.js`: `processCodeOutput` invoked without the loadAuthValues round trip, for both LegacyHandler and Responses-API handlers. - `api/app/clients/tools/util/handleTools.js`: `createCodeExecutionTool` called with just `user_id` + files. **packages/api:** - `packages/api/src/agents/skillFiles.ts`: `PrimeSkillFilesParams`, `PrimeInvokedSkillsDeps`, `primeSkillFiles`, `primeInvokedSkills` all drop the `apiKey` param; the gate is purely `codeEnvAvailable`. - `packages/api/src/agents/handlers.ts`: `handleSkillToolCall` drops the `process.env[EnvVar.CODE_API_KEY]` read; skill-file priming is now gated solely on `codeEnvAvailable`. `ToolExecuteOptions` signatures drop apiKey from `batchUploadCodeEnvFiles` and `getSessionInfo`. - `packages/api/src/agents/skillConfigurable.ts`: JSDoc no longer references the env var. - `packages/api/src/tools/classification.ts`: PTC creation no longer gated on `loadAuthValues`; `buildToolClassification` drops the `loadAuthValues` dep entirely (no LibreChat-side callers need it for this path anymore). - `packages/api/src/tools/definitions.ts`: `LoadToolDefinitionsDeps` drops the `loadAuthValues` field. **Frontend:** - Delete `client/src/hooks/Plugins/useAuthCodeTool.ts`, `useCodeApiKeyForm.ts`, and `client/src/components/SidePanel/Agents/Code/ApiKeyDialog.tsx` — the install/revoke dialogs for CODE_API_KEY are fully dead. - `BadgeRowContext.tsx`: drop `codeApiKeyForm` from the context type and provider. `codeInterpreter` toggle treated as always authenticated (sandbox auth is server-side). - `ToolsDropdown.tsx`, `ToolDialogs.tsx`, `CodeInterpreter.tsx`, `RunCode.tsx`, `SidePanel/Agents/Code/Action.tsx` +`Form.tsx`: all API-key dialog trigger refs, "Configure code interpreter" gear buttons, and auth-verification plumbing removed. The "Code Interpreter" toggle is now a plain `AgentCapabilities.execute_code` checkbox — no key-entry gate. - `client/src/locales/en/translation.json`: drop the three `com_ui_librechat_code_api*` keys and `com_ui_add_code_interpreter_api_key`. Other locales are externally automated per CLAUDE.md. **Config:** - `.env.example`: remove the `# LIBRECHAT_CODE_API_KEY=your-key` section and its header. **Tests:** - `crud.spec.js`: assertions flipped to pin "no X-API-Key header" and "no apiKey param". - `skillFiles.spec.ts`: removed env-var save/restore; tests now pin that the batch-upload path is gated solely on `codeEnvAvailable` and that no apiKey is threaded through. - `handlers.spec.ts`: same — just the `codeEnvAvailable` gate pins remain. - `classification.spec.ts`: remove the two tests that asserted `loadAuthValues` was (not) called for PTC. - `definitions.spec.ts`: drop every `loadAuthValues: mockLoadAuthValues` entry from the deps shape. - `process.spec.js`: strip the mock of `EnvVar.CODE_API_KEY`. **Comment hygiene:** - `tools.ts`, `initialize.ts`, `registry/definitions.ts`: shortened stale comment references to "legacy `execute_code` tool" without naming the retired env var. Tests verified: 678 packages/api tests pass, 836 backend api tests pass. Typecheck clean, lint clean. Only remaining CODE_API_KEY mentions in the code are two regression-guard assertions: - `crud.spec.js`: pins "no X-API-Key header" stays absent. - `skillConfigurable.spec.ts`: pins `configurable` never grows a `codeApiKey` field. * 🧹 chore: Remove the last two CODE_API_KEY name mentions in LibreChat Follow-up to the prior full deprecation commit: two tests still named the retired identifier in their regression-guard assertions. - `packages/api/src/agents/skillConfigurable.spec.ts`: drop the "does not inject a codeApiKey key" test. The `codeApiKey` field is gone from the production configurable shape, so an absence-assertion naming it re-introduces the retired identifier in code. - `api/server/services/Files/Code/crud.spec.js`: rename the "without an X-API-Key header" case back to "should request stream response from the correct URL" and drop the `expect(headers).not.toHaveProperty('X-API-Key')` assertion. The surrounding request-shape checks (URL, timeout, responseType) still pin the behavior; the explicit header-absence line was named-after the deprecated contract. Result: `grep -rn "CODE_API_KEY\|codeApiKey\|LIBRECHAT_CODE_API_KEY"` against the LibreChat source tree returns zero hits. The only remaining `X-API-Key` strings in this repo are on unrelated OpenAPI Action + MCP server auth configurations, where the string is user-facing config, not a LibreChat-owned identifier. Tests: 677 packages/api pass (2 pre-existing summarization e2e failures unrelated); 126 api-workspace controller/service tests pass. Typecheck and lint clean. * 🎯 fix: Narrow codeEnvAvailable to per-agent (admin cap AND agent.tools) Before this commit, `codeEnvAvailable` was computed in the three JS controllers as the admin-level capability flag only (`enabledCapabilities.has(AgentCapabilities.execute_code)`) and passed through `initializeAgent` → `injectSkillCatalog` / `primeInvokedSkills` / `enrichWithSkillConfigurable` unchanged. A skills-only agent whose `tools` array didn't include `execute_code` still got `bash_tool` registered (via `injectSkillCatalog`) and skill files re-primed to the sandbox on every turn — wrong, because the agent never opted in to code execution. **Fix:** `initializeAgent` now computes the per-agent effective value once as `params.codeEnvAvailable === true && agent.tools.includes(Tools.execute_code)`, reuses the same boolean for: 1. The `execute_code` → `bash_tool + read_file` expansion gate (previously already consulted `agent.tools`; now shares the single `effectiveCodeEnvAvailable` binding). 2. The `injectSkillCatalog` call (previously got the raw admin flag). 3. The returned `InitializedAgent.codeEnvAvailable` field (new, typed as required boolean). **Controllers (initialize.js, openai.js, responses.js):** store `primaryConfig.codeEnvAvailable` in `agentToolContexts.set(primaryId, ...)`, capture `config.codeEnvAvailable` in every handoff `onAgentInitialized` callback, and read it from the per-agent ctx inside the `toolExecuteOptions.loadTools` runtime closure. The hoisted `const codeEnvAvailable = enabledCapabilities.has(...)` locals in the two OpenAI-compat controllers are gone — they were shadowing the narrowed per-agent value. **primeInvokedSkills:** `handlePrimeInvokedSkills` in `services/Endpoints/agents/initialize.js` now uses `primaryConfig.codeEnvAvailable` (per-agent, narrowed) instead of the raw admin flag. A skills-only primary agent won't re-prime historical skill files to the sandbox even when the admin enabled the capability globally. **Efficiency:** one extra `&&` in `initializeAgent`. No runtime hot-path cost — the `includes()` scan on `agent.tools` was already happening for the `execute_code` expansion gate; it's now just bound to a local. Tool execution closures read `ctx.codeEnvAvailable === true` (property access + strict equality, O(1)). **Ephemeral-agent note:** per-agent narrowing is authoritative for both persisted and ephemeral flows. The ephemeral toggle (`ephemeralAgent.execute_code`) is reconciled into `agent.tools` upstream in `packages/api/src/agents/added.ts`, so `agent.tools.includes('execute_code')` is the single source of truth by the time `initializeAgent` runs. **Tests:** two new regression tests pin the narrowing contract: - `initialize.test.ts` — four-quadrant matrix on `InitializedAgent.codeEnvAvailable` (cap on × agent asks, cap on × doesn't ask, cap off × asks, neither). Catches future refactors that drop either half of the AND. - `skills.test.ts` — `injectSkillCatalog` with `codeEnvAvailable: false` against an active skill catalog must NOT register `bash_tool` even though it still registers `read_file` + `skill`. This is the state a skills-only agent gets post-narrowing. All 191 affected packages/api tests pass + 836 backend api tests pass. Typecheck clean, lint clean. * 🧽 refactor: Comprehensive-review polish — hoist tool defs, pin verifyToolAuth contract, doc appConfig Addresses the comprehensive review of Phase 8. Findings mapped: **#1 (MINOR): `verifyToolAuth` unconditional auth for execute_code** - Added doc comment explicitly stating the deployment contract (admin capability → reachable sandbox; no per-check health probe to keep UI-gate queries O(1)). - New `api/server/controllers/__tests__/tools.verifyToolAuth.spec.js` with 4 regression tests pinning the contract: 1. `authenticated: true` + `SYSTEM_DEFINED` for execute_code. 2. 404 for unknown tool IDs. 3. `loadAuthValues` is never consulted (catches a future revert that would resurface the per-user key-entry dialog). 4. Response `message` is never `USER_PROVIDED`. **#2 (MINOR): `openai/service.ts` undocumented `appConfig` dependency** - Expanded the `ChatCompletionDependencies.appConfig` JSDoc to spell out that omitting it silently disables code execution for agents with `execute_code` in their tools. External consumers of `createAgentChatCompletion` now have the contract documented at the type boundary. **#5 (NIT): `registerCodeExecutionTools` re-allocates tool defs** - Hoisted `READ_FILE_DEF` and `BASH_TOOL_DEF` to module-level `Object.freeze`d constants. The shapes derive entirely from static `@librechat/agents` exports, so a single frozen object per tool is safe to share across every agent init. Eliminates the ~4-property allocations on every call (including the common second-call no-op path). **#6 (NIT): Verbose history-priming comment in initialize.js** - Trimmed the 16-line `handlePrimeInvokedSkills` block to a 5-line summary with `@see InitializedAgent.codeEnvAvailable` pointer. The canonical narrowing explanation lives on the type; the controller comment is just the ACL-vs-capability rationale. **Skipped:** - #3 (memory spec tests a mirror function): reviewer self-dismissed as a design tradeoff; the enum-literal pin already catches the highest-risk drift vector. - #4 (cross-repo contract for `createCodeExecutionTool`): user will explicitly install the latest `@librechat/agents` dev version once the companion PR publishes, so the version pin will be authoritative. - #7 (migration/deprecation note for self-hosters): out of scope per user direction — release notes handle this. Tests verified: 679 packages/api + 840 backend api tests pass. Typecheck + lint clean. * 🔧 chore: Update @librechat/agents version to 3.1.68-dev.1 across package-lock and package.json files This commit updates the version of the `@librechat/agents` package from `3.1.68-dev.0` to `3.1.68-dev.1` in the `package-lock.json` and relevant `package.json` files. This change ensures consistency across the project and incorporates any updates or fixes from the new version.	2026-04-25 04:02:01 -04:00
Danny Avila	7581540ab6	🔌 refactor: Decouple bash_tool from Per-User CODE_API_KEY (#12712) ... * 🔌 refactor: Decouple bash_tool from Per-User CODE_API_KEY Phase 4 of Agent Skills umbrella (#12625): gate bash_tool and skill file priming on the `execute_code` capability only. Thread a boolean `codeEnvAvailable` through `enrichWithSkillConfigurable` and `primeInvokedSkills` in place of the old per-user `codeApiKey` + `loadAuthValues` plumbing. The sandbox API key is the LibreChat- hosted service key — system-level, not a user secret — so the per-user lookup was legacy; when needed, it's read directly from `process.env[EnvVar.CODE_API_KEY]` inside the capability gate. `handleSkillToolCall` and `primeInvokedSkills` gate sandbox uploads on `codeEnvAvailable` first, preventing skill-file uploads to the sandbox when an agent has `execute_code` disabled even if the env var happens to be set. The agents library resolves the env key itself for `bash_tool`, so `ToolService.js` drops the `loadAuthValues` lookup and the "Code execution is not available" placeholder tool in favor of a plain `createBashExecutionTool({})` with a loud error log if the env var is missing. Also fixes a pre-existing `appConfig`-undefined lint error in `responses.js`/`createResponse` that surfaced when this file was touched (declares `const appConfig = req.config` at function top, matching the existing pattern in other controllers). Preserves the `skillPrimedIdsByName` threading added by Phase 3/5/6 and all Phase 3/5/6 call-site signatures. Adds `skillConfigurable.spec.ts` (5 cases pinning the new surface) and `skillFiles.spec.ts` (4-way matrix of capability × env key for `primeInvokedSkills`). * 🧪 refactor: Address Codex Review Feedback Resolves findings from the second codex review on #12712: - MAJOR: `handlers.spec.ts` now covers the `codeEnvAvailable` gate in `handleSkillToolCall` across three cases (gate off, gate on + env set, gate on + env unset). The gate is the critical regression prevention — a future edit that drops it would silently re-enable sandbox uploads for agents with `execute_code` disabled. - MINOR: Hoist `codeEnvAvailable` and `skillPrimedIdsByName` out of `loadTools` closures in `openai.js` and `responses.js`. Both values are fixed once `initializeAgent` resolves, so recomputing them on every tool execution was wasted work. `responses.js` shares a single pair between its streaming and non-streaming branches. - MINOR: `skillFiles.spec.ts` now has a test that exercises the full upload path end-to-end with real file records, asserting `batchUploadCodeEnvFiles` is called with the env-sourced apiKey and the correct file set (including the synthetic `SKILL.md`). - NIT: Finish the `appConfig` extraction in `responses.js/createResponse` — replaces the remaining `req.config` references with `appConfig` for consistency with the pattern in other controllers. No behavioral changes beyond what was already in place; this is coverage and readability polish. * 🧷 test: Tighten Spec Hygiene Per Codex Nit Feedback Round-3 codex review flagged two NITs on the test code added in the previous commit: - Replace `_id: 'skill-id' as unknown as never` in the new `makeSkillHandlerWithFiles` helper with a real `Types.ObjectId`, matching the pattern used by the primed-skill tests further up in the same file (and by `skillFiles.spec.ts`). The `never` cast hides the fact that `_id` really is a string / ObjectId at runtime. - Replace the ad-hoc `{ on, pipe, read }` stub with a real `Readable.from(Buffer.from(''))` in the upload-path test. The stub worked only because `batchUploadCodeEnvFiles` is mocked and never iterates the stream; `Readable.from` satisfies the same contract and is robust to any future partial-real replacement of the upload function. Pure test-hygiene improvements; no runtime code touched. * 🧹 chore: Remove Duplicate appConfig Declaration After Rebase The upstream `2463b6acd` fix declared `const appConfig = req.config` inside the try block (line 381) to patch the same `no-undef` error I fixed in this PR at the top of `createResponse` (line 283). The rebase kept both declarations side-by-side. Drops the inner one — the outer binding covers every downstream reference already.	2026-04-25 04:02:01 -04:00
Danny Avila	89b6bffc46	🧼 fix: Missing Enum imports	2026-04-25 04:02:01 -04:00
Danny Avila	dfc3dfa57f	📍 feat: always-apply frontmatter: auto-prime skills every turn (#12746) ... * 🔁 refactor: Rebase always-apply work onto merged structured-frontmatter columns Phase 6 (disable-model-invocation / user-invocable / allowed-tools) landed first on feat/agent-skills. Reconcile this branch with the new mainline: - Thread alwaysApplySkillPrimes through unionPrimeAllowedTools alongside manualSkillPrimes, applying the combined MAX_PRIMED_SKILLS_PER_TURN ceiling before loading tools. - Add `_id` to ResolvedAlwaysApplySkill to match Phase 6's ResolvedManualSkill shape (read_file name-collision protection). - Register 'always-apply' in ALLOWED_FRONTMATTER_KEYS / FRONTMATTER_KIND so Phase 6's validator recognizes it. - Drop frontmatter from the listSkillsByAccess projection; the backfill helper remains as defensive code but its read path is no longer exercised on summary rows (no legacy rows exist — the branch never shipped), saving ~200KB per page. - Retire the corresponding "backfills legacy on summaries" test. - Plumb listAlwaysApplySkills through the JS controllers + endpoint initializer so the always-apply resolver sees a real DB method. * 🧹 fix: Dedupe manual/always-apply overlap, share YAML util, tidy comments Addresses review findings: - Cross-list dedup: when a user $-invokes a skill that is also marked always-apply, the always-apply copy is now dropped so the same SKILL.md body never primes twice in one turn. Manual wins (explicit intent, closer to the user message). Dedup runs in both initializeAgent (so persisted user-bubble pills stay in sync) and injectSkillPrimes (defense-in-depth at splice time). New test cases cover single-overlap, partial-overlap, and dedup-before-cap. - DRY: extract stripYamlTrailingComment to packages/data-schemas/src/utils/yaml.ts; packages/api/src/skills/import.ts now imports the shared helper. Also drop the redundant inner stripYamlTrailingComment call inside parseBooleanScalar — the call site already strips. - Mark injectManualSkillPrimes as @deprecated in favor of injectSkillPrimes (kept for external consumers of @librechat/api). - Document SKILL_TRIGGER_MODEL as forward-looking plumbing for the model-invoked path rather than leaving it as a bare unused export. - Replace the stale "frontmatter is included" comment on listSkillsByAccess with an accurate explanation of why it was intentionally excluded. * 🔒 fix: Include always-apply primes in skillPrimedIdsByName + clear alwaysApply on body opt-out Two bugs flagged by Codex review: P1 (read_file): `manualSkillPrimedIdsByName` only carried manual-invocation primes, so an always-apply skill with `disable-model-invocation: true` was blocked from reading its own bundled files, and same-name collisions could resolve to a different doc than the one whose body got primed. - Rename `buildManualSkillPrimedIdsByName` → `buildSkillPrimedIdsByName` (accepts both manual + always-apply prime arrays). - Rename the configurable field `manualSkillPrimedIdsByName` → `skillPrimedIdsByName` throughout the plumbing (skillConfigurable.ts, handlers.ts, CJS callers, tests). - Overlap resolution: manual wins on the rare edge case where the same name appears in both arrays (upstream dedup should prevent this, but defensive merging treats manual as authoritative). - New tests: (1) gate-relaxation fires for always-apply primes, (2) `_id` pinning works for always-apply same-name collisions. P2 (updateSkill): when a body update had no `always-apply:` key, `extractAlwaysApplyFromBody` returned `absent` and the column was left untouched. A skill that was once `alwaysApply: true` would keep auto-priming even after its SKILL.md no longer declared the flag. - Treat `absent` as a positive "not always-apply" declaration when the body is explicitly submitted; flip the column to `false`. - Explicit top-level `alwaysApply` still wins (three-source precedence unchanged). - New tests: body removes key → false, body has no frontmatter at all → false, explicit + body-without-key → explicit wins. * 🧵 refactor: Collapse duplicate prime types + tighten parse + test hygiene Sanity-check review follow-ups: - Collapse `ResolvedManualSkill` / `ResolvedAlwaysApplySkill` into a single `ResolvedSkillPrime` canonical interface with two backward- compatible type aliases. Both resolvers feed the same pipeline stages (injectSkillPrimes, unionPrimeAllowedTools, buildSkillPrimedIdsByName); the per-source distinction lives on `additional_kwargs.trigger`, not on the resolver output. - Move the `always-apply` branch in `parseFrontmatter` to operate on the raw post-colon text. The outer `unquoteYaml` was fine today because it's idempotent on non-quoted strings, but running it twice (once per line, once after stripping the inline comment) would be fragile if the unquoter ever grows richer YAML-escape handling. - Add the missing `alwaysApplyDedupedFromManual: 0` field to the `injectSkillPrimes` mocks in `openai.spec.js` and `responses.unit.spec.js` so they match the full `InjectSkillPrimesResult` contract. - Insert the blank line between the `unionPrimeAllowedTools` and `resolveAlwaysApplySkills` describe blocks. * 🔧 fix(tsc): Cast mock.calls via `unknown` for strict tuple destructure `getSkillByName.mock.calls[0]` is typed as `[]` by jest's generic default; a direct cast to `[string, ..., ...]` fails TS2352 under `--noEmit` even though the runtime shape matches. Go through `as unknown as [...]` like the earlier test in the same file so CI's type-check step stays green. * 🪢 fix: Propagate skillPrimedIdsByName into handoff agent tool context Handoff agents go through the same `initializeAgent` flow as the primary (with `listAlwaysApplySkills` now plumbed), so they resolve their own `manualSkillPrimes` and `alwaysApplySkillPrimes` — but the `agentToolContexts.set(...)` for handoff agents didn't carry `skillPrimedIdsByName` into the per-agent context. That meant `handleReadFileCall` fell back to the full ACL set + a `prefer*` flag for handoff agents: same-name collisions could resolve to a different doc than the one whose body got primed, and a `disable-model-invocation: true` skill primed via manual `$` or always-apply inside the handoff flow would be blocked from reading its own bundled files. Build the map via `buildSkillPrimedIdsByName(config.manualSkillPrimes, config.alwaysApplySkillPrimes)` for every handoff tool context so `read_file` behaves identically across primary and handoff agents.	2026-04-25 04:02:00 -04:00
Danny Avila	82173f7b91	🛡️ feat: Persist & enforce disable-model-invocation / user-invocable / allowed-tools (#12745) ... * 🧬 feat: Persist `disable-model-invocation` / `user-invocable` / `allowed-tools` Adds first-class columns mirroring the three runtime-enforced frontmatter fields, with a `deriveStructuredFrontmatterFields` helper that maps from frontmatter at create/update time and re-syncs (via `$unset`) when fields are removed. `listSkillsByAccess` projection includes them so the Phase 6 catalog filter and popover filter can both read off the summary row. Marks `invocationMode` as @deprecated on `TSkill` and the `InvocationMode` enum — the runtime now reads the persisted pair instead. * 🛡️ feat: Enforce frontmatter at runtime (catalog, skill tool, manual resolver, tool union) Wires the persisted columns into actual runtime behavior across all four invocation paths: - `injectSkillCatalog` excludes `disableModelInvocation: true` skills before catalog formatting — they cost zero context tokens and stay invisible to the model. - `handleSkillToolCall` rejects with a clear error when the model names a skill marked `disable-model-invocation: true` (defends against a stale-cache or hallucinated invocation getting past the catalog filter). - `resolveManualSkills` skips `userInvocable: false` skills with a warn log so an API-direct caller can't bypass the popover-side filter. - `unionPrimeAllowedTools` collects skill-declared `allowed-tools` minus what's already on the agent; `initialize.ts` re-runs `loadTools` for the extras and merges resulting `toolDefinitions` into the agent's effective set for the turn. Tool-name resolution is tolerant — unknown names silently drop with a debug log so cross-ecosystem skills referencing yet-to-be-implemented tools (Claude Code's `edit_file`, etc.) import without breaking. The agent document is never modified; the union is turn-scoped. Helper exports (`unionPrimeAllowedTools`) are structured so Phase 5's always-apply primes flow through the same union (combined `[...manualPrimes, ...alwaysApplyPrimes]`) once the resolver lands. Skill handler wire format gains the three fields so clients can render them on detail / list views. * 🎛️ feat: `$` popover reads `userInvocable` instead of UI-only `invocationMode` Replaces the phase-1 UI-only `invocationMode` check with the persisted `userInvocable` field (mirrors the `user-invocable` frontmatter). Skills authored with `user-invocable: false` no longer surface in the popover; the backend resolver enforces the same rule for defense-in-depth. Default-visible behavior is preserved: skills without an explicit `userInvocable` value (older rows, freshly imported skills that don't declare the field) stay visible — only an explicit `false` hides them. Test fixture updated to reflect the new field. * 🔧 fix: Address Phase 6 review findings Codex P2 + reviewer #1: Single `loadTools` call with the union of `agent.tools + allowed-tools`. The earlier two-call approach dropped `userMCPAuthMap` / `toolContextMap` / `actionsEnabled` from the skill-added pass — an MCP tool gained via `allowed-tools` would be visible to the model but fail at execution without per-user auth context. Resolution of `manualSkillPrimes` is hoisted before `loadTools` so the union can be computed up-front; the dropped-tools debug log now compares loaded vs. requested across the single call. Codex P3 + reviewer #2: `injectSkillCatalog.activeSkillIds` now includes `disable-model-invocation: true` skills. The runtime ACL check in `handleSkillToolCall` previously couldn't reach the explicit "cannot be invoked by the model" rejection because the broader access set excluded those skills. Catalog text and tool registration still gate on the visible subset (zero-context-token guarantee preserved); only the per-user `isActive` filter is a hard exclusion now. Reviewer #1 (try/catch around loadTools, MAJOR): A single bad `allowed-tools` entry from a shared skill could crash the entire turn. Now wrapped — on failure with extras, retry with just `agent.tools` and continue (the dropped-tools debug log surfaces what vanished). If the retry-without-extras still throws, propagate; the agent's own tools are the load-bearing surface. Reviewer #3 (integration tests, MAJOR): Added six tests in `initialize.test.ts` covering the full `allowed-tools` loading path: union pass-through, no-extras short-circuit, agent-baseline dedup, loadTools throw + retry, propagated throw without extras, and the empty-tools edge case. Smaller cleanups bundled in: - Reviewer #4: Moved `logger` import to the package-imports section (was wedged among local imports). - Reviewer #5: Removed unused index on `disableModelInvocation` (filtering happens application-side in `injectSkillCatalog`; index cost write overhead for zero query benefit). - Reviewer #6: Swapped order of `userInvocable` and body checks in `resolveManualSkills` so the more authoritative author-decision reason surfaces first when both apply. - Reviewer #8: Documented the `allowedTools` enforcement gap on the schema + type — model-invoked skills (mid-turn `skill` tool calls) do NOT trigger tool union, since adding tools after the graph starts would require a rebuild. Manual / always-apply (Phase 5) primes are the supported paths. - Reviewer #9: Renamed `dmi` / `ui` / `at` locals to `disableModelInvocationRaw` / `userInvocableRaw` / `allowedToolsRaw` in `deriveStructuredFrontmatterFields`. Reviewer #7 (DRY shared `getSkillByName` return type) deferred — field sets diverge meaningfully across the three call sites (handler needs `body + fileCount`; resolver needs `author + allowedTools + userInvocable`; the InitializeAgentDbMethods contract needs the superset). A `Pick<>`-based consolidation is a follow-up cleanup. * 🔧 fix: Address codex iter 2 — catalog quota + duplicate-name dedup P1: `injectSkillCatalog` cap now counts only model-visible skills, not the merged active set. The previous behavior let a tenant with many `disable-model-invocation: true` rows near the top of the cursor exhaust the 100-slot quota before any invocable skill got scanned — the catalog could end up empty even though invocable skills existed further down the paginated results. `MAX_CATALOG_PAGES` stays the ceiling on scan budget; only `visibleCount` drives the early-exit on quota fill. P2: When an invocable and a `disable-model-invocation: true` skill share a name, drop the disabled doc(s) from `activeSkillIds`. Without this dedup, `getSkillByName` (which sorts by `updatedAt` desc) could pick the disabled doc and every model call to the cataloged name would fail with "cannot be invoked by the model" instead of executing the visible skill. When ONLY a disabled doc exists for a name, it stays in `activeSkillIds` so the explicit-rejection error path still fires for hallucinated invocations. Tests: 3 new cases in `injectSkillCatalog` covering (a) cap counted on visible skills only, (b) same-name collision drops disabled doc, (c) sole-disabled-name case keeps the disabled doc. * 🔒 fix: Apply `disable-model-invocation` gate to read_file too (codex iter 3 P1) `activeSkillIds` is shared between the `skill` and `read_file` handlers. The skill-tool gate was applied last iteration, but `handleReadFileCall` authorized purely on `getSkillByName(..., accessibleIds)` — so a model that learned a hidden skill's name (stale catalog or hallucination) could still read its `SKILL.md` body or bundled files via `read_file`, defeating the contract. Same explicit rejection now fires from both handlers; no change needed to the ACL set itself (disabled docs stay in `activeSkillIds` so the explicit error path keeps firing). Two new tests in `handlers.spec.ts` cover the read_file gate and regression-protect the happy path. * 🔧 fix: Address codex iter 4 — manual-prime exception + legacy frontmatter backfill P1: Scope the `read_file` `disableModelInvocation` gate to AUTONOMOUS model probes only. A user-invoked `$` skill that is also marked `disable-model-invocation: true` had its bundled `references/*` / `scripts/*` files unreadable, leaving the manually-primed skill body referencing files the model couldn't load. Now the handler bypasses the gate when the skill name appears in `manualSkillNames` (the per-turn allowlist threaded from `manualSkillPrimes` → `agentToolContexts` → `enrichWithSkillConfigurable` → `mergedConfigurable`). Defense-in-depth: the bypass is scoped to the specific names in the allowlist; a different disabled skill name is still rejected. P2: Read-time fallback for legacy skills authored before Phase 6 landed the structured columns. `user-invocable: false` / `disable-model-invocation: true` set in `frontmatter` (the validator already accepted those keys) but with no derived column would incorrectly evaluate as "user-invocable / model-allowed" until a save backfilled the columns. New `backfillDerivedFromFrontmatter` helper fills undefined columns from frontmatter at read time in both `getSkillByName` and `listSkillsByAccess` — column wins when both are set, frontmatter fills the gap when only it's set. No DB writes; the next `updateSkill` naturally persists. `listSkillsByAccess` projection expanded to include `frontmatter` (bounded by validator, payload impact small) so summaries can also be backfilled. Sticky-primed disabled skills (ones invoked in prior turns of the same conversation) are not yet in the manual-prime allowlist — same- turn manual invocation is the load-bearing path codex flagged; the sticky-turn case is a known limitation tracked for a follow-up. Tests: 2 new in handlers.spec.ts (manual-prime allows + name-scoped block holds), 3 new in skill.spec.ts (legacy backfill via getSkillByName + listSkillsByAccess + column-wins precedence). * 🔧 fix: Address codex iter 5 — propagate manualSkillNames + keep read_file P1: `enrichWithSkillConfigurable` is also called from `openai.js` and `responses.js` (the OpenAI Responses + completions endpoints). Both were ignoring the new `manualSkillNames` parameter, which meant the manual-prime exception in the `read_file` gate (iter 4) only worked on the agents endpoint. Now all three call sites pass `primaryConfig.manualSkillPrimes?.map(p => p.name)` so manual `$` invocations of disabled skills work consistently across endpoints. P2: When every accessible skill is `disable-model-invocation: true`, the catalog text and `skill` tool are correctly omitted (no model- reachable targets) — but `read_file` and `bash_tool` MUST still be registered. A user manually invoking such a skill gets its SKILL.md body primed into context; if the body references `references/foo.md` or `scripts/run.sh`, those reads need a registered tool. Restructured `injectSkillCatalog` so `skill` registration is gated on `catalogVisibleSkills.length > 0` while `read_file` (always) and `bash_tool` (when codeEnvAvailable) register whenever any active skill is in scope. Tests: existing all-disabled test rewritten to assert read_file IS registered + skill is NOT; new test confirms bash_tool joins it when codeEnvAvailable. * 🔧 fix: Address codex iter 6 — name-collision consistency via preferInvocable P2a (resolveManualSkills): a name collision between an older user-invocable doc and a newer non-user-invocable doc made manual `$` invocation silently no-op. The popover surfaced the older invocable doc; resolver looked it up by name; `getSkillByName` returned the newer non-invocable doc; resolver skipped on `userInvocable: false`. P2b (handler / runtime ACL): with same-name duplicates (e.g. older invocable + newer disabled), the manual prime resolved to one doc while later `read_file` / `skill` execution resolved a different doc through `activeSkillIds`. Model could follow one SKILL.md body while reading files from a different skill. Both root-cause: `getSkillByName` always returned the newest match and let the caller filter, but with collisions the newest can be something the caller didn't want. Fix: extend `getSkillByName` with `options.preferInvocable`. When true, prefer the newest doc satisfying BOTH `userInvocable !== false` AND `disableModelInvocation !== true` (with frontmatter backfill); fall back to the newest match otherwise. Fast path preserved when caller doesn't opt in. Callers passing `preferInvocable: true`: - `resolveManualSkills` — picks the popover-visible invocable doc even when a newer disabled / non-user-invocable duplicate exists. - `handleSkillToolCall` — keeps execution aligned with the catalog; falls back to the disabled doc only when no invocable variant exists (so the explicit "cannot be invoked by the model" gate still fires for the hallucinated-disabled-name case). - `handleReadFileCall` — same alignment, plus the manual-prime exception added in iter 4 still applies. Tests: - 2 new in skill.spec.ts (preferInvocable picks invocable when collision exists; falls back to newest when no clean-invocable exists). - 1 new in skills.test.ts (resolver passes preferInvocable through). - 2 new in handlers.spec.ts (skill tool + read_file pass it). - Existing initialize.test.ts assertion updated for the new option. * 🔧 fix: Address codex iter 7 — split preferInvocable into per-axis flags The previous unified `preferInvocable` filter required BOTH `userInvocable !== false` AND `disableModelInvocation !== true`. That was wrong for the model paths: `userInvocable: false` skills are model-only and remain valid `skill` / `read_file` invocation targets. A duplicate-name scenario where the newer cataloged doc was model- only would let the older user-invocable variant shadow it on every model call. Split the option into two independent axes: - `preferUserInvocable` — for manual paths (`$` popover). Skips docs with `userInvocable: false`. Disable-model-invocation status is irrelevant; iter 4 explicitly supports manual prime of disabled skills. - `preferModelInvocable` — for model paths (`skill` / `read_file` handlers). Skips docs with `disableModelInvocation: true`. User- invocable status is irrelevant; model-only skills are valid here. Both flags fall back to the newest match when no preferred doc exists, so the explicit-rejection error paths still fire correctly in the sole-disabled-name case. Callers updated: - `resolveManualSkills` → `preferUserInvocable: true` - `handleSkillToolCall` / `handleReadFileCall` → `preferModelInvocable: true` Tests: - New spec test for preferModelInvocable not filtering on userInvocable. - Existing preferInvocable test renamed/split to cover the new axes. - New test asserts preferUserInvocable still returns disabled docs (preserves iter 4 manual-disabled support). - Caller tests assert each path passes the right single flag and does NOT pass the wrong one. * 🔧 fix: TypeScript type-check failure in handlers.spec.ts (CI green) `jest.fn(async () => ...)` without explicit args infers an empty tuple for the call signature, so `mock.calls[0][2]` flagged as "Tuple type '[]' has no element at index '2'." Cast to `unknown[]` then narrow to the expected option shape. Behavior unchanged. Caught by the `Type check @librechat/api` CI step (.github/workflows/backend-review.yml). * 🔧 fix: Address codex iter 8 — undefined-result fallback + read_file alignment P1 (loadTools returning undefined): Production loaders (`createToolLoader` in `initialize.js` / `openai.js` / `responses.js`) wrap `loadAgentTools` in try/catch and return `undefined` on failure rather than throwing. Without explicit handling, my iter-1 try/catch only fired for thrown errors — a silent-failure on a skill-added tool would fall through to the empty fallback and silently DROP the agent's baseline tools for the turn (much worse than just losing the extras). Added an `undefined`-result branch that retries with just `agent.tools`, mirroring the throw branch. Test pins both behaviors. P2 (read_file alignment with manual prime): When a skill is in this turn's `manualSkillNames`, the `read_file` handler now uses `preferUserInvocable` instead of `preferModelInvocable`. Same name-collision rule as `resolveManualSkills`, so the doc whose files get read is the same doc whose body got primed. For autonomous probes (skill not in `manualSkillNames`), the handler keeps `preferModelInvocable` to align with the catalog the model saw. Two new tests cover both branches and regression-protect that the wrong flag isn't passed. * 🔧 fix: Address codex iter 9 — pin read_file lookup to primed skill _id P1 (manually-primed disabled IDs were dropped from activeSkillIds): The `executableSkills` dedup in `injectSkillCatalog` correctly drops `disable-model-invocation: true` duplicates when an invocable doc shares the name — but `resolveManualSkills` legitimately primes disabled docs (iter 4 supports manual `$` invocation of disabled skills). When the resolver primed a disabled doc, the read_file handler couldn't find it in the (deduped) `activeSkillIds` and either resolved a different same-name skill or returned not-found. Fix: `ResolvedManualSkill` now carries `_id`; the legacy `initialize.js` / `openai.js` / `responses.js` controllers build a `manualSkillPrimedIdsByName` map and `enrichWithSkillConfigurable` passes it into `mergedConfigurable`. `handleReadFileCall` now pins its lookup's `accessibleIds` to `[primedId]` whenever the requested skill is in the map. The constrained set guarantees the lookup returns the EXACT doc the resolver primed — body/files come from the same source even when same-name duplicates exist or the dedup removed the prime's id from `activeSkillIds`. Autonomous read_file probes (skill not in the manual-primed map) keep the full ACL set + `preferModelInvocable` so they align with the catalog the model saw and the disabled-only case still fires the explicit-rejection gate. Test fixture changes flow from `_id` becoming required on `ResolvedManualSkill`. `buildSkillPrimeContentParts` / `injectManualSkillPrimes` widen their param types to `Pick<...>` because they only read `name` / `body` and shouldn't force test literals to invent placeholder ids. * 🧹 fix: Address independent reviewer findings (DRY + types + tests + docs) Sanity-pass review surfaced 7 findings; addressed 6 (the 7th — DRY on inline `getSkillByName` return types — is acknowledged tech debt deferred to a follow-up). #1 [MAJOR, DRY]: The 4-line `manualSkillPrimedIdsByName` map construction was duplicated across 4 CJS call sites (openai.js, responses.js x2, initialize.js). Extracted `buildManualSkillPrimedIdsByName` helper in `skillDeps.js`; all four sites now call the helper. If `ResolvedManualSkill` ever renames `_id` or gains identifying fields, only the helper changes. #2 [MINOR, type safety]: `handleReadFileCall` was casting a hex string to `Types.ObjectId[]` via `as unknown as`, relying on mongoose's auto-cast in `$in` queries. Replaced with `new Types.ObjectId(...)` so any future consumer comparing with `.equals()` / `===` gets the correct value type. Imported `Types` as a value (was type-only). #5 [MINOR, test gap]: Added a test for the worst-case silent-failure path — both the union and base-only `loadTools` calls return undefined. The agent gets no tools but the turn doesn't crash hard; pinning that contract. #4 [MINOR, performance]: Added a TODO on the `listSkillsByAccess` projection noting the `frontmatter` field can be dropped once a write migration backfills all pre-Phase-6 skills' columns. ~2KB/skill × 100/page is wasted bandwidth post-backfill. #6 [NIT, docs]: `backfillDerivedFromFrontmatter` JSDoc said "Pure" right before "mutates its undefined fields in place". Replaced with "Side-effect-free w.r.t. the DB (no writes), but mutates its argument in place" which describes both halves accurately. #7 [NIT, test determinism]: Replaced `await new Promise(r => setTimeout(r, 5))` in two same-name collision tests with explicit `updateOne` setting `updatedAt: new Date(Date.now() - 1000)` on the older doc. Removes the wall-clock race on fast CI runners. The pagination test (line 480) still uses setTimeout — that test is pre-existing and order is incidental, not load-bearing. Existing test fixtures updated to use valid 24-char hex ObjectIds (required by the iter-9 test that constructs a real `ObjectId`). #3 [MINOR, deferred]: Inline `getSkillByName` return type duplicated across `handlers.ts`, `initialize.ts`, `skills.ts`. Reviewer acknowledged this as deferred; field sets diverge across call sites (handler needs `fileCount`, resolver needs `author`/`allowedTools`). A `Pick<>`-based consolidation is a clean follow-up.	2026-04-25 04:02:00 -04:00
Danny Avila	539c4c7e4d	🎬 feat: Prime Manually-Invoked Skills via $ Popover (#12709) ... * 🎬 feat: Prime Manually-Invoked Skills via $ Popover Lands the backend for manual skill invocation, making the $ popover deterministically prime SKILL.md before the LLM turn instead of leaving the model to discover the skill via the catalog. Flow: popover drains pendingManualSkillsByConvoId on submit, attaches names to the ask payload, controllers forward to initializeAgent, and initialize resolves each name to its body (ACL + active-state filtered, reusing the same rules as catalog injection). AgentClient splices the primes as meta HumanMessages before the user's current message. - Extract primeManualSkill / resolveManualSkills in packages/api/src/agents/skills.ts and reuse primeManualSkill inside handleSkillToolCall for a single shape source. - Thread manualSkills + getSkillByName through InitializeAgentParams / DbMethods and all three initializeAgent call sites (initialize.js, responses.js, openai.js). - Splice HumanMessage primes in client.js chatCompletion after formatAgentMessages, shifting indexTokenCountMap so hydrate still fills fresh positions correctly. - Carry isMeta / source / skillName in additional_kwargs for downstream filtering. * 🛡️ fix: Scope manual skill primes to single-agent + cap resolver input Two follow-ups to the Phase 3 priming path flagged in Codex review. Multi-agent runs: skipping the splice when agentConfigs is non-empty. `initialMessages` is shared across every agent in `createRun`, so splicing a skill body there would bypass Phase 1's per-agent `scopeSkillIds` contract — a handoff / added-convo agent with a different skill scope would see content its configuration excludes. Warn + skip is the minimal correct behavior; lifting this to per-agent initial state is a follow-up. Input bounding: `resolveManualSkills` now truncates to `MAX_MANUAL_SKILLS` (10) after dedup, with a warn listing the dropped tail. Controllers only validate `Array.isArray(req.body.manualSkills)`, so a crafted payload could otherwise fan out into an unbounded `Promise.all` of concurrent `getSkillByName` DB lookups. Cap lives in the resolver so every caller (including future `always-apply` in Phase 5) inherits it. * 🧪 refactor: Testable Helpers + Payload Validation for Manual Skill Primes Follow-ups from the comprehensive review. No behavior change for the happy path — these are architectural and defensive improvements that shrink the JS surface in /api, tighten the request-body contract, and cover the delicate splice logic with proper unit tests. - Extract `injectManualSkillPrimes` into packages/api/src/agents/skills.ts so the message-array splice and `indexTokenCountMap` shift are unit- testable in TS. client.js now calls the helper. Tests pin the `>=` vs `>` boundary condition — a regression here would silently corrupt token accounting for every message after the insertion point. - Extract `extractManualSkills(body)` and use in all three controllers (initialize.js, responses.js, openai.js). Replaces copy-pasted `Array.isArray(...) ? ... : undefined` with a helper that also filters non-string / empty elements — closes a type-safety gap where a crafted payload like `{"manualSkills": [123, {"$gt":""}]}` would otherwise reach `getSkillByName` and waste DB round-trips. - Rename `primeManualSkill` → `buildSkillPrimeMessage`. The helper serves three invocation modes (`$` popover, `always-apply`, model-invoked); the old name misled readers coming from `handleSkillToolCall`. - Add `loadable.state === 'hasValue'` guard in `drainPendingManualSkills` — defensive, since the atom has a synchronous `[]` default, but the previous `.contents` cast would have been unsound under loading/error. - Document why `resolveManualSkills` honors the active-state filter even for explicit `$` selections (Phase 2 popover filter + API-direct hardening). - Remove stray `void Types;` in initialize.test.ts — `Types` is already consumed elsewhere in that test. * 🔖 refactor: Single source for the skill-message source marker Export `SKILL_MESSAGE_SOURCE = 'skill'` and use it in both construction paths that stamp skill-primed messages — `buildSkillPrimeMessage` (for the model-invoked tool path) and `injectManualSkillPrimes` (for the user-invoked splice path). Downstream filtering and telemetry read this marker, so the two paths must agree; keeping the literal in one place removes the risk of them drifting when Phase 5's `always-apply` adds a third caller. * ♻️ refactor: Drop Multi-Agent Guard + Review Polish - Remove the multi-agent skip in `AgentClient.chatCompletion`. Leaking primes to handoff / added-convo agents via shared `initialMessages` is the agents SDK's concern to scope; this layer should just inject and let the graph handle agent-scoped state. The guard was well-intended but produced a silent-drop UX where `$skill` in a multi-agent run did nothing. - Bound the `[resolveManualSkills] Truncating ...` warn output to the first 5 dropped names plus a count suffix. A malicious payload of 1000 names was previously spilling all ~990 names into the log line. - Remove dead `?? []` from the `hasValue`-guarded loadable read in `drainPendingManualSkills` — the atom always yields a string[] when resolved, so the nullish fallback was unreachable. - Reorder skills.ts imports to follow the style guide: value imports shortest-to-longest (`data-schemas` → `langchain/core/messages` → multi-line `@librechat/agents`), type imports longest-to-shortest. * 🧠 fix: Strip Skill Primes from Memory Window + Unbreak CI Mocks Two fixes after the last push. CI unbreak: `responses.unit.spec.js` and `openai.spec.js` mock `@librechat/api` and the mock didn't expose the new `extractManualSkills` symbol, so every test in those files crashed before reaching the `recordCollectedUsage` assertion. Added `extractManualSkills: jest.fn()` returning `undefined` to both mocks; the controllers now no-op on manualSkills as the tests expect. Codex P2: `runMemory` passes `messages` straight through to the memory processor, so after the splice in `injectManualSkillPrimes`, SKILL.md bodies ride along as if they were real user chat. That pollutes memory extraction with synthetic instruction content and crowds out real turns from the window. - Export `isSkillPrimeMessage(msg)` from `packages/api/src/agents/skills.ts` — a predicate keyed on the shared `SKILL_MESSAGE_SOURCE` marker. - Filter `chatMessages = messages.filter(m => !isSkillPrimeMessage(m))` at the top of `runMemory` before the window-sizing logic. Keeps the primes visible to the LLM (they still ride in `initialMessages`) but invisible to the memory layer. - 5 new tests for the predicate covering marker-present, plain messages, different source, non-object inputs, and array filter integration. * 📜 feat: Show Skill-Loaded Cards for Manually-Invoked Skills The $ popover was priming SKILL.md bodies into the turn but leaving no visible trace on the assistant response — from the user's view it looked like the `$name ` cosmetic text did nothing. Now each manually-invoked skill renders the same "Skill X loaded" tool-call card that model-invoked skills already produce via PR #12684's SkillCall renderer. Approach: post-run prepend to `this.contentParts`. The aggregator owns per-step indices during the run, so pre-seeding collides; waiting until `await runAgents(...)` returns lets the graph settle before synthetic parts slot in at the front. - Export `buildSkillPrimeContentParts(primes, { runId })` from `packages/api/src/agents/skills.ts`. Returns completed tool_call parts (`progress: 1`, args JSON-encoded with `{skillName}`, output matching the model-invoked path's wording) that the existing `SkillCall.tsx` renderer draws identically. - In `AgentClient.chatCompletion`, prepend the built parts to `this.contentParts` immediately after `await runAgents`. Persistence and the final-event reconcile come for free — `sendCompletion` already reads `this.contentParts` verbatim. - Card ordering: skills appear first in the assistant message, reflecting that priming ran before the LLM's turn. Live-during-streaming cards are a separate follow-up — the graph's index-based aggregator makes that a bigger lift and this change delivers the core UX win without fighting the stream ordering. 6 new unit tests covering part shape, args JSON contract, output text, unique IDs, empty input, and startOffset ID differentiation. * ⚡ feat: Emit Optimistic Skill Cards + Wire Primes in OpenAI/Responses Two follow-ups from testing. Optimistic card emit: the main chat path was only showing "Skill X loaded" cards at final-reconcile time, so the user saw nothing happen until the stream finished. Now emit synthetic ON_RUN_STEP + ON_RUN_STEP_COMPLETED events right before `runAgents` starts — same pattern the MCP OAuth flow uses in `ToolService` — so the cards appear immediately. The graph's content at index 0 may overwrite them during streaming, but the post-run `contentParts` prepend (unchanged) restores them on final reconcile. OpenAI + Responses parity: both controllers were resolving `manualSkillPrimes` via `initializeAgent` but never injecting them into `formattedMessages` before the run. Manual invocation silently did nothing on `/v1/chat/completions` and the Responses API path. Now both call `injectManualSkillPrimes` on the formatted messages so the model sees SKILL.md bodies on every path. LibreChat-style card SSE events don't apply to these OpenAI-shaped responses, so the live-emit is chat-path-only. - Export `buildSkillPrimeStepEvents(primes, { runId })` from `packages/api/src/agents/skills.ts`. Uses `Constants.USE_PRELIM_RESPONSE_MESSAGE_ID` by default so the frontend maps events to the in-flight preliminary response message, matching the OAuth emitter. - In `AgentClient.chatCompletion`, emit via `sendEvent` (or `GenerationJobManager.emitChunk` in resumable mode) after `injectManualSkillPrimes` runs, before the LLM turn begins. - Wire `injectManualSkillPrimes` into `openai.js` + `responses.js` after `formatAgentMessages`. Refactored the destructure to `let` on `indexTokenCountMap` so the injector's returned map is usable. - 8 new unit tests covering the step-event builder: pair cardinality, default/custom runId, TOOL_CALLS shape + JSON args, progress:1 on completion, index ordering, stepId/toolCallId pairing, empty input. * 🎯 fix: Route Skill Prime Events to the Real Response + Sparse-Array Offset Two bugs in the optimistic-card emit from the last pass. 1. Wrong runId. The events used `USE_PRELIM_RESPONSE_MESSAGE_ID` (the MCP OAuth pattern), but OAuth emits DURING tool loading — before the real response messageId exists. By the time skill priming fires, the graph is about to emit with `this.responseMessageId`, so the PRELIM runId orphaned every card onto the client's placeholder response entry in `messageMap`, separate from the one the LLM's events were building. Net effect: cards never rendered mid-stream. Now passing `this.responseMessageId` — the same ID `createRun` receives — so synthetic and real steps land on the same `messageMap` entry. 2. Index 0 collision. With the runId fixed, card-at-0 would have hit `updateContent`'s type-mismatch guard when the LLM's text delta arrived at the same index, suppressing the whole text stream. New `SKILL_PRIME_INDEX_OFFSET` = 100 placed on both the live SSE emit and the server-side `contentParts` assignment. Sparse array during streaming renders as `[llm_text, ..., card]` (skip-holes via `Array#filter` / `Array#map`). `filterMalformedContentParts` from `sendCompletion` compacts to dense `[text, card]` before persistence, so streaming UI and saved message agree on order — no finalize reorder jank. Post-run switches from `contentParts.unshift` to `contentParts[OFFSET + i] = part` to mirror the live placement. - Add `startIndex` option to `buildSkillPrimeStepEvents` with `SKILL_PRIME_INDEX_OFFSET` default. Export the constant from `@librechat/api` so `client.js` can reuse it for the post-run splice. - Update the existing index-ordering test to the new default and add a new test for the explicit `startIndex` override. * 🎗️ feat: Replace \$skill-name Text with Pills on the User Message The `$skill-name ` cosmetic text the popover was inserting into the textarea had two problems: it lingered in the user message forever (the card is a more meaningful marker), and it implied that free-form text invocation like \"\$foo help me\" should work — which it doesn't, and supporting it would mean another parsing layer nobody asked for. Dropped the textarea insertion. Visual confirmation after submit now comes from a compact `ManualSkillPills` row on the user bubble that self-extinguishes once the backend's live skill-card stream (`buildSkillPrimeStepEvents` from the last commit) populates the sibling assistant response. Multiple skills render as multiple pills — the atom was already a string array, so multi-select works for free. - `SkillsCommand.tsx`: select handler no longer writes to the textarea. Still drops the trigger `$` via `removeCharIfLast`, still pushes to `pendingManualSkillsByConvoId`, still flips `ephemeralAgent.skills`. - `families.ts`: new `attachedSkillsByMessageId` atomFamily keyed by user messageId. `useChatFunctions.ask` writes the drained skill list here on every fresh submit (regenerate/continue/edit still skip). - `ManualSkillPills.tsx` renders pills conditionally: hidden when the message isn't a user message, when no skills are attached, or when the sibling assistant response already carries a `skill` tool_call content part (the live card took over). Reads messages via React Query so we don't re-render on every message-state keystroke. - `Container.tsx` mounts the pills above the user message text, parallel to the existing `Files` slot. - Updated the SkillsCommand select-flow spec to assert the textarea is cleared of `$` instead of populated with `\$name `. 5 new tests for `ManualSkillPills` covering empty state, non-user message guard, multi-skill rendering, the skill-card hide condition, and the text-only-content-doesn't-hide case. * 🎛️ feat: Manual Skills as Persisted Message Field + Compose-Time Chips Three problems with the previous pass: 1. Cards rendered BELOW the LLM text on the assistant message (and stayed there on reload) because the sparse index-100 offset put them after the model's content. Now back to `unshift` — cards at the top, same as before the live-emit detour. 2. Pills on the user message disappeared the moment the live card arrived, so users barely saw them. The live-emit channel also added meaningful complexity and relied on a per-message Recoil atom that had no clean cleanup story. 3. No visual cue at all during new-chat compose — the `$name ` text was removed, the submitted-message pills weren't there yet, and the popover closes after selection. User had no way to see what they'd queued up before sending. New architecture: `manualSkills` is a first-class field on `TMessage`, persisted by the backend on the user message. `ManualSkillPills` reads straight from `message.manualSkills` — no atom, no sibling-lookup — so pills survive reload, show in history, and stay for the lifetime of the message. Compose-time chips above the textarea read the existing `pendingManualSkillsByConvoId` atom and let users × skills out before submitting. Backend reverts: - `client.js`: dropped the `ON_RUN_STEP` live-emit loop, restored `this.contentParts.unshift(...primeParts)` so cards sit at the top of the persisted assistant response. - `skills.ts`: removed `buildSkillPrimeStepEvents` and `SKILL_PRIME_INDEX_OFFSET` (both unused now). `GraphEvents`, `StepTypes`, and `Constants` imports went with them. Removed 8 tests. Field persistence: - `tMessageSchema` gains `manualSkills: z.array(z.string()).optional()`. - Mongoose message schema gains `manualSkills: { type: [String] }` with matching `IMessage` TS field. - `BaseClient.js` reads `req.body.manualSkills` on user-message save, filters to non-empty strings, pins onto `userMessage` before `saveMessageToDatabase`. Mirrors the existing `files` pattern right above it. Runtime resolution still reads top-level `req.body.manualSkills` — persistence and resolution are separate concerns. Frontend: - `useChatFunctions.ask` sets `currentMsg.manualSkills` directly; the drained atom value goes onto the message, not a separate atom. Removed the `attachSkillsToMessage` Recoil callback. - `ManualSkillPills`: pure render of `message.manualSkills`. No more `useQueryClient`, no sibling scan, no atom read. Loses the auto-hide-when-card-arrives behavior — pills stay on the user bubble, cards live on the assistant bubble, both are informative. - Dropped the `attachedSkillsByMessageId` atomFamily and its export. - New `PendingManualSkillsChips` above the textarea reads the compose-time atom and renders chips with × to remove. Mounted in `ChatForm` right after `TextareaHeader`. Naturally hides on submit when the atom drains. Tests: updated `ManualSkillPills` suite to the new field-based reads (5 passing). New `PendingManualSkillsChips` suite covering empty state, multi-chip render, single × removal, and full-clear (4 passing). Backend suite trimmed to 89 (was 97) from the step-events test removal — no regressions on the remaining helpers. * 🧪 feat: Assistant-Side Skill-Loading Chips + Pill Padding Two small UX fixes on top of the field-on-message architecture. Pill padding: bumped the user-side `ManualSkillPills` from `py-0.5` to `py-1` on each chip and added `py-0.5` to the wrapper so the row breathes a little without feeling tall. Mid-stream indicator: new `InvokingSkillsIndicator` mirrors the parent user message's `manualSkills` onto the assistant bubble as transient "Running X" chips while the real card is in flight. Renders above `ContentParts` in `MessageParts`. Hides itself when the assistant's own `content` grows a `skill` tool_call — the authoritative card from `buildSkillPrimeContentParts.unshift` is showing, so the placeholder steps aside. No SSE emit, no aggregator injection, no index collision with the LLM's streaming content: just a render slot keyed off the parent's field. Why not stream the cards live: whichever content index we'd choose either blocks the LLM's text stream (`updateContent` type-mismatch at index 0) or lands below the response after sparse compaction (index 100+). Mirroring the parent field sidesteps the aggregator entirely and gives the user an immediate "skill is loading" signal that naturally gives way to the real card at finalize. Covers the gap the user flagged: pills on the user message said "I asked for these" but nothing on the assistant side said "we're working on it" until the stream finished. 5 new tests for the indicator: user-msg guard, missing parent-field guard, multi-chip render, hides-on-card-landing, orphan-parent guard. * 🔁 fix: Indicator Visibility + Carry Manual Skills Through Regenerate/Edit Two bugs. Indicator never rendered: `InvokingSkillsIndicator` looked up the parent user message via `queryClient.getQueryData([QueryKeys.messages, convoId])`, but on a new chat the React Query cache is keyed by `"new"` (the URL `paramId`) until the server assigns a real conversation ID — while `message.conversationId` on the assistant message is already the server ID. Lookup missed, `skills.length === 0`, nothing rendered. Switched to `useChatContext().getMessages()`, which reads from the same `paramId` the rest of the UI uses, so new-chat and existing-chat cases both resolve to the correct message list. Regenerate / save-and-submit dropped manual skills: the compose-time `pendingManualSkillsByConvoId` atom is drained on the first submit, so replaying that turn later found an empty atom and sent `manualSkills: []`. The pills were still on the user bubble, so from the user's point of view the model was running primed — but the backend saw nothing and produced an unprimed response. - Added `overrideManualSkills?: string[]` to `TOptions`. Callers with a reference message pass its persisted `manualSkills`; `useChatFunctions.ask` uses the override verbatim when present, otherwise falls back to the existing drain-or-empty logic. - `regenerate` in `useChatFunctions` passes `parentMessage.manualSkills` — the user message being regenerated has the field persisted by the backend, so the second turn primes the same skills as the first. - `EditMessage.resubmitMessage` covers both edit branches: - User-message save-and-submit: forwards the edited message's own `manualSkills` so the new sibling turn primes identically. - Assistant-response edit: forwards the parent user message's `manualSkills` for the same reason. Indicator test suite converted from `@tanstack/react-query` harness to a jest-mocked `useChatContext().getMessages()`. 6 tests (was 5), added a cache-miss case. * 🧭 fix: Drive Mid-Stream Skill Chips from Submission Atom, Not Message Lookup Message-ID-keyed lookups kept racing the stream: the user message flips from its client-side intermediate UUID to the server-assigned ID mid-run, conversation IDs flip from the URL `paramId="new"` to the real convo ID on brand-new chats, and the React Query cache splits briefly between the two. Previous attempts — direct `queryClient.getQueryData` and then `useChatContext().getMessages()` — each missed a different window. `TSubmission.manualSkills` is already populated at `ask()` time and the submission atom (`store.submissionByIndex(index)`) is the single stable anchor across the whole lifecycle: set once at submit, lives through every SSE event, cleared when the stream ends. No ID lookups, no cache timing. - `InvokingSkillsIndicator` now reads `submissionByIndex(index)` via Recoil. Shows chips when: • the message is assistant-side, • a submission is in flight with non-empty `manualSkills`, • the assistant's `parentMessageId` matches `submission.userMessage.messageId` (so chips appear only on the bubble for the current turn, never on siblings), • the assistant's own content doesn't yet carry a `skill` tool_call (real card takes over from the server's post-run `contentParts.unshift`). - Drops the `useChatContext().getMessages()` dependency and the `useQueryClient` dependency before that. No more lookups by conversationId or messageId. Test suite now mocks `useChatContext` to supply `index: 0` and seeds the `submissionByIndex(0)` atom via Recoil initializer. 6 cases cover user-side, no-submission history, empty `manualSkills`, multi-chip render, hides-on-card-landing, and wrong-turn guard. * 🌱 fix: Seed Response manualSkills in createdHandler, Indicator Becomes Pure The mid-stream indicator kept getting wired off state I don't own: first `queryClient.getQueryData` (raced the new-chat paramId flip), then `useChatContext().getMessages()` (same cache, same race), then `useRecoilValue(submissionByIndex)` (pulled every message into the submission subscription — re-renders all indicators on any submission change, exactly the "limit hooks in rendering" concern). Cleanest path is the one the user pointed at: the submission owns the data, `useSSE` / `useEventHandlers` owns the save points, so seed the field ONTO the response message at the save site and let the indicator be a pure prop-read. - `createdHandler` now writes `manualSkills` onto the initial response from `submission.manualSkills` at the moment the placeholder enters the messages array. The field rides through the normal mutation pipeline via spreads (`useStepHandler` response creation, `updateContent` result returns) — no special handling needed. - `InvokingSkillsIndicator` drops the Recoil / context / queryClient reads. Pure function of `message`: if assistant, has `manualSkills`, and `content` hasn't grown a `skill` tool_call yet, render chips. Only `useLocalize` left, which was already unavoidable for the i18n string. - Renders decouple: no single state change (`submissionByIndex` flip, React Query cache update) forces every indicator in the message list to re-render anymore. Only the message whose prop changed re-runs. Finalize story unchanged: server's `responseMessage` doesn't carry the frontend-only `manualSkills` field, so `finalHandler`'s replacement drops it — but by then the real `skill` tool_call is in `content` and the indicator's content-scan hides itself anyway. Test suite back to pure prop mocks: 7 cases covering user-guard, no-seed, multi-chip render, skill-card-hide, non-skill-tool-call-keeps, text-only-keeps, and missing message. * 🪞 fix: Render Skill Indicator Inside ContentParts, Adjacent to Parts The indicator still wasn't showing because even though MessageParts mounted it as a sibling of ContentParts, ContentParts is a `memo`'d component that owns the only rendering path that refreshes in lockstep with content deltas. Mounting above it put the indicator one layer further out — reachable, but not exercised on the same render cycle that processes the streaming `message` prop. Moved the indicator into ContentParts itself, rendered at the top of both the sequential and parallel branches. Reads the `message` prop (newly threaded through as an optional prop alongside `content`), so: - Same render cycle as Parts — updates from the SSE pipeline flow through the same pathway. - Lives outside the `content.map`, so delta-driven content reshuffles never wipe it. - Still a pure prop-read inside the indicator itself (no Recoil, queryClient, context hooks). The only dep is `useLocalize`. Thread: - `ContentPartsProps` gains `message?: TMessage`. - `MessageParts` passes `message={message}` through, drops its own indicator mount + import. - `ContentParts` renders `<InvokingSkillsIndicator message={message} />` in both the parallel-content and sequential-content branches, right under `MemoryArtifacts` and before the empty-cursor / parts map. Companion data flow (unchanged): `createdHandler` seeds `initialResponse.manualSkills` from `submission.manualSkills`; the field rides through `useStepHandler` via spreads; indicator hides on `skill` tool_call landing in `content`. * 🔎 refactor: Narrow Skill Components to Scalar skills Prop, Kill Memo Churn Passing the full `message` object into presentational components busts `React.memo` shallow comparisons every time the message reference changes for unrelated reasons. Swap to scalar `skills?: string[]` throughout: - `InvokingSkillsIndicator`: props-only (`skills?: string[]`); visibility logic (user-vs-assistant, skill tool_call arrival) now lives in the caller so this stays pure presentational. - `ManualSkillPills`: props-only (`skills?: string[]`). - `ContentParts`: takes `manualSkills?: string[]` scalar, computes `showInvokingSkills` once per render from `manualSkills` + content scan for the `skill` tool_call, then mounts the indicator with `skills=` prop in both parallel and sequential branches. - `MessageParts`: passes `manualSkills={message.manualSkills}` through to `ContentParts`. - `Container`: passes `skills={message.manualSkills}` to `ManualSkillPills`. - Tests updated to exercise the narrowed prop surface. * 📜 feat: Mid-Stream Skill Cards via SkillCall, Drop Custom Indicator Instead of a separate `InvokingSkillsIndicator` chip component, render pending skill placeholders through the existing `SkillCall` renderer — same component the backend's finalized prime part uses. The loading visual (`progress < 1` + empty output → pulsing "Running X") and the completed visual ("Ran X") now come from one source of truth. `ContentParts` computes `pendingSkillNames` from `manualSkills` minus any `skill` tool_call already in `content` (dedupe by `args.skillName` since the synthetic's id differs from the real one). Those names render through a separate slot ABOVE the Parts iteration — not prepended to the content array, which would shift React keys on every downstream streaming text / tool part and force unmount/remount mid-stream. When the real prime `tool_call` lands at finalize (backend unshifts to content[0..]), `collectExistingSkillNames` picks it up, the pending set empties, and the real part takes over rendering in the Parts iteration. Layout is identical either way because primes are always at the top of content. - `InvokingSkillsIndicator.tsx` + test deleted (no longer referenced) - `ContentParts.tsx` renders `<SkillCall .../>` directly for pending names, mirrors `Part.tsx`'s usage of the same component - `createdHandler` doc comment updated to reflect the new flow * ✂️ fix: Render Interim Skill Cards From manualSkills Only, Leave Content Untouched Previous revision read `content` to de-dupe pending cards against real `skill` tool_calls, so any optimistic skill part streamed from the backend would race our placeholder off the screen mid-turn — exactly the "getting overridden" symptom. Now: interim `SkillCall` cards are driven purely by the response message's `manualSkills` field. `content` is never inspected here, so no backend delta can pull the cards down. The field is now seeded directly onto the assistant placeholder in `useChatFunctions` (not only in `createdHandler`) so the cards appear from the first render, before the `created` SSE event round-trip. Lifecycle: - `useChatFunctions` puts `manualSkills` on the freshly-minted `initialResponse` — cards render the instant the placeholder lands. - `createdHandler` keeps its own re-seed (idempotent; safe) so a regenerate / save-and-submit flow that hits that path still works. - `useStepHandler` spread operations preserve the field through every content update. - `finalHandler` replaces the message with the server-backed `responseMessage` (no `manualSkills`) — cards disappear, and the real `skill` tool_call part in `content` takes over. ContentParts changes: - Drop `collectExistingSkillNames` / `parseJsonField` dedupe path. - `renderPendingSkills` reads only `manualSkills` + `isCreatedByUser`. - Simpler control flow — one boolean (`hasPendingSkills`) gates the early return, one function renders. * 🩹 fix: Codex Review Resolutions — Localization, Guards, Tests, Docs Addresses seven findings from comprehensive code review: Finding 1 (MAJOR) — Document sticky re-priming as intentional - `buildSkillPrimeContentParts`: expanded doc comment explaining synthetic `skill` tool_calls persist and get re-primed on every subsequent turn via `extractInvokedSkillsFromPayload` (shape parity with model-invoked skills). This matches the UX: the assistant skill card is a visible, persistent signal that the skill is active for the conversation. Not a bug — called out explicitly so future maintainers don't mistake it for one. Finding 2 (MAJOR) — Add ContentParts render tests - New `ContentParts.test.tsx` with 7 cases covering the interim skill card logic: assistant-only rendering, user-message suppression, undefined-content safety, parallel+sequential branch integration, progress<1 (pending) state. Child components mocked so the test exercises only the branching and prop wiring ContentParts owns. Finding 3 (MINOR) — Localize hardcoded aria-labels - Added `com_ui_skills_manual_invoked` + `com_ui_skills_queued` keys. - Reused existing `com_ui_remove_skill_var` for the remove-button aria-label. - `PendingManualSkillsChips` and `ManualSkillPills` now call `useLocalize()`. Test mocks updated to the label-echo pattern. Finding 4 (MINOR) — Max-length guard in `extractManualSkills` - New `MAX_SKILL_NAME_LENGTH = 200` constant and filter. Blocks a crafted payload like `{ manualSkills: ['a'.repeat(100000)] }` from reaching `getSkillByName` / Mongo's query planner. Finding 5 (NIT) — `BaseClient.js` comment contradicted itself - Rewrote to call the filter what it is: defense-in-depth on top of Mongoose schema validation, not a redundant second layer. Finding 6 (NIT) — `ManualSkillPills` now wrapped in `React.memo` - Consistent with peer components (`PendingManualSkillsChips`, `ContentParts`). Rendered inside `Container`, which re-renders on every content update, so the memo is a real cycle savings. Finding 7 (NIT) — Redundant guard in `ContentParts.renderPendingSkills` - Collapsed the duplicate null-check by computing `pendingSkills` as a `useMemo`'d array (`[]` when not applicable), and mapping directly. `hasPendingSkills` now derives from the array length — one source of truth, no redundant gate inside the render function. * 🔧 fix: Update ParallelContent to Handle Optional Content Prop Modified the `ParallelContentRendererProps` to make the `content` prop optional, ensuring safer access within the component. Adjusted the calculation of `lastContentIdx` to handle cases where `content` may be undefined, preventing potential runtime errors. This change enhances the robustness of the component when dealing with varying message structures. * 🎯 fix: Thread manualSkills Through ContentRender — The Real Renderer This is why the interim skill cards never appeared across many rounds of iteration: `ContentRender.tsx` (the memo'd renderer used by most paths, including the agents endpoint) was calling `ContentParts` without the `manualSkills` prop. Only `MessageParts.tsx` had it wired up — and that's not the component that actually renders the assistant response in production. Two fixes: 1. Pass `manualSkills={msg.manualSkills}` to the `ContentParts` call. 2. Extend the `areContentRenderPropsEqual` memo comparator to include `manualSkills.length`, otherwise a message update that adds the field (seeded by `useChatFunctions` on the initialResponse) would be bailed out by the memo and never re-render. Verified the two ContentParts call sites are now consistent; Container usages for `ManualSkillPills` on the user side were already correct. * 🧹 polish: Address Audit Follow-Up (F1/F3/F6) F1 — Clarify sticky re-priming opt-out path. The previous comment said "regenerate without the pick" as one opt-out, but `useChatFunctions.regenerate` forwards the original picks via `overrideManualSkills`, so regeneration alone keeps the skill sticky. Updated to: edit the originating message to remove the pills and resubmit, or start a new conversation. F3 — Add DOM-order assertions to the parallel + sequential tests. The two "alongside" tests verified both elements existed but didn't pin the ordering contract. Both now use `compareDocumentPosition` to assert the pending SkillCall precedes the real content, matching the backend semantic (`contentParts.unshift(...primeParts)` puts primes at the top). F6 — Fix package import order in PendingManualSkillsChips. `recoil` (58 chars) was listed before `lucide-react` (45 chars) which violates the "shortest to longest after react" rule in AGENTS.md. Swapped order; no behavior change. F2 / F4 / F5 from the audit were confirmed as non-issues (React-safe empty map, cosmetic test-mock artifact, accepted memo tradeoff) and require no change. * ✨ feat: Dedicated PendingSkillCall + Running→Ran Transition on Real Content UX polish on the interim skill card now that it's actually rendering: 1. New `PendingSkillCall` component (mirrors `SkillCall` visually but drops the expand affordance). `SkillCall`'s underlying `ProgressText` always renders a chevron + clickable button when any input is present, which on a card with empty output points at nothing — misleading cursor:pointer and a no-op toggle. The pending variant has only the icon + label, no button wrapper, no chevron. 2. "Running X" → "Ran X" transition when real content lands. `ContentParts` computes `hasRealContent` (any non-text part, or a text part with non-empty content — placeholder empty-text parts don't count) and passes `loaded={hasRealContent}` to `PendingSkillCall`. Matches what users see for model-invoked skills as they finish priming: pulsing shimmer → static icon. 3. Cleanup: - Dropped direct `SkillCall` import from `ContentParts` (replaced by `PendingSkillCall`). `SkillCall` is still used by `Part` for real `skill` tool_call content parts — no behavior change there. - Removed the now-redundant explicit `manualSkills` assignment in `createdHandler`. `useChatFunctions` seeds the field on `initialResponse` at construction, so the `...submission.initialResponse` spread already carries it through — the re-assignment was defensive belt-and-suspenders doing the same work twice. Comment rewritten to describe the actual lifecycle. Tests updated to the new component (12/12 pass): two new cases pin the loaded-state transition (unloaded when content has no real parts, flips to loaded once a non-empty text part lands).	2026-04-25 04:02:00 -04:00
Danny Avila	9225a279eb	🎚️ feat: Per-User Skill Active/Inactive Toggle with Ownership-Aware Defaults (#12692) ... * feat: per-user skill active/inactive toggle with ownership-aware defaults - Add `skillStates` map (Record<string, boolean>) to user schema for per-user active/inactive overrides on skills - Add `defaultActiveOnShare` to interface.skills config (default: false) so admins can control whether shared skills auto-activate - Add GET/POST /api/user/settings/skills/active endpoints with validation - Add React Query hooks with optimistic mutations for skill states - Add useSkillActiveState hook with ownership-aware resolution: owned skills default active, shared skills default inactive - Add toggle switch UI to SkillListItem and SkillDetail components - Filter inactive skills in injectSkillCatalog before agent injection - Add localization keys for active/inactive labels * fix: use Record instead of Map for IUser.skillStates Mongoose .lean() flattens Map to a plain object, causing type incompatibility with IUser in methods that return lean documents. * fix: address review findings for skill active states - Fail-closed when userId is absent: filter rejects all shared skills instead of passing them through unfiltered (Codex P1) - Validate Mongoose Map key characters (reject . and $) in controller to return 400 instead of a 500 from schema validation (Codex P2) - Block toggle while initial skill states query is loading to prevent overwriting server-side overrides with an empty snapshot (Codex P2) - Extract shared SkillToggle component, eliminating duplicate toggle markup in SkillListItem and SkillDetail (Finding #3) - Move skill state query/mutation hooks from Favorites.ts to Skills/queries.ts per feature-directory convention (Finding #4) - Fix hardcoded English aria-label in SkillListItem by passing the localized string from the parent SkillList (Finding #5) - Fix inline arrow in SkillList render loop: pass stable callback reference so SkillListItem memo() is not invalidated (Finding #1) - Extract toRecord() helper in controller to DRY the Map-to-Object conversion (Finding #6) - Remove Promise.resolve wrapping synchronous config read (Finding #8) - Remove unused TUpdateSkillStatesRequest type (Finding #12) * fix: forward tabIndex on SkillToggle to preserve list keyboard nav The original inline toggle had tabIndex={-1} so the row itself remained the sole tab target. The extraction into SkillToggle dropped this prop, making every list toggle a tab stop. Add an optional tabIndex prop and pass -1 from SkillListItem. * fix: plumb skillStates to all agent entry points, isolate toggle keydown - Add skillStates/defaultActiveOnShare loading to openai.js and responses.js controllers so shared-skill activation is respected across all agent entry points, not just initialize.js (Codex P1) - Stop keydown propagation on SkillToggle so Enter/Space does not bubble to the parent row's navigation handler (Codex P2) * fix: paginate catalog fetch and serialize toggle writes - Paginate listSkillsByAccess (up to 10 pages of 100) until the active catalog quota is filled, so inactive shared skills in recent positions do not starve active owned skills past the first page (Codex P1) - Extend listSkillsByAccess interface with cursor/has_more/after for catalog pagination - Serialize skill-state writes via a ref queue: one in-flight request at a time, with the latest desired state sent when the previous one settles. Prevents last-response-wins races where an older request overwrites newer toggles (Codex P2) * fix: share write queue across hook instances, block toggle on fetch error - Move the write queue from a per-instance useRef to a module-scoped object so every mount of useSkillActiveState (SkillList, SkillDetail, etc.) serializes against the same in-flight slot. Prior per-instance queues allowed two components to race full-map POSTs (Codex P1) - Extend the toggle guard beyond isLoading: also block when isError is true or data is undefined. Prevents a failed GET from seeding a toggle with an empty baseline that would wipe server-side overrides on the next successful POST (Codex P1) * fix: stale closure, orphan cleanup, and cap-error UX - Read toggle baseline from React Query cache via queryClient.getQueryData instead of the captured skillStates closure. The closure can be stale between onMutate's setQueryData and the next render, so rapid successive toggles would build on old state and drop earlier changes (Codex P1) - Surface the MAX_SKILL_STATES_EXCEEDED error code with a specific toast key (com_ui_skill_states_limit) so users understand the 200-cap rather than seeing a generic error - Prune orphaned entries (skillIds whose Skill doc no longer exists) on both GET and POST in SkillStatesController. Self-heals over time without needing cascade-delete hooks or a migration job. Uses one indexed Skill._id query per request * test: pin skill active-state precedence with unit tests Extract the active-state resolution logic from a closure inside injectSkillCatalog into an exported resolveSkillActive helper, then cover every branch of the precedence matrix: - Fails closed when userId is absent (even with defaultActiveOnShare=true) - Explicit override wins over ownership and config (both true and false) - Owned skills default to active when no override is set - Shared skills default to defaultActiveOnShare value - Undefined skillStates behaves identically to an empty object - defaultActiveOnShare defaults to false when omitted - Owned skills ignore defaultActiveOnShare entirely Closes Finding #2 from the pre-rebase comprehensive review. Mirrors the existing scopeSkillIds test style; injectSkillCatalog now calls resolveSkillActive instead of inlining the closure. * refactor: limit skill active toggle to detail header, drop label - Remove the per-row toggle from SkillListItem and the active-state plumbing (hook call, isSkillEnabled/onToggleEnabled/toggleAriaLabel props) from SkillList. The detail view is now the single place to change a skill's active state - Drop dim/muted styling for inactive skills in the sidebar: without a control there, the visual indication has nowhere to land - Resize SkillToggle to match neighbor buttons: outer h-9 container, h-6 w-11 track with size-5 knob, no label span. The 'Active' / 'Inactive' text that accompanied the detail-view toggle is removed - Remove the now-unused label prop and tabIndex prop (the tabIndex existed only for the list-row context) from SkillToggle. Drop the onKeyDown stopPropagation for the same reason - Remove now-orphaned com_ui_skill_active / com_ui_skill_inactive translation keys * style: shrink SkillToggle track to h-5 w-9 with size-4 knob Container stays at h-9 to match neighbor button heights. The toggle track itself drops from h-6 w-11 to h-5 w-9, with a size-4 knob travelling 1.125rem on activation. Visually lighter inside the row. * fix: remove redundant skillStates entries that match the resolved default When a toggle lands on the ownership/config default, delete the key from the map instead of persisting `{id: defaultValue}`. Without this, a user toggling a skill off and back on would leave `{id: true}` for an owned skill (whose default is already true), silently consuming a slot against the 200-entry cap. Repeated round-trip toggles could exhaust the quota with zero meaningful overrides (Codex P2). Preserves the exceptions-list invariant that the runtime-resolution design depends on. * fix: prune before enforcing skill-state cap; reject non-ObjectId keys Reorder the update controller so pruneOrphans runs before the 200-cap check. Without this, a user near the cap with some orphaned entries (skills deleted since their last GET) could send a payload that would pass after pruning but gets rejected by the raw-size check first. Add a sanity cap on raw payload size (2 * MAX_SKILL_STATES) so abusive inputs do not reach the DB query, and enforce the real cap on the pruned result instead. Harden pruneOrphans: the earlier early-return path could pass non-ObjectId keys through unchanged. Now only valid ObjectIds are returned, and the Skill-model-unavailable fallback filters by format. Also add isValidObjectIdString validation at the input boundary so malformed (but otherwise non-Mongo-unsafe) keys never reach persistence (Codex P2 x2). * fix: enforce active filter at execute time, prune revoked shares, scope queue per user P1: injectSkillCatalog now returns activeSkillIds (the filtered set that appears in the catalog). initializeAgent uses that set as the stored accessibleSkillIds on the initialized agent, so getSkillByName at runtime cannot resolve a deactivated skill — even if the LLM hallucinates a name or the user invokes by direct-invocation shorthand. Previously the executor authorized against the full ACL set, bypassing the active-state guarantee (Codex P1). P2: pruneOrphans now checks user access via findAccessibleResources in addition to skill existence. When a share is revoked, the user's skillStates entry for that skill had no cleanup path and silently consumed the 200-cap. Self-heals on both GET and POST. One extra ACL query per settings read/write; scoped to a single user so no N-user amplification (Codex P2). P2: the write queue moves from a single module-scoped object to a Map keyed by userId. Logout/login in the same tab can no longer flush the previous user's pending snapshot under the new session's auth. Each userId gets its own pending/inFlight slot; the in-flight request retains its original auth via the cookie already attached when sent, so the race window closes (Codex P2). * refactor: extract skillStates helpers to packages/api; add tests; polish Address the remaining valid findings from the comprehensive review: - Extract toRecord, loadSkillStates, validateSkillStatesPayload, and pruneOrphanSkillStates into packages/api/src/skills/skillStates.ts as TypeScript. The controller in /api shrinks to a ~90-line thin wrapper that builds live dependency adapters for Mongoose + the permission service (Review #2 DRY, #3 workspace boundary) - Replace the triplicated 12-line skillStates loading block in initialize.js, openai.js, and responses.js with a single call to loadSkillStates from @librechat/api. One helper, three sites - Swap console.error for the project logger in the controller (Review #7) - Remove the redundant INVALID_KEY_PATTERN regex: a valid ObjectId cannot contain . or $, so isValidObjectIdString already covers it (Review #11) - Parameterize the 200-cap error toast with {{0}} interpolation driven by the error response's `limit` field, so future changes to MAX_SKILL_STATES update the UI message automatically (Review #12) - Add 24 unit tests for the new skillStates helpers (toRecord, resolveDefaultActiveOnShare, loadSkillStates, validateSkillStates- Payload, pruneOrphanSkillStates) covering success paths, malformed input, cap boundaries, and parallel-query behavior (Review #4) - Add 10 tests for injectSkillCatalog pagination covering empty accessible set, missing listSkillsByAccess, single-page filter, owned-vs-shared defaults, explicit-override precedence, multi-page collection, MAX_CATALOG_PAGES safety cap, early termination on has_more=false, additional_instructions injection, and fail-closed without userId (Review #5) Total test count: 60 (was 26 on this surface). * fix: rename skillStates ValidationError to avoid barrel-export collision packages/api/src/types/error.ts already exports a ValidationError (MongooseError extension). Re-exporting a different shape from skills/skillStates.ts through the skills barrel caused TS2308 in CI because the root index re-exports both. Rename to SkillStatesValidationError to keep the exports disjoint. * refactor: tighten tests and absorb caller guard into loadSkillStates Address the followup review findings: - Add optional `accessibleSkillIds` param to loadSkillStates so the helper short-circuits to defaults when no skills are accessible. All three controllers drop the residual 7-line conditional wrapper in favor of a single destructured call (Review #2) - Remove the unreachable `typeof key !== 'string'` check from validateSkillStatesPayload: Object.entries always yields string keys per the JS spec (Review #3) - Replace the two `as unknown as` agent casts in the injectSkillCatalog tests with a `makeAgent()` factory typed directly as the function's parameter shape (Review #4) - Tighten the MAX_CATALOG_PAGES assertion from `toBeLessThanOrEqual(11)` to `toHaveBeenCalledTimes(10)` — the loop deterministically makes exactly 10 page fetches before hitting the cap (Review #1) - Rewrite the parallel-execution test for pruneOrphanSkillStates using deferred promises instead of microtask-order assertions. The test now inspects `toHaveBeenCalledTimes(1)` on both mocks after a single Promise.resolve() yield, pinning Promise.all usage without relying on push-order into a shared array (Review #5) - Evict stale writeQueue entries on user change via a module-scoped `lastSeenUserId` sentinel. When a different user's toggle is the first one after a logout/login, the previous user's queue entry is deleted. Keeps the Map bounded without adding hook-instance effect cleanup (Review #6) * fix(test): mock loadSkillStates in openai and responses controller specs The prior refactor replaced the inline 12-line skillStates loading block with a call to loadSkillStates from @librechat/api. Both controller spec files mock @librechat/api as a flat object, so any new named import from that package is undefined in the test env. Calling `await loadSkillStates(...)` threw before recordCollectedUsage ran, surfacing as "undefined is not iterable" on the test's array destructure of `mockRecordCollectedUsage.mock.calls[0]`. Add the missing mock to both spec files alongside the existing scopeSkillIds stub. * fix: abandon stale skillStates write queues on user switch Close the cross-session leak window where an in-flight flush loop still holds a reference to a previous user's queue: it could fire its next mutateAsync under the new session's auth cookies and persist the stale snapshot to the new user's document (Codex P1). Add an `abandoned` flag on `WriteQueue`. Three mechanisms cooperate: - `getWriteQueue` marks every non-active queue abandoned when the user differs from the last-seen identity (pre-existing eviction site, now more aggressive). - A `useEffect` on `userId` calls the same abandonment pass on every render with a new active identity, covering the window between logout/login and the new user's first toggle (when `getWriteQueue` would otherwise not fire). - The flush loop checks `!queue.abandoned` in its while condition so the second and later iterations exit without firing another `mutateAsync` after the session changes. The first iteration's in-flight request (already dispatched under the original user's cookies) still runs to completion or failure on its own — only the subsequent iterations, which are the dangerous ones, are blocked.	2026-04-25 04:02:00 -04:00
Danny Avila	3e064c2f2b	🎯 feat: Per-Agent Skill Selection in Builder and Runtime Scoping (#12689) ... * feat: per-agent skill selection in builder and runtime scoping Wire skills persistence on the Agent model and enable the skills section in the agents builder panel. At runtime, scope the skill catalog to only the skills configured on each agent (intersected with user ACL). When no skills are configured, the full user catalog is used as the default. The ephemeral chat toggle overrides per-agent scoping to provide the full catalog. * fix: add scopeSkillIds to @librechat/api mock in responses unit test The test mocks @librechat/api but was missing the newly imported scopeSkillIds, causing createResponse to throw before reaching the assertions. Added a passthrough mock that returns the input array. * fix: scope primeInvokedSkills by agent's configured skills primeInvokedSkills was receiving the full unscoped accessibleSkillIds, bypassing the per-agent skill scoping applied to initializeAgent. This allowed previously invoked skills from message history to be resolved and primed even when excluded from the agent's configured skill set. Apply the same scopeSkillIds filtering to match the initializeAgent calls, so skill resolution is consistent across catalog injection and history priming. * fix: preserve agent skills through form reset and union prime scope Two related bugs in the per-agent skill selection flow: 1. resetAgentForm dropped the persisted skills array because the generic fall-through at the end of the loop excludes object/array values. Combined with composeAgentUpdatePayload always emitting skills, this caused any save of a previously-configured agent to silently overwrite skills with an empty array. Add an explicit case for skills mirroring the agent_ids handling. 2. primeInvokedSkills processes the full conversation payload, including prior handoff-agent invocations. Scoping it to only primaryAgent.skills meant a skill invoked by a handoff agent in a prior turn could not be resolved when the current primary agent had a different scope, leaving message history reconstruction incomplete. Union the per-agent scoped accessibleSkillIds across primary plus all loaded handoff agents so any skill any active agent could invoke is resolvable from history. * fix: mark inline skill removals as dirty The inline X button on the skills list called setValue without shouldDirty: true, so removing a skill via this control did not mark the skills field as dirty in react-hook-form state. When a user removed a skill with the X button and also staged an avatar upload in the same save, isAvatarUploadOnlyDirty returned true and onSubmit short-circuited to avatar-only upload, silently dropping the PATCH that would persist the skill removal. The dialog path (SkillSelectDialog) already passes shouldDirty: true on add/remove; this aligns the inline control with that behavior. * fix: restore full ACL scope for primeInvokedSkills history reconstruction Reverting the earlier scoping of primeInvokedSkills to the active-agent union. That change conflated runtime invocation scoping (which correctly gates what the model can call now) with history reconstruction (which restores bodies the model already saw in prior turns). Per-agent scoping still applies at: - Catalog injection (injectSkillCatalog via initializeAgent) - Runtime invocation (handleSkillToolCall via enrichWithSkillConfigurable, using each agent's scoped accessibleSkillIds in agentToolContexts) History priming is a read of past context, not a grant of new capability. Scoping it causes historical skill bodies to vanish from formatAgentMessages when an agent's skills list is edited mid-conversation or when the ephemeral toggle flips, which breaks message reconstruction and drops code-env file continuity for /mnt/data/{skillName}/ references. The user's ACL-accessible set is the correct and sufficient gate for history reconstruction. * fix: close openai.js skill gap and pin undefined vs [] semantics Three related gaps surfaced in review: 1. api/server/controllers/agents/openai.js was a third skill resolution site alongside responses.js and initialize.js, but still used the old activation gate (required ephemeralAgent.skills === true) and never passed accessibleSkillIds through scopeSkillIds. Per-agent scoping silently did not apply on this route. Mirror the same pattern used in responses.js so all three routes behave identically. 2. scopeSkillIds previously collapsed undefined and [] into the same "full catalog" fallback, making it impossible for a user to express "this agent has no skills." Tighten the semantics before any data is written under the old behavior: - undefined / null = not configured, full catalog - [] = explicitly none, returns [] - non-empty = intersection with ACL-accessible set Update defaultAgentFormValues.skills from [] to undefined so a brand new agent whose skills UI was never touched does not accidentally persist "explicit none" on first save (removeNullishValues strips undefined from the payload server side). 3. Add direct unit tests for scopeSkillIds covering all five cases (undefined, null, empty, disjoint, overlap, exact match, empty accessible set). 16 tests total in skills.test.ts pass. * fix: add scopeSkillIds to @librechat/api mock in openai unit test Same pattern as the earlier responses.unit.spec.js fix: the test mocks @librechat/api with an explicit object, so each newly imported symbol must be added to the mock. Without scopeSkillIds, OpenAIChatCompletion controller throws on destructuring before reaching recordCollectedUsage, causing the token usage assertions to fail.	2026-04-25 04:02:00 -04:00
Danny Avila	64ec5f18b8	⚙️ feat: Skill runtime integration: catalog, tools, execution, file priming (#12649) ... * feat: Skill runtime integration — catalog injection, tool registration, execute handler Wires the @librechat/agents SkillTool primitive into LibreChat's agent runtime: **Enums:** - Add `skills` to AgentCapabilities + defaultAgentCapabilities **Data layer:** - Add `getSkillByName(name, accessibleIds)` — compound query that combines name lookup + ACL check in one findOne **Agent initialization (packages/api/src/agents/initialize.ts):** - Accept `accessibleSkillIds` param and `listSkillsByAccess` db method - Query accessible skills, format catalog via `formatSkillCatalog()`, append to `additional_instructions` (appears in agent system prompt) - Register `SkillToolDefinition` + `createSkillTool()` when catalog is non-empty (tool appears in model's tool list) - Store `accessibleSkillIds` and `skillCount` on InitializedAgent **Execute handler (packages/api/src/agents/handlers.ts):** - Add `getSkillByName` to `ToolExecuteOptions` - `handleSkillToolCall()` intercepts `Constants.SKILL_TOOL`: extracts skillName, loads body from DB with ACL check, substitutes $ARGUMENTS, returns ToolExecuteResult with injectedMessages (skill body as isMeta user message) **Caller wiring:** - initialize.js: query skill IDs via findAccessibleResources, pass to initializeAgent + store on agentToolContexts, add getSkillByName to toolExecuteOptions, pass accessibleSkillIds through loadTools configurable - openai.js + responses.js: same pattern for their flows Requires @librechat/agents >= 3.1.65 (PR #91 exports). * feat: Skills toggle in tools menu + backend capability gating Frontend: - Add skills?: boolean to TEphemeralAgent type - Add LAST_SKILLS_TOGGLE_ to LocalStorageKeys for persistence - Add skillsEnabled to useAgentCapabilities hook - Add skills useToolToggle to BadgeRowContext with localStorage init - New Skills.tsx badge component (Scroll icon, cyan theme, permission-gated via PermissionTypes.SKILLS) - Add skills entry to ToolsDropdown with toggle + pin - Render Skills badge in BadgeRow ephemeral section Backend: - Extract injectSkillCatalog() into packages/api/src/agents/skills.ts (reduces initializeAgent module size, reusable helper) - initializeAgent delegates to helper instead of inline block - Capability-gate the findAccessibleResources query: - Agents endpoint: checks AgentCapabilities.skills in admin config - OpenAI/Responses controllers: checks ephemeralAgent.skills toggle - ACL query runs once per run, result shared across all agents * refactor: remove createSkillTool() instance from injectSkillCatalog SkillTool is event-driven only. The tool definition in toolDefinitions is sufficient for the LLM to see the tool schema. No tool instance is needed since the host handler intercepts via ON_TOOL_EXECUTE before tool.invoke() is ever called. Removes tools from InjectSkillCatalogParams/Result, drops the createSkillTool import. * feat: skill file priming, bash tool, and invoked skills state Multi-file skill support: - New primeSkillFiles() helper (packages/api/src/agents/skillFiles.ts) uploads skill files + SKILL.md body to code execution environment - handleSkillToolCall primes files on invocation when skill.fileCount > 0, returns session info as artifact so ToolNode stores the session - Skill-primed files available to subsequent bash/code tool calls Bash tool auto-registration: - BashExecutionToolDefinition added alongside SkillToolDefinition when skills are enabled, giving the model a bash tool for running scripts Conversation state: - Add invokedSkillIds field to conversation schema (Mongoose + Zod) - handleSkillToolCall updates conversation with $addToSet on success - Enables re-priming skill files on subsequent runs (future) Dependency wiring: - Pass listSkillFiles, getStrategyFunctions, uploadCodeEnvFile, updateConversation through ToolExecuteOptions - Pass req and codeApiKey through mergedConfigurable - All three controller entry points wired (initialize.js, openai.js, responses.js) * fix: load bash_tool instance in loadToolsForExecution, remove file listing - Add createBashExecutionTool to loadToolsForExecution alongside PTC/ToolSearch pattern: loads CODE_API_KEY, creates bash tool instance on demand - Add BASH_TOOL and SKILL_TOOL to specialToolNames set so they don't go through the generic loadTools path (bash is created here, skill is intercepted in handler before tool.invoke) - Remove file name listing from skill content text — it's the skill author's responsibility to disclose files in SKILL.md, not the framework * feat: batch upload for skill files, replace sequential uploads - Add batchUploadCodeEnvFiles() to crud.js: single POST to /upload/batch with all files in one multipart request, returns shared session_id - Rewrite primeSkillFiles to collect all streams (SKILL.md + bundled files) then do one batch upload instead of N sequential uploads - Replace uploadCodeEnvFile with batchUploadCodeEnvFiles across all callers (handlers.ts, initialize.js, openai.js, responses.js) * refactor: remove invokedSkillIds from conversation schema Skills aren't re-loaded between runs, so conversation-level state for invoked skills doesn't help. Skill state will live on messages instead (like tool_search discoveredTools and summaries), enabling in-place re-injection on follow-up runs. Removes invokedSkillIds from: convo Mongoose schema, IConversation interface, Zod schema, ToolExecuteOptions.updateConversation, and all three caller wiring points. * feat: smart skill file re-priming with session freshness checking Schema: - Add codeEnvIdentifier field to ISkillFile (type + Mongoose schema) - Add updateSkillFileCodeEnvIds batch method (uses tenantSafeBulkWrite) - Export checkIfActive from Code/process.js Extraction: - Add extractInvokedSkillsFromHistory() to run.ts — scans message history for AIMessage tool_calls where name === 'skill', extracts skillName args. Follows same pattern as extractDiscoveredToolsFromHistory. Smart re-priming in primeSkillFiles: - Before batch uploading, checks if existing codeEnvIdentifiers are still active via getSessionInfo + checkIfActive (23h threshold) - If session is still active, returns cached references (zero uploads) - If stale or missing, batch-uploads everything and persists new identifiers on SkillFile documents (fire-and-forget) - Single session check covers all files (batch shares one session_id) Wiring: - Pass getSessionInfo, checkIfActive, updateSkillFileCodeEnvIds through ToolExecuteOptions and all three controller entry points * feat: wire skill file re-priming at run start via initialSessions Flow: 1. initialize.js creates primeInvokedSkills callback with all deps 2. client.js calls it with message history before createRun 3. extractInvokedSkillsFromHistory scans for skill tool calls 4. For each invoked skill with files, primeSkillFiles uploads/checks 5. Returns initialSessions map passed to createRun 6. createRun passes initialSessions to Run.create (via RunConfig) 7. Run constructor seeds Graph.sessions, making skill files available to subsequent bash/code tool calls via ToolNode session injection Requires @librechat/agents with initialSessions on RunConfig (PR #94). * refactor: use CODE_EXECUTION_TOOLS set for code tool checks Import CODE_EXECUTION_TOOLS from @librechat/agents and replace inline constant checks in handlers.ts and callbacks.js. Fixes missing bash tool coverage in the session context injection (handlers.ts) and code output processing (callbacks.js). * refactor: move primeInvokedSkills to packages/api, add skill body re-injection Moves primeInvokedSkills from an inline closure in initialize.js (with dynamic requires) to a proper exported function in packages/api skillFiles.ts with explicit typed dependencies. Key changes: - primeInvokedSkills now returns both initialSessions (for file priming) AND injectedMessages (skill bodies for context continuity) - createRun accepts invokedSkillMessages and appends skill bodies to systemContent so the model retains skill instructions across runs - initialize.js calls the packaged function with all deps passed explicitly - client.js passes both initialSessions and injectedMessages to createRun * fix: move dynamic requires to top-level module imports Move primeInvokedSkills, getStrategyFunctions, batchUploadCodeEnvFiles, getSessionInfo, and checkIfActive from inline requires to top-level module requires where they belong. * refactor: skill body reconstruction via formatAgentMessages, not systemContent Replaces the lazy systemContent approach with proper message-level reconstruction: SDK (formatAgentMessages): - New invokedSkillBodies param (Map<string, string>) - Reconstructs HumanMessages after skill ToolMessages at the correct position in the message sequence, matching where ToolNode originally injected them LibreChat: - extractInvokedSkillsFromPayload replaces extractInvokedSkillsFromHistory (works with raw TPayload before formatAgentMessages, not BaseMessage[]) - primeInvokedSkills now takes payload instead of messages, returns skillBodies Map instead of injectedMessages - client.js calls primeInvokedSkills BEFORE formatAgentMessages, passes skillBodies through as the 4th param - Removed invokedSkillMessages from createRun (no more systemContent hack) - Single-pass: skill detection happens inside formatAgentMessages' existing tool_call processing loop, zero extra message iterations * refactor: rename skillBodies to skills for consistency with SDK param * refactor: move auth loading into primeInvokedSkills, pass loadAuthValues as dep The payload/accessibleSkillIds guard and CODE_API_KEY loading now live inside primeInvokedSkills (packages/api) rather than in the CJS caller. initialize.js passes loadAuthValues as a dependency and the callback is only created when skillsCapabilityEnabled. * feat: ReadFile tool + conditional bash registration + skill path namespacing ReadFile tool (read_file): - General-purpose file reader, event-driven (ON_TOOL_EXECUTE) - Schema: { file_path: string } — "{skillName}/{path}" convention - handleReadFileCall: resolves skill name from path, ACL check, reads from DB cache or storage, binary detection, size limits (256KB), lazy caching (512KB), line numbers in output - SKILL.md special case: reads skill.body directly - Dispatched alongside SKILL_TOOL in createToolExecuteHandler - Added to specialToolNames in ToolService Conditional tool registration: - ReadFile + SkillTool: always registered when skills enabled - BashTool: only registered when codeEnvAvailable === true - codeEnvAvailable passed through InitializeAgentParams from caller Skill file path namespacing: - primeSkillFiles now uploads as "{skillName}/SKILL.md" and "{skillName}/{relativePath}" instead of flat names - Prevents file collisions when multiple skills are invoked Wiring: - getSkillFileByPath + updateSkillFileContent passed through ToolExecuteOptions in all three callers * feat: return images/PDFs as artifacts from read_file, tighten caching Binary artifact support: - Images (png, jpeg, gif, webp) returned as base64 in artifact.content with type: 'image_url', processed by existing callback attachment flow - PDFs returned as base64 artifact similarly - Binary size limit: 10MB (MAX_BINARY_BYTES) - Other binary files still return metadata + bash fallback Caching: - Text cached only on first read (file.content == null check) - Binary flag cached only on first detection (file.isBinary == null) - Skill files are immutable; no redundant cache writes Registration: - ReadFileToolDefinition now includes responseFormat: 'content_and_artifact' * chore: update @librechat/agents to version 3.1.66-dev.0 and add peer dependencies in package-lock.json and package.json files * fix: resolve review findings #1,#2,#4,#5,#6,#10,#13 Critical: - #1: primeInvokedSkills now accumulates files across all skills into one session entry instead of overwriting. Parallel processing via Promise.allSettled. - #2: codeEnvAvailable now computed and passed in openai.js and responses.js (was missing, bash tool never registered in those flows) Major: - #4: relativePath in updateSkillFileCodeEnvIds now strips the {skillName}/ prefix to match SkillFile documents. SKILL.md filter uses endsWith instead of exact match. - #5: File priming guarded on apiKey being non-empty (skip when not configured instead of failing with auth error) - #6: Skills processed in parallel via Promise.allSettled instead of sequential for-of loop Minor: - #10: Use top-level imports in initialize.js instead of inline requires - #13: Log warning when skill catalog reaches the 100-skill limit * fix: resolve followup review findings N1,N2,N4 N1 (CRITICAL): Wire skill deps into responses.js non-streaming path. Was completely missing getSkillByName, file strategy functions, etc. N2 (MAJOR): Single batch upload for ALL skills' files. Resolves skills in parallel (Phase 1), then collects all file streams across skills and does ONE batchUploadCodeEnvFiles call (Phase 2). All files share one session_id, eliminating cross-session isolation issues. N4 (MINOR): Move inline require() to top-level in openai.js and responses.js, consistent with initialize.js. * fix: add mocks for new file strategy imports in controller tests * fix: restore session freshness check, parallelize file lookups, add warnings R1: Re-add session freshness check before batch upload. Checks any existing codeEnvIdentifier via getSessionInfo + checkIfActive. If the session is still active (23h window), returns cached file references with zero re-uploads. R2: listSkillFiles calls parallelized via Promise.all (were sequential in the for-of loop). R3: Log warning when skill record lookup fails during identifier persistence (was a silent empty-string fallback). * fix: guard freshness cache on single-session consistency * fix: multi-session freshness check (code env handles mixed sessions natively) The code execution environment fetches each file by its own {session_id, fileId} pair independently — no single-session requirement. Removed the sessionIds.size === 1 guard. Now checks ALL distinct sessions for freshness. If every session is still active (23h window), returns cached references with per-file session_ids preserved. If any session expired, falls through to re-upload everything in a single batch. * perf: parallelize session freshness checks via Promise.all * fix: add optional chaining for session info retrieval in primeInvokedSkills Updated the primeInvokedSkills function to use optional chaining for getSessionInfo and checkIfActive methods, ensuring safer access and preventing potential runtime errors when these methods are undefined. * fix: address review findings #1-#9 + Codex P1/P2 + session probe Critical: - #1/Codex P1: Add codeApiKey loading to openai.js and responses.js loadTools configurable (was missing, file priming broken in 2/3 paths) - Codex P1: Fix cached file name prefix in primeSkillFiles cache path (was sf.relativePath, now ${skill.name}/${sf.relativePath}) Major: - Codex P2: Honor ephemeral skills toggle in agents endpoint (check ephemeralAgent?.skills !== false alongside admin capability) - #4: Early size check using file.bytes from DB before streaming (prevents full-file buffer for oversized files) Minor: - #5: Replace Record<string, any> with Record<string, boolean | string> - #6: Localize Pin/Unpin aria-labels with com_ui_pin/com_ui_unpin - #8: Parallelize stream acquisition in primeSkillFiles via Promise.allSettled - #9: Log warning for partial batch upload failures with filenames Performance: - Session probe optimization: getSessionInfo now hits per-object endpoint (GET /sessions/{sid}/objects/{fid}) instead of listing entire session (GET /files/{sid}?detail=summary). O(1) stat vs O(N) list + linear scan. * refactor: extract shared skill wiring helper + add unit tests DRY (#3): - New skillDeps.js exports getSkillToolDeps() with all 9 skill-related deps (getSkillByName, listSkillFiles, getStrategyFunctions, etc.) - Replaces 5 identical copy-paste blocks across initialize.js, openai.js, responses.js (streaming + non-streaming paths) - One place to maintain when skill deps change Tests (#2): - 8 unit tests for extractInvokedSkillsFromPayload covering: string args, object args, missing skill tool_calls, non-assistant messages, malformed JSON, empty skillName, empty payload, dedup * fix: remove @jest/globals import, use global jest env * fix: resolve round 2 review findings R2-1 through R2-7 R2-1 (toggle semantics): openai.js + responses.js now check admin capability (AgentCapabilities.skills) alongside ephemeral toggle. Aligns with initialize.js. R2-2 (swallowed error): primeInvokedSkills now logs updateSkillFileCodeEnvIds failures (was .catch(() => {})) R2-4 (test cast): Record<string, string> → Record<string, unknown> R2-5 (DRY regression): Extract enrichWithSkillConfigurable() into skillDeps.js. Replaces 4 identical loadAuthValues blocks. Each loadTools callback is now a one-liner. JSDoc added (R2-6). R2-7 (sequential streams): primeInvokedSkills now uses Promise.allSettled for parallel stream acquisition. * fix: require explicit skills toggle + treat partial cache as miss - initialize.js: change ephemeralSkillsToggle !== false to === true (unset toggle no longer enables skills) - primeSkillFiles cache: require ALL files to have codeEnvIdentifier before using cache (partial persistence = cache miss = re-upload) - primeInvokedSkills cache: same check (allFilesWithIds.length must equal total file count) * fix: pass entity_id=skillId on batch upload, eliminates per-user cache thrashing primeSkillFiles now passes entity_id: skill._id.toString() to batchUploadCodeEnvFiles. This scopes the code env session to the skill, not the user. All users sharing a skill share the same uploaded files — no more cache thrashing from overwriting each other's codeEnvIdentifier. The stored codeEnvIdentifier now includes ?entity_id= suffix so freshness checks pass the entity_id through to the per-object stat endpoint. Both primeSkillFiles and primeInvokedSkills store consistent identifier formats. * fix: pass entity_id on multi-skill batch upload, consistent identifier format * Revert "fix: pass entity_id on multi-skill batch upload, consistent identifier format" This reverts commit c85ce2161e. * refactor: per-skill upload in primeInvokedSkills, eliminate multi-skill batch Replace the monolithic multi-skill batch upload with per-skill primeSkillFiles calls. Each skill gets its own session with entity_id=skillId, ensuring: - Correct session auth (entity_id matches on freshness checks) - Per-skill freshness caching (only expired skills re-upload) - Shared skill sessions work across users (same entity_id=skillId) - Code env handles mixed session_ids natively The big batch block (stream collection, single upload, identifier mapping) is replaced by a simple loop over primeSkillFiles, which already handles freshness caching, batch upload, and identifier persistence per-skill. * fix: resolve review findings #1,#3-5,#7,#9-11 Critical: - #1: Strip ?entity_id= query string before splitting codeEnvIdentifier into session_id/fileId (was corrupting cached file IDs in 4 locations) Major: - #4: Parallelize per-skill primeSkillFiles via Promise.allSettled - #5: Add logger.warn to all empty .catch(() => {}) on cache writes Minor: - #7: Add logger.debug to enrichWithSkillConfigurable catch block - #9: Use error instanceof Error guard in batchUploadCodeEnvFiles - #10: Move enrichWithSkillConfigurable to TypeScript in packages/api (skillConfigurable.ts), skillDeps.js wraps with loadAuthValues dep - #11: Reduce MAX_BINARY_BYTES from 10MB to 5MB (~11.5MB peak with b64) * fix: forward entity_id in session probe + always register bash tool Codex P2 (entity_id in probe): getSessionInfo now preserves and forwards query params (including entity_id) to the per-object stat endpoint. Without this, identifiers stored as ...?entity_id=... would fail auth checks because the entity_id scope was dropped. Codex P2 (bash tool availability): Remove codeEnvAvailable gate from injectSkillCatalog. Bash tool definition is now always registered when skills are enabled. Actual tool instance creation still happens at execution time in loadToolsForExecution (which loads per-user credentials). This ensures users with per-user CODE_API_KEY get bash without requiring a global env var at init time. Removes codeEnvAvailable from InjectSkillCatalogParams, InitializeAgentParams, and all three controller entry points. * fix: add debug logging to primeInvokedSkills catch, rename export alias * fix: stub bash tool when no key + remove PDF artifact path Codex P1 (bash tool): When CODE_API_KEY is unavailable, create a stub tool that returns "Code execution is not available. Use read_file instead." This prevents "tool not found" errors from the model repeatedly calling bash_tool in no-code-env deployments while still registering the definition for per-user credential users. Codex P2 (PDF artifacts): Remove PDF image_url artifact path. The host artifact pipeline processes image_url via saveBase64Image which fails for PDFs. PDFs now fall through to the generic binary handler ("Use bash to process"). TODO comment for future document artifact support. Also: isImageOrPdf → isImage in early size checks (PDFs are no longer treated as artifact candidates). * fix: remove dead PDF_MIME constant, hoist skillToolDeps, document session_id - #7: Remove unused PDF_MIME constant (dead code after PDF artifact removal) - #11: Hoist skillToolDeps to module-level constant (avoid per-call allocation) - #6: Document that CodeSessionContext.session_id is a representative value; ToolNode uses per-file session_id from the files array * fix: call toolEndCallback for skill/read_file artifacts + clear codeEnvIdentifier on re-upload Codex P1 (toolEndCallback bypass): skill and read_file handler branches returned early, bypassing the toolEndCallback that processes artifacts (image attachments). Now calls toolEndCallback when the result has an artifact, using the same metadata pattern as the normal tool.invoke path. Codex P1 (stale identifiers): upsertSkillFile now $unset's codeEnvIdentifier alongside content and isBinary when a file is re-uploaded. Prevents the freshness cache from returning references to old file content after a skill file is replaced. * fix: add session_id comment at cached path, rename skillResult to handlerResult * fix: return content_and_artifact from bash stub so result.content is populated * fix: deterministic skill lookup, dedup warning, and multi-session freshness check - getSkillByName: add sort({updatedAt:-1}) so name collisions resolve deterministically to the most recently updated skill - injectSkillCatalog: warn when multiple accessible skills share a name - primeSkillFiles: check ALL distinct sessions for freshness, not just the first file's session, preventing stale refs after partial bulkWrite * refactor: update icon import in Skills component - Replaced the Scroll icon with ScrollText in the Skills component for improved clarity and consistency in the UI. * fix: SKILL.md cache parity, gate bash_tool on code env, fix read_file too-large message - primeSkillFiles: filter SKILL.md from returned files array on fresh upload so cached and non-cached paths return identical file sets (SKILL.md is still on disk in the session for bash access) - injectSkillCatalog: only register bash_tool when codeEnvAvailable is true; thread the flag from all three CJS callers via execute_code capability check - handleReadFileCall: tell the model to invoke the skill first before suggesting /mnt/data paths for oversized files * fix: use EnvVar constant, deduplicate auth lookup, validate batch upload, stream byte limit - Replace hardcoded 'LIBRECHAT_CODE_API_KEY' with EnvVar.CODE_API_KEY in skillConfigurable.ts and skillFiles.ts - Resolve code API key once at run start in initialize.js and pass to both primeInvokedSkills and enrichWithSkillConfigurable via optional preResolvedCodeApiKey param, eliminating redundant loadAuthValues calls - Add response structure validation in batchUploadCodeEnvFiles before accessing session_id/files to surface unexpected responses early - Add streaming byte counter in handleReadFileCall that aborts and destroys the stream when accumulated bytes exceed MAX_BINARY_BYTES, preventing full file buffering when DB metadata is inaccurate * refactor: update icon import in ToolsDropdown component - Replaced the Scroll icon with ScrollText in the ToolsDropdown component for improved clarity and consistency in the UI. * fix: partial upload failure detection, EnvVar in initialize.js, declaration ordering - primeSkillFiles: return null (failure) when batch upload partially succeeds — missing bundled files would cause runtime bash/read failures with missing paths in code env - initialize.js: replace hardcoded 'LIBRECHAT_CODE_API_KEY' with EnvVar.CODE_API_KEY imported from @librechat/agents - initialize.js: move enabledCapabilities, accessibleSkillIds, and codeApiKey declarations before the toolExecuteOptions closure that references them (eliminates reliance on temporal dead zone hoisting)	2026-04-25 04:02:00 -04:00
Danny Avila	181d705579	🧹 fix: Clean Up Orphaned Agent File Stubs After Deletion (#12781) ... * 🧹 fix: Prune Orphaned File References on File Deletion Deleting a file via the Manage Files tab left its file_id in every agent's tool_resources.*.file_ids. Stubs accumulate until the frontend dedupe keys them as duplicates and blocks all new uploads (issue #12776). - Add removeAgentResourceFilesFromAllAgents in packages/data-schemas: a single updateMany/$pullAll across every EToolResources category. - Invoke it from processDeleteRequest after db.deleteFiles so every referencing agent is cleaned up, not just the one passed in req.body. - Wrap the cleanup in try/catch so a stale agent update cannot mask a successful file deletion. * 🧼 fix: Prune Orphaned File References on Agent Update Already-affected agents would stay broken even after the delete-time fix: the stubs sit on the agent document until something strips them. Heal them on the next save (issue #12776). - Add collectToolResourceFileIds + stripFileIdsFromToolResources helpers in @librechat/api — centralizing the tool_resources traversal used by the controller and the follow-up migration script. - In updateAgentHandler, check the effective tool_resources against the files collection. When orphans are found, either strip them from the incoming tool_resources (if the update sets them) or run the bulk cleanup (if the update leaves tool_resources untouched). * 🧰 chore: Add Migration to Clean Up Orphaned Agent File References Complements the delete-time and save-time fixes by healing agents that already accumulated orphan stubs before the upgrade (issue #12776). The script is idempotent — re-running it on a clean database is a no-op. - Add config/migrate-orphaned-agent-files.js following the existing migrate-*.js convention: --dry-run by default omitted (writes by default) and --batch-size= tuning knob. Streams agents via cursor. - Register migrate:orphaned-agent-files and :dry-run npm scripts. - Reuse collectToolResourceFileIds from @librechat/api so migration and runtime share the same traversal logic. * 🩹 fix: Address Codex/Copilot Review on Orphaned Agent File Cleanup Refines the #12776 fix series based on automated review feedback. - Scope save-time pruning to the current agent only. When a PATCH carries tool_resources, strip orphans from the incoming payload and pay the DB round-trip only then. Removes the collection-wide updateMany previously triggered when tool_resources was absent (Codex P2 / Copilot). - Wrap the orphan check in try/catch so a transient db.getFiles failure can't turn a good save into a 500 (comprehensive review #1). - Replace Object.values(EToolResources) casts with an explicit list of agent-side categories in both orphans.ts and agent.ts. code_interpreter belongs to the Assistants API and isn't a key of AgentToolResources — including it was a type lie and generated dead MongoDB clauses (comprehensive review #3, #8). - Export TOOL_RESOURCE_KEYS from @librechat/api and consume it in the migration script, dropping one duplicated definition (#4). - Cap migration results.details at 50 sample entries so the memory footprint stays bounded on deployments with thousands of corrupted agents (Codex P3). - Add migrate:orphaned-agent-files:batch npm script to match the convention set by migrate-agent-permissions / migrate-prompt-permissions (#7). - Add controller-level tests covering the three orphan-pruning paths: strip from incoming tool_resources, leave alone when tool_resources is absent, swallow db.getFiles errors and still save (#6). - Back pre-existing "should validate tool_resources in updates" test's file_ids with real File docs — the new pruning would otherwise strip them, and that test is about OCR conversion / schema filtering, not file existence. Register the File model in beforeAll so the fixture works. * 🩹 fix: Tighten TOOL_RESOURCE_KEYS Type and Align Migration Sample Output Two follow-ups from the second review pass. - Type data-schemas' TOOL_RESOURCE_KEYS as ReadonlyArray<keyof AgentToolResources> instead of readonly string[]. Data-schemas depends on data-provider, so the import is clean. Catches typos and aligns with the matching export in @librechat/api — doesn't guarantee exhaustiveness, but that's a TypeScript limitation, not a workspace one. - Align the migration's console output with DETAIL_SAMPLE_LIMIT: print every collected detail (up to 50) and, when more agents were affected than the sample size allowed, show a truncation notice. The old hard cap of 25 meant affected agents in the 26-50 range were collected but never shown. * ✅ test: Add Integration Coverage for Orphan Cleanup Paths (#12776) Exercise the delete-time and migration paths end-to-end against a real in-memory Mongo. Catches integration bugs the isolated unit tests on each layer couldn't. - api/server/services/Files/process.integration.spec.js — the primary repro: seed an Agent + File, call processDeleteRequest, assert the file_id disappears from every referencing agent's tool_resources while unrelated agents stay untouched. Also covers the no-op case and confirms a failure in the new cleanup step cannot roll back the file deletion itself. - api/test/migrate-orphaned-agent-files.spec.js — drives the migration module: --dry-run reports without writing, apply mode prunes across every tool_resource category, re-running is idempotent, and DETAIL_SAMPLE_LIMIT caps the in-memory sample on wide corruption. Mocks only the connect helper (the spec owns the mongoose instance) so the real migration code path — cursor, $pullAll, reduce — runs. * 🔒 fix: Run Orphan Cleanup Migration in System Tenant Context Codex P2 catch: under TENANT_ISOLATION_STRICT=true, the migration throws on the very first Agent.countDocuments() because the tenant isolation plugin fail-closes on queries without tenant context — which makes migrate:orphaned-agent-files unusable on the exact deployments most likely to have accumulated corruption. - Wrap the scan/prune body in runAsSystem so queries bypass the tenant filter (SYSTEM_TENANT_ID sentinel). The migration legitimately needs cross-tenant visibility — this is the same pattern seedDatabase and the S3 refresh job already use. - Add a regression test that spies on Agent.countDocuments() and asserts the active tenantStorage context is SYSTEM_TENANT_ID during the call. Pins the wrap against future regressions without the brittleness of toggling the strict-mode env var (which caches on first read). Note: the delete-time and save-time paths already run inside an authenticated HTTP request where tenantStorage.run is set by auth middleware, so the cleanup naturally scopes to the current tenant — which is the correct behavior there since file ownership is tenant-scoped. * 🧹 chore: Drop Unused path Import From Process Integration Spec Leftover from an earlier iteration that resolved the migration path via path.resolve before I switched to a relative require. The import does nothing now — removing it.	2026-04-22 11:35:48 -07:00
Danny Avila	d2cbd551b7	🤝 fix: Load Handoff Agents for Agents API (#12740) ... * 🤝 fix: load handoff sub-agents on OpenAI-compat endpoints (#12726) Extracts the BFS discovery + ACL-gated initialization of handoff sub-agents into a shared `discoverConnectedAgents` helper in `@librechat/api` and wires it into the OpenAI-compatible `/v1/chat/completions` and Open Responses `/v1/responses` controllers. These endpoints previously only passed the primary agent config to `createRun` while keeping `primaryConfig.edges` intact, which forced `MultiAgentGraph` into multi-agent mode without loading the referenced sub-agents and caused StateGraph to throw "Found edge ending at unknown node <id>". The discovery helper also filters orphaned edges (deleted sub-agents or those the caller lacks VIEW permission on), so API users see the same graceful fallback the chat UI already had. * 🧪 fix: use ServerRequest in discovery spec helpers CI `tsc --noEmit -p packages/api/tsconfig.json` caught that the test helpers typed `req` as `express.Request`, which is not assignable to `DiscoverConnectedAgentsParams.req` (typed as `ServerRequest` whose `user` is `IUser`). Local jest passed because ts-jest is transpile-only, but the CI typecheck uses the full compiler. * 🪲 fix: drop orphan edges on both endpoints, not just `to` Addresses the P1 codex finding on #12740: `filterOrphanedEdges` previously only removed edges whose `to` referenced a skipped agent. Edges whose `from` was a skipped agent — the symmetric case in a bidirectional graph like `A <-> B` where `B` is deleted or the user lacks VIEW on it — leaked through to `createRun` and re-triggered `Found edge ending at unknown node <id>` at StateGraph compile time. The filter now drops an edge if either endpoint references a skipped id, and the existing `to`-only test cases were updated to reflect the stricter behavior. Adds a bidirectional-graph regression test in `discovery.spec.ts`. * 🔒 fix: enforce REMOTE_AGENT ACL on handoff sub-agents for API routes Addresses the second P1 codex finding on #12740: the OpenAI-compat `/v1/chat/completions` and Open Responses `/v1/responses` routes gate the primary agent on `REMOTE_AGENT` (via `createCheckRemoteAgentAccess`), but `discoverConnectedAgents` was checking handoff sub-agents against the looser in-app `AGENT` resource type. That allowed a remote caller who could reach the orchestrator but had only in-app visibility on a sub-agent to invoke it via the API — bypassing the remote-sharing boundary. Adds an optional `resourceType` param to `discoverConnectedAgents` (defaulting to `AGENT` for the chat UI path) and passes `ResourceType.REMOTE_AGENT` from both API controllers so every discovered sub-agent clears the same sharing boundary enforced at route entry. * 🧯 fix: enforce allowedProviders for discovered sub-agents Addresses the third P1 codex finding on #12740: `discoverConnectedAgents` forwarded the caller's `endpointOption` verbatim into `initializeAgent`, but on the OpenAI-compat routes that option's `endpoint` is the primary agent's provider (e.g. `openai`), not `agents`. `initializeAgent` only enforces `allowedProviders` when `isAgentsEndpoint(endpointOption.endpoint)` is true, so handoff sub-agents silently bypassed the provider allowlist configured under `endpoints.agents.allowedProviders`. Override `endpointOption.endpoint` to `EModelEndpoint.agents` for every per-sub-agent init call. The primary agent still uses the caller's endpointOption as before — this only affects the BFS-loaded handoff targets. Regression test asserts the override. * ✂️ fix: prune unreachable sub-agents after orphan-edge filtering Addresses the fourth P1 codex finding on #12740: BFS eagerly initializes every sub-agent referenced in the primary's edge scan, but once `filterOrphanedEdges` drops edges whose endpoints were skipped, some of those sub-agents end up disconnected from the primary. In an `A -> B -> C` graph (edges stored directly on A) where B is skipped (missing or no VIEW), both edges are filtered, but C was already loaded and would still be passed to `createRun` — which flips into multi-agent mode on `agents.length > 1` and turns C into an unintended parallel start node. After filtering edges, compute the set of agent ids reachable from the primary through the surviving edge set and prune `agentConfigs` to that set. Two regression tests added: one for the pruning case, one that confirms agents connected via surviving edges are still kept. * 🔁 fix: don't seed initialize.js agentConfigs from the pre-pruning callback Addresses the fifth P1 codex finding on #12740: `onAgentInitialized` fires during BFS, BEFORE the helper prunes agents that become disconnected once `filterOrphanedEdges` runs. Writing the sub-agent straight into the outer `agentConfigs` there and then only additively merging the pruned `discoveredConfigs` left stranded entries in the outer map, and `AgentClient` would still hand them to `createRun` as extra parallel start nodes (the exact failure mode the pass-4 prune was meant to eliminate for the API controllers). Drop the `agentConfigs.set` from the callback and replace the additive merge with a direct copy from `discoveredConfigs`, which is now the single authoritative source of what the run should see. The per-agent tool context map is still populated during BFS — stale entries there are harmless because they're only read by closure inside `ON_TOOL_EXECUTE` and are unreachable once the agent is not in `agentConfigs`. * 🔬 fix: address audit findings on discovery helper Resolves findings from a comprehensive external audit of #12740. **Finding 1 (CRITICAL) — stale edges survive the reachability prune.** The pass-4 prune removed unreachable agents from `agentConfigs` but left matching edges in the return value. In an `A -> B -> C -> D` graph (all edges stored on A) where B is skipped, `filterOrphanedEdges` drops A->B and B->C but keeps C->D (neither endpoint is skipped). The caller then sees `agentConfigs` without C/D but `edges` still references them, flipping `createRun` into multi-agent mode with mismatched agents/edges — the exact crash this PR is supposed to fix. Now filter the edge list to the reachable set in the same pass, so the returned shape is self-consistent: every edge endpoint is either the primary id or a key of `agentConfigs`. New regression test covers A->B->C->D with B skipped. **Finding 2 (MAJOR) — unconditional `getModelsConfig` on every API request.** The OpenAI-compat and Responses controllers called `getModelsConfig(req)` and `discoverConnectedAgents` even when the primary agent had no edges (the common single-agent API case). Gate both behind `primaryConfig.edges?.length > 0` so single-agent runs don't pay that cost. **Finding 5 (MINOR) — silent mutation of caller's `primaryConfig.userMCPAuthMap`.** The helper aliased that object and then `Object.assign`'d sub-agent entries into it, changing the caller's config in-place. Shallow-clone up front so the returned merged map is the only destination. **Finding 7 (NIT) — dead `?? []` coalescing.** `filterOrphanedEdges` always returns a concrete array, so the `discoveredEdges ?? []` fallback was never reached. Simplified the `primaryConfig.edges = …` assignment. Also adds a test that verifies `primaryConfig.userMCPAuthMap` is not mutated in-place. * 🧹 chore: address audit NITs on discovery helper Addresses two NIT findings from the post-fix audit: **F1** — the shallow clone on `primaryConfig.userMCPAuthMap` was only applied on the primary side; the `else` branch (hit when the primary had no MCP auth and the first sub-agent seeds the map) assigned the sub-agent's `config.userMCPAuthMap` directly, so a later sub-agent's `Object.assign` mutated the first one's map in place. Harmless in practice (per-request ephemeral objects) but asymmetric. Clone in the else branch too. Test added. **F2** — `initialize.js` had a defensive `if (agentConfigs.size > 0 && !edges) edges = []` normalizer. Pre-existing dead code: the helper now always returns a concrete array from `filteredEdges.filter(...)`. Removed for clarity. * 🕸 fix: require all sources reachable when traversing fan-in edges Addresses the seventh P1 codex finding on #12740: the reachability BFS advanced through an edge as soon as any of its `from` endpoints matched the current frontier node (`sources.includes(current)`), but the subsequent edge filter required ALL sources to be reachable (`every`). The two-semantics mismatch let a fan-in edge like `{from: ['A','B'], to: 'C'}` mark C reachable purely via A even when B had no path from the primary, then drop the edge itself at filter time. Result: C survived in `agentConfigs` with no surviving edge connecting it to A, so `createRun` flipped into multi-agent mode on `agents.length > 1` and C ran as an unintended parallel root. Replace the BFS with a fixed-point iteration keyed on the same all-sources-reachable predicate used by the filter, so traversal and filtering stay aligned and multi-source edges only fire once every source is in the reachable set. Two regression tests added: - `{from: ['A','B'], to: 'C'}` with B having no incoming path — asserts neither B nor C leak into the result. - `A -> B`, `A -> C`, `['B','C'] -> D` — asserts the fan-in edge fires and D becomes reachable once both B and C are. * 🔀 fix: match SDK OR semantics for multi-source edge reachability Reverts the all-sources-required reachability gate from 4982f1c3b and replaces it with an any-source-reachable model, which matches how `@librechat/agents`'s `MultiAgentGraph.createWorkflow` actually wires multi-source edges at runtime (per-source `builder.addEdge(source, destination)`). With the previous `every` gate, a legitimate handoff edge `{ from: ['A', 'B'], to: 'C' }` where B had no incoming path was pruned along with C, regressing OR-semantics routing that the SDK would otherwise handle correctly. New behavior: 1. Reachability: an edge advances when ANY of its `from` endpoints is already reachable. Fixed-point iteration over `filteredEdges`. 2. Edge filter: keep an edge when it has at least one reachable source AND all destinations are reachable (a missing destination would still crash `StateGraph.compile` with `Found edge ending at unknown node`). 3. Agent prune: keep agents that are reachable OR referenced on any endpoint of a surviving edge. The second clause preserves co-sources in multi-source edges (B in `{ from: ['A','B'], to: 'C' }` when nothing else reaches B) so the SDK's per-source `addEdge` — and the `validateEdgeAgents` safety-net I added to the SDK in #111 — still finds B as a node. The pass-audit A->B->C->D regression test continues to pass: with B skipped, `filterOrphanedEdges` drops both B-adjacent edges, reachability never expands past A, C->D has no reachable source so it gets filtered, and C/D are pruned because they're neither reachable nor referenced. * ✂️ fix: strip skipped co-members from multi-source/multi-dest edges Addresses codex pass-9 P2 on #12740. `filterOrphanedEdges` previously dropped an edge whenever any `from` id was skipped, which was correct for scalar edges but over-aggressive for multi-source ones: the agents SDK adds one `builder.addEdge(source, destination)` per source, so `{ from: ['A','B'], to: 'C' }` with B skipped still has a valid `A -> C` route that was being thrown away. Now sanitize each endpoint: - Scalar skipped → drop the whole edge (no route survives). - Array with some skipped → strip the skipped ids, keep the edge with the surviving members. If the array empties out, drop the edge. Symmetric handling for `to` covers multi-destination fan-out when one co-destination is skipped. Tests updated/added: - `strips skipped co-sources from multi-source edges…` - `strips skipped co-destinations from multi-destination edges` - `drops multi-member edges only when every member on a side is skipped` - Discovery-side: `preserves valid routes when one co-source of a multi-source edge is skipped` asserts the end-to-end behavior — skipped co-source B gets stripped from the edge, A->C routing survives, and C remains in `agentConfigs`. * 🔓 fix: respect SHARE-on-AGENT fallback for handoff ACL on API routes Addresses codex pass-10 P1 on #12740. The API controllers were handing `discoverConnectedAgents` a raw `PermissionService.checkPermission` call against `ResourceType.REMOTE_AGENT`, but the route-level middleware (`createCheckRemoteAgentAccess`) authorizes the primary agent via `getRemoteAgentPermissions`, which first consults the AGENT ACL and treats owners with the SHARE bit as remotely authorized even without an explicit REMOTE_AGENT grant. The mismatch meant a user could open the primary via `/v1/chat/completions` or `/v1/responses`, but their own owned handoff sub-agents were silently skipped — breaking multi-agent handoffs for the common "owner runs their own multi-agent orchestrator" case. Both controllers now pass `discoverConnectedAgents` a `checkPermission` wrapper that delegates to `getRemoteAgentPermissions` (with `getEffectivePermissions` injected from `PermissionService`) and compares the returned bitmask against the required permission via `hasPermissions`. Sub-agents are now authorized by the exact same rules the route middleware applies to the primary. * 🌱 fix: preserve user-defined parallel-start branches Addresses codex pass-11 P2 on #12740. The post-filter reachability prune seeded only from `primaryConfig.id`, which killed `MultiAgentGraph`'s legitimate multi-start pattern — a user-defined edge like `X -> Y` where X has no incoming path (X is an intentional parallel starting node, run alongside the primary) was being dropped because neither X nor Y was reachable from the primary. Reconcile the tension with pass-4 ("prune accidental orphans when an intermediate is skipped") by using pre-filter reachability as the signal: - An agent that WAS reachable from the primary via the original (pre-filter) edges but loses that path when `filterOrphanedEdges` runs is an accidental orphan (a skipped hop broke the chain) — prune. - An agent that was NEVER reachable from the primary, even pre-filter, is an intentional parallel start — seed it into post-filter reachability so its component survives. Surviving-edge endpoint references still keep an agent (co-sources in multi-source edges). New test `preserves user-defined parallel-start branches disconnected from the primary` covers the pass-11 scenario; the existing `A->B->C->D, B skipped` regression test continues to pass because C/D were pre-filter reachable through B and lose that reachability after filtering. * 🎯 fix: tighten parallel-start seed criterion to 'no pre-filter incoming edge' Addresses codex pass-12 P1 on #12740. The pass-11 seed heuristic — 'agent is in `agentConfigs` but was not pre-filter reachable from the primary' — was too permissive. A downstream agent like Y in `X -> Y` where X gets skipped (missing / no VIEW) was never pre-filter reachable from the primary either, so the old rule promoted Y to a parallel start node and discovery returned `agents: [primary, Y]` with no connecting edge. The SDK then ran Y as an unintended parallel root — exactly the orphan behavior pass-4 wanted to prevent. Tighter criterion: seed a post-filter reachability root only when the agent had NO incoming edge in the pre-filter graph. That matches `MultiAgentGraph.analyzeGraph`'s "no-incoming-edge" definition of a start node applied to the user's original declared topology, so: - `A -> B` plus a user-defined `X -> Y` parallel branch: X has no incoming pre-filter → seeded → X and Y both survive. - `A -> B` plus `X -> Y` with X skipped: Y had an incoming pre-filter (`X -> Y`) → NOT seeded → Y is pruned as the orphan it is. - `A -> B -> C` with B skipped: C had an incoming pre-filter (`B -> C`) → NOT seeded → C is pruned. New test `does not promote a downstream orphan to a parallel start when its only upstream is skipped` locks in the pass-12 scenario. The pass-11 `preserves user-defined parallel-start branches` test continues to hold. * 📁 fix: don't enforce AGENT-only file ACL on REMOTE_AGENT API callers Addresses codex pass-13 P1 on #12740. When I refactored the API controllers' DB-method bundle, I inadvertently started forwarding `filterFilesByAgentAccess` into `initializeAgent`. That helper calls `checkPermission` with `resourceType: ResourceType.AGENT`, but these routes authorize callers through `REMOTE_AGENT` (via `getRemoteAgentPermissions`). A user granted `REMOTE_AGENT_VIEWER` on a shared agent but lacking direct `AGENT_VIEW` could invoke the agent yet all its owner-attached context files would get silently filtered out — breaking `file_search`/context retrieval for remote consumers. Drop `filterFilesByAgentAccess` from the OpenAI-compat and Responses controllers' `dbMethods` (and remove the now-unused import). The chat UI's `initialize.js` keeps it since that path legitimately authorizes at the AGENT level. No functional change inside the helper — passing `undefined` simply tells `primeResources` to skip the per-file ACL filter, restoring the pre-refactor API behavior. * 🪓 fix: strip unreachable co-sources from surviving multi-source edges Addresses codex pass-14 P1 on #12740. The earlier pass-8 fix kept any agent referenced as an endpoint of a surviving edge (via a `referencedByEdge` fallback) to avoid the SDK's `validateEdgeAgents` failing on missing nodes. But that fallback propped up unreachable co-sources too: with `[A -> C, X -> B, [B,C] -> D]` and X skipped, `X -> B` gets filtered, the `[B,C] -> D` fan-in survives because C is reachable, and B stays in `agentConfigs` solely because the fan-in still lists it. `MultiAgentGraph.analyzeGraph` then sees B with no incoming edge and runs it as an unintended parallel root. Sanitize surviving edges instead: for a kept edge whose `from` is an array, filter out any co-source that isn't reachable. The SDK's per-source `addEdge` fires independently, so dropping an unreachable co-source doesn't invalidate the remaining routes — in the scenario above `[B,C] -> D` becomes `[C] -> D`, every endpoint of every surviving edge is now reachable, and the agent prune collapses to a strict `reachable.has(agentId)` check. No more referenced-by-edge fallback. Regression test added: `strips unreachable co-sources from surviving multi-source edges (no stray parallel root)` — asserts B is absent from every surviving edge endpoint and the fan-in's `from` is just `['C']`. All 22 prior discovery tests still pass unchanged.	2026-04-20 02:20:43 -04:00
Danny Avila	6183303653	🔉 fix: Normalize audio MIME types in STT format validation (#12674) ... * fix: normalize audio MIME types in STT format validation Use getFileExtensionFromMime() to normalize non-standard MIME types (e.g. audio/x-m4a, audio/x-wav, audio/x-flac) before checking against the accepted formats list in azureOpenAIProvider. This is the same class of bug as #12608 (text/x-markdown), but for STT audio validation. Only audio/ and video/ MIME prefixes are normalized to prevent non-audio types from matching via the webm default fallback. Export getFileExtensionFromMime for testability. Fixes #12632 * fix: reject unknown audio subtypes in STT format validation Use MIME_TO_EXTENSION_MAP for normalization instead of getFileExtensionFromMime() which falls back to 'webm' for unrecognized types. Gate raw subtype matching on audio/video prefix to prevent non-audio types (e.g. text/webm) from passing validation. Resolves Codex review comment about unknown subtypes silently passing. --------- Co-authored-by: Tobias Jonas <t.jonas@innfactory.de>	2026-04-15 09:58:07 -04:00
Caesar Isidro Va-ay	9b9a86d17d	🔀 fix: Resolve Action Tools by Exact Name to Prevent Multi-Action Domain Collision (#12594) ... * 🐛 fix: resolve Action tools by exact tool name to prevent multi-action collision When two OpenAPI Actions on the same Agent share a hostname, the second action's entry overwrote the first in the encoded-domain Map and one action's tools silently disappeared from the LLM payload. The buggy resolution loop also used substring matching, which caused similar shadowing for any encoded-domain prefix overlap. This change builds a Map keyed on the full tool name (`<operationId>_action_<encoded-domain>`) directly, mirroring the exact lookup pattern that getActionToolDefinitions already uses. Each function in an action's spec gets its own slot, so two actions sharing a hostname no longer collide. Both the new and the legacy domain encodings are registered for each function so agents whose stored tool names predate the current encoding still resolve. Applied at all three call sites that had the buggy pattern: - processRequiredActions (assistants/threads path) - loadAgentTools (agent build path) - loadActionToolsForExecution (agent execution path) Adds three regression tests covering both ordering directions and the execution path. Tests fail without the fix and pass with it. * 🐛 fix: Normalize action tool name at lookup + cover assistants path Follow-up to the multi-action domain collision fix. Addresses PR #12594 review feedback: **Must-fix #1 — short-hostname lookup mismatch.** The toolToAction map is keyed on the `_`-collapsed domain, but `agent.tools` and `currentAction.tool` persist the raw `domainParser(..., true)` output, which for hostnames ≤ ENCODED_DOMAIN_LENGTH is a `---`-separated string (e.g. `medium---com`). Exact-match `Map.get()` missed those keys and silently dropped the tool. Fix: normalize every incoming tool name through a new `normalizeActionToolName` helper before the lookup in `loadAgentTools`, `processRequiredActions`, and `loadActionToolsForExecution`. **Must-fix #2 — assistants path coverage.** `processRequiredActions` received the same structural rewrite but had zero tests. Added a regression test under `multi-action domain collision regression` that drives two shared-hostname actions through the assistants path and asserts each tool reaches its own request builder. **Must-fix #3 — legacy encoding branch coverage.** The `if (legacyNormalized !== normalizedDomain)` registration was never exercised by any test. Added a test where `agent.tools` stores the legacy-format name and asserts it still resolves. **Should-fix #4 — DRY the registration loop.** Extracted `registerActionTools({ toolToAction, functionSignatures, normalizedDomain, legacyNormalized, makeEntry })`. All three call sites now share the same key-building logic; the key template lives in one place. **Should-fix #5 — remove stale optional chaining.** In `loadActionToolsForExecution`, `functionSignature?.description ?? ''` became `functionSignature.description` — `sig` is always defined by the iterator, matching the style of `loadAgentTools`. **Should-fix #6 — drop unreachable `!requestBuilder` guard.** Entries in `processRequiredActions` are now pre-built with `requestBuilder: requestBuilders[sig.name]`, which `openapiToFunction` always produces alongside the signature, so the guard is dead. **Should-fix #7 — unwrap `actionSetsData`.** It now holds a bare `Map` instead of `{ toolToAction }`; the sentinel `!actionSetsData` check still works because `new Map()` is truthy. Also added a short-hostname regression test (`loadAgentTools resolves raw ---separated tool names`) that reproduces Must-fix #1: it fails against the previous commit (0 create calls) and passes with the normalization in place. 41 tests, all passing. The 3 new regression tests are under `multi-action domain collision regression` and cover the assistants path, the legacy encoding branch, and the short-hostname lookup path. * 🐛 fix: Tighten registerActionTools key handling and assistants test Follow-up to d643444 addressing the second review pass on PR #12594. **ESLint** — Two prettier errors in the spec file (multi-line arrow function bodies that should fit on one line). Auto-fixed. **[MINOR] operationId containing `---` → key mismatch.** The lookup path collapsed every `actionDomainSeparator` sequence in the full tool name, but the registration path passed `sig.name` through unchanged. A `---` that survived into an operationId would shift the underscore boundary at lookup and miss its own key. Fix in `registerActionTools`: normalize `sig.name` with the same helper so registration and lookup always agree on the canonical form. `sanitizeOperationId` strips the characters that produce `---` in practice, so this is theoretical hardening, not a fix for a known reproducer. **[MINOR] Same-operationId + same-hostname silent overwrite.** Two actions sharing both an operationId and a hostname still produced a silent `Map.set()` overwrite (the new key is identical, so neither the operationId nor the domain disambiguates). Added a `setKey` helper inside `registerActionTools` that logs a `[Actions] operationId collision: ...` warning whenever a key is already present, naming the overwriting action_id. The silent-overwrite mode from the original bug cannot reappear under a different disguise without surfacing in the logs. **[NIT] processRequiredActions test simulated a runtime crash.** `mockCreateActionTool` returned a tool with `_call: jest.fn()`, which resolves to `undefined`. `processRequiredActions` chains `.then(handleToolOutput).catch(handleToolError)` directly onto that return, so `undefined.then(...)` threw synchronously and the outer try/catch funneled the error into `handleToolError`. Creation count assertions still passed because `createActionTool` runs before the crash, but the test was silently exercising the failure path. Updated the global mock to `_call: jest.fn().mockResolvedValue('{"status":"ok"}')` so the success path runs end-to-end. The assistants regression test now executes in ~5ms instead of ~90ms, which corroborates that it's no longer hitting the synchronous throw. **[NIT] Duplicated rationale comments.** All three call sites carried multi-line comment blocks restating why we key on the full tool name. That rationale now lives canonically in `registerActionTools`'s JSDoc; the inline blocks collapsed to `// See registerActionTools for the key-shape rationale.` Net -22 lines of comments. 41/41 tests still pass; lint is clean. * 🐛 fix: Scope tool-name normalization to the encoded-domain suffix Follow-up to f22228e addressing the Codex P1 on PR #12594. **Regression.** The previous commit normalized the entire tool name (`normalizeActionToolName(sig.name)` at registration, full-name `.replace()` at lookup) to handle operationIds that theoretically contained `---`. But `openapiToFunction` uses user-supplied operationIds verbatim and the fallback `sanitizeOperationId` only strips characters outside `[a-zA-Z0-9_-]`, so specs can legitimately produce operationIds like `get_foo---bar` and `get_foo_bar` side by side. Collapsing `---` to `_` across the entire key merged those two into a single map slot — one silently overwrote the other, and both tool requests routed to the surviving entry's request builder. **Fix.** Limit normalization to the encoded-domain portion of the full tool name, i.e. the substring after the last `actionDelimiter`. The operationId half is left verbatim, so hyphens-vs-underscores remain disambiguating. The short-hostname bug (Must-fix #1 from the original review) is still covered because the `---` → `_` collapse still happens on the domain suffix where it matters: ```js const normalizeActionToolName = (toolName) => { const delimiterIndex = toolName.lastIndexOf(actionDelimiter); if (delimiterIndex === -1) return toolName; const prefixEnd = delimiterIndex + actionDelimiter.length; const encodedDomain = toolName.slice(prefixEnd); return toolName.slice(0, prefixEnd) + encodedDomain.replace(domainSeparatorRegex, '_'); }; ``` `registerActionTools` reverts to `sig.name` verbatim — no more `normalizeActionToolName(sig.name)` ahead of the key build. **Regression test.** Added `loadAgentTools distinguishes operationIds that differ only by ---` vs `_`` under `multi-action domain collision regression`. It loads two actions sharing a hostname whose operationIds are `get_foo---bar` and `get_foo_bar` respectively, each pointing at a different path (`/foo-bar`, `/foo_bar`), and asserts that each tool resolves to its own request builder. Verified the test fails against f22228e (`hyphenTool` resolves to `/foo_bar` — the sibling's builder) and passes with this commit. 42/42 tests pass; lint clean.	2026-04-13 09:08:06 -04:00
Airam Hernández Hernández	277fdd2b43	🪪 feat: Optimized Entra ID Group Sync with Auto-Creation (#12606) ... * feat: implement optimized Entra group sync with auto-creation ## Changes ### MUST FIX (Critical Issues) - RESOLVED 1. **BUG FIX: Prevent unintended user removal from existing groups** - ISSUE: db.syncUserEntraGroups() was called with only missing groups, causing removal from all existing Entra groups (full bidirectional sync behavior) - SOLUTION: Replaced with db.upsertGroupByExternalId() for each missing group followed by single bulkUpdateGroups() to add memberships (race-safe, idempotent) - BENEFIT: User memberships correctly maintained for mix of existing + new groups 2. **JSDoc @throws contradiction** - ISSUE: JSDoc declared function throws, but implementation catches all errors - SOLUTION: Removed @throws from JSDoc - function is best-effort - BENEFIT: Prevents unnecessary try/catch in caller code 3. **Missing test for group creation flow** - ISSUE: Auto-creating missing Entra groups had no test coverage - SOLUTION: Added regression test for mix of existing + new groups scenario - BENEFIT: Prevents future regressions on critical path ### SHOULD FIX (Important Improvements) - RESOLVED 4. **E11000 race condition handling** - SOLUTION: Upserts are idempotent and race-safe by design - BENEFIT: Concurrent logins no longer race each other 5. **Direct Mongoose access instead of db layer** - SOLUTION: Added findGroupsByExternalIds() helper to userGroup.ts - BENEFIT: Centralized data access, easier to add tenant scoping 6. **Serial DB round-trips on login path** - ISSUE: 40+ queries for user with 20 new groups - SOLUTION: Promise.all() for parallel upserts + single bulkUpdate - BENEFIT: ~10x performance improvement 7. **Graph API 429/503 throttling unhandled** - SOLUTION: Retry logic with exponential backoff (1s, 2s delays) - BENEFIT: Temporary API issues no longer cause permanent membership loss 8. **Sequential batch requests slow** - ISSUE: 200 groups = 10 batches × 200ms = ~2s sequential - SOLUTION: Promise.all() with concurrency limit (5 parallel batches) - BENEFIT: ~400ms total time ## Minor Fixes - Removed dead code check - PII removal: user._id instead of user.email in logs - ES6 shorthand fixes - Style consistency (blank lines) - Projection optimization ## Verification ✅ npm run build - success ✅ npm run test:api - 61/61 passing (+ new regression test) ✅ npm run lint - no errors ✅ All feedback from danny-avila resolved * docs: better JSDoc for the syncUserEntraGroupMemberships method --------- Co-authored-by: Airam Hernández Hernández <airam.hernandez@intelequia.com>	2026-04-13 08:50:52 -04:00
Denis Palnitsky	8ed0bcf5ca	♻️ fix: Reuse Existing MCP OAuth Client Registrations to Prevent client_id Mismatch (#11925) ... * fix: reuse existing OAuth client registrations to prevent client_id mismatch When using auto-discovered OAuth (DCR), LibreChat calls /register on every flow initiation, getting a new client_id each time. When concurrent connections or reconnections happen, the client_id used during /authorize differs from the one used during /token, causing the server to reject the exchange. Before registering a new client, check if a valid client registration already exists in the database and reuse it. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Handle re-registration of OAuth clients when redirect_uri changes * Add undefined fields for logo_uri and tos_uri in OAuth metadata tests * test: add client registration reuse tests for horizontal scaling race condition Reproduces the client_id mismatch bug that occurs in multi-replica deployments where concurrent initiateOAuthFlow calls each register a new OAuth client. Tests verify that the findToken-based client reuse prevents re-registration. * fix: address review findings for client registration reuse - Fix empty redirect_uris bug: invert condition so missing/empty redirect_uris triggers re-registration instead of silent reuse - Revert undocumented config?.redirect_uri in auto-discovery path - Change DB error logging from debug to warn for operator visibility - Fix import order: move package type import to correct section - Remove redundant type cast and misleading JSDoc comment - Test file: remove dead imports, restore process.env.DOMAIN_SERVER, rename describe blocks, add empty redirect_uris edge case test, add concurrent reconnection test with pre-seeded token, scope documentation to reconnection stabilization * fix: resolve type check errors for OAuthClientInformation redirect_uris The SDK's OAuthClientInformation type lacks redirect_uris (only on OAuthClientInformationFull). Cast to the local OAuthClientInformation type in handler.ts when accessing deserialized client info from DB, and use intersection types in tests for clientInfo with redirect_uris. * fix: address follow-up review findings R1, R2, R3 - R1: Move `import type { TokenMethods }` to the type-imports section, before local types, per CLAUDE.md import order rules - R2: Add unit test for empty redirect_uris in handler.test.ts to verify the inverted condition triggers re-registration - R3: Use delete for process.env.DOMAIN_SERVER restoration when the original value was undefined to avoid coercion to string "undefined" * fix: clear stale client registration on OAuth flow failure When a stored client_id is no longer recognized by the OAuth server, the flow fails but the stale client stays in MongoDB, causing every retry to reuse the same invalid registration in an infinite loop. On OAuth failure, clear the stored client registration so the next attempt falls through to fresh Dynamic Client Registration. - Add MCPTokenStorage.deleteClientRegistration() for targeted cleanup - Call it from MCPConnectionFactory's OAuth failure path - Add integration test proving recovery from stale client reuse * fix: validate auth server identity and target cleanup to reused clients - Gate client reuse on authorization server identity: compare stored issuer against freshly discovered metadata before reusing, preventing wrong-client reuse when the MCP server switches auth providers - Add reusedStoredClient flag to MCPOAuthFlowMetadata so cleanup only runs when the failed flow actually reused a stored registration, not on unrelated failures (timeouts, user-denied consent, etc.) - Add cleanup in returnOnOAuth path: when a prior flow that reused a stored client is detected as failed, clear the stale registration before re-initiating - Add tests for issuer mismatch and reusedStoredClient flag assertions * fix: address minor review findings N3, N5, N6 - N3: Type deleteClientRegistration param as TokenMethods['deleteTokens'] instead of Promise<unknown> - N5: Elevate deletion failure logging from debug to warn for operator visibility when stale client cleanup fails - N6: Use getLogPrefix() instead of hardcoded log prefix to respect system-user privacy convention * fix: correct stale-client cleanup in both OAuth paths - Blocking path: remove result?.clientInfo guard that made cleanup unreachable (handleOAuthRequired returns null on failure, so result?.clientInfo was always false in the failure branch) - returnOnOAuth path: only clear stored client when the prior flow status is FAILED, not on COMPLETED or PENDING flows, to avoid deleting valid registrations during normal flow replacement * fix: remove redundant cast on clientMetadata clientMetadata is already typed as Record<string, unknown>; the as Record<string, unknown> cast was a no-op. * fix: thread reusedStoredClient through return type instead of re-reading flow state FlowStateManager.createFlow() deletes FAILED flow state before rejecting, so getFlowState() after handleOAuthRequired() returns null would find nothing — making the stale-client cleanup dead code. Fix: hoist reusedStoredClient flag from flowMetadata into a local variable, include it in handleOAuthRequired()'s return type (both success and catch paths), and use result.reusedStoredClient directly in the caller instead of a second getFlowState() round-trip. * fix: selective stale-client cleanup in returnOnOAuth path The returnOnOAuth cleanup was unreliable: it depended on reading FAILED flow state, but FlowStateManager.monitorFlow() deletes FAILED state before rejecting. Move cleanup into createFlow's catch handler where flowMetadata.reusedStoredClient is still in scope. Make cleanup selective in both paths: add isClientRejection() helper that only matches errors indicating the OAuth server rejected the client_id (invalid_client, unauthorized_client, client not found). Timeouts, user-cancelled flows, and other transient failures no longer wipe valid stored registrations. Thread the error from handleOAuthRequired() through the return type so the blocking path can also check isClientRejection(). * fix: tighten isClientRejection heuristic Narrow 'client_id' match to 'client_id mismatch' to avoid false-positive cleanup on unrelated errors that happen to mention client_id. * test: add isClientRejection tests and enforced client_id on test server - Add isClientRejection unit tests: invalid_client, unauthorized_client, client_id mismatch, client not found, unknown client, and negative cases (timeout, flow state not found, user denied, null, undefined) - Enhance OAuth test server with enforceClientId option: binds auth codes to the client_id that initiated /authorize, rejects token exchange with mismatched or unregistered client_id (401 invalid_client) - Add integration tests proving the test server correctly rejects stale client_ids and accepts matching ones at /token * fix: issuer validation, callback error propagation, and cleanup DRY - Issuer check: re-register when storedIssuer is absent or non-string instead of silently reusing. Narrows unknown type with typeof guard and inverts condition so missing issuer → fresh DCR (safer default). - OAuth callback route: call failFlow with the OAuth error when the authorization server redirects back with error= parameter, so the waiting flow receives the actual rejection instead of timing out. This lets isClientRejection match stale-client errors correctly. - Extract duplicated cleanup block to clearStaleClientIfRejected() private method, called from both returnOnOAuth and blocking paths. - Test fixes: add issuer to stored metadata in reuse tests, reset server to undefined in afterEach to prevent double-close. * fix: gate failFlow behind callback validation, propagate reusedStoredClient on join - OAuth callback: move failFlow call to after CSRF/session/active-flow validation so an attacker with only a leaked state parameter cannot force-fail a flow without passing the same integrity checks required for legitimate callbacks - PENDING join path: propagate reusedStoredClient from flow metadata into the return object so joiners can trigger stale-client cleanup if the joined flow later fails with a client rejection * fix: restore early oauthError/code redirects, gate only failFlow behind CSRF The previous restructuring moved oauthError and missing-code checks behind CSRF validation, breaking tests that expect those redirects without cookies. The redirect itself is harmless (just shows an error page). Only the failFlow call needs CSRF gating to prevent DoS. Restructure: oauthError check stays early (redirects immediately), but failFlow inside it runs the full CSRF/session/active-flow validation before marking the flow as FAILED. * fix: require deleteTokens for client reuse, add missing import in MCP.js Client registration reuse without cleanup capability creates a permanent failure loop: if the reused client is stale, the code detects the rejection but cannot clear the stored registration because deleteTokens is missing, so every retry reuses the same broken client_id. - MCPConnectionFactory: only pass findToken to initiateOAuthFlow when deleteTokens is also available, ensuring reuse is only enabled when recovery is possible - api/server/services/MCP.js: add deleteTokens to the tokenMethods object (was the only MCP call site missing it) * fix: set reusedStoredClient before createFlow in joined-flow path When joining a PENDING flow, reusedStoredClient was only set on the success return but not before the await. If createFlow throws (e.g. invalid_client during token exchange), the outer catch returns the local variable which was still false, skipping stale-client cleanup. * fix: require browser binding (CSRF/session) for failFlow on OAuth error hasActiveFlow only proves a PENDING flow exists, not that the caller is the same browser that initiated it. An attacker with a leaked state could force-fail the flow without any user binding. Require hasCsrf or hasSession before calling failFlow on the oauthError path. * fix: guard findToken with deleteTokens check in blocking OAuth path Match the returnOnOAuth path's defense-in-depth: only enable client registration reuse when deleteTokens is also available, ensuring cleanup is possible if the reused client turns out to be stale. * fix: address review findings — tests, types, normalization, docs - Add deleteTokens method to InMemoryTokenStore matching TokenMethods contract; update test call site from deleteToken to deleteTokens - Add MCPConnectionFactory test: returnOnOAuth flow fails with invalid_client → clearStaleClientIfRejected invoked automatically - Add mcp.spec.js tests: OAuth error with CSRF → failFlow called; OAuth error without cookies → failFlow NOT called (DoS prevention) - Add JSDoc to isClientRejection with RFC 6749 and vendor attribution - Add inline comment explaining findToken/deleteTokens coupling guard - Normalize issuer comparison: strip trailing slashes to prevent spurious re-registrations from URL formatting differences - Fix dead-code: use local reusedStoredClient variable in PENDING join return instead of re-reading flowMeta * fix: address final review nits N1-N4 - N1: Add session cookie failFlow test — validates the hasSession branch triggers failFlow on OAuth error callback - N2: Replace setTimeout(50) with setImmediate for microtask drain - N3: Add 'unknown client' attribution to isClientRejection JSDoc - N4: Remove dead getFlowState mock from failFlow tests --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Danny Avila <danny@librechat.ai>	2026-04-03 22:15:08 -04:00
Danny Avila	275af48592	🎯 fix: MCP Tool Misclassification from Action Delimiter Collision (#12512) ... * fix: prevent MCP tools with `_action` in name from being misclassified as OpenAPI action tools Add `isActionTool()` helper that checks for the `_action_` delimiter while guarding against cross-delimiter collision with `_mcp_`. Replace all `includes(actionDelimiter)` classification checks with the new helper across backend and frontend. * test: add coverage for MCP/action cross-delimiter collision Verify that `isActionTool` correctly rejects MCP tool names containing `_action` and that `loadAgentTools` does not filter them based on `actionsEnabled`. Add ToolIcon and definitions test cases. * fix: simplify isActionTool to handle all MCP name patterns - Use `!toolName.includes('_mcp_')` instead of checking only after the first `_action_` occurrence, which missed MCP tools with `_action_` in the middle of their name (e.g. `get_action_data_mcp_myserver`). - Reference `Constants.mcp_delimiter` value via a local const to avoid circular import from config.ts, with a comment explaining why. - Remove dead `actionDelimiter` import from definitions.ts. - Replace double-filter with single-pass partition in loadToolsForExecution. - Add test for mid-name `_action_` collision case. * fix: narrow MCP exclusion to delimiter position in isActionTool Only reject when `_mcp_` appears after `_action_` (the MCP suffix position). `_mcp_` before `_action_` is part of the operationId and is valid — e.g. `sync_mcp_state_action_api---example---com` is a legitimate action tool whose operationId happens to contain `_mcp_`. * fix: document positional _mcp_ guard and known RFC-invalid domain limitation Expand JSDoc on isActionTool to explain the action/MCP format disambiguation and the theoretical false negative for non-RFC-compliant domains containing `_mcp_`. Add test documenting this known edge case.	2026-04-01 22:36:21 -04:00
Danny Avila	fda72ac621	🏗️ refactor: Remove Redundant Caching, Migrate Config Services to TypeScript (#12466) ... * ♻️ refactor: Remove redundant scopedCacheKey caching, support user-provided key model fetching Remove redundant cache layers that used `scopedCacheKey()` (tenant-only scoping) on top of `getAppConfig()` which already caches per-principal (role+user+tenant). This caused config overrides for different principals within the same tenant to be invisible due to stale cached data. Changes: - Add `requireJwtAuth` to `/api/endpoints` route for proper user context - Remove ENDPOINT_CONFIG, STARTUP_CONFIG, PLUGINS, TOOLS, and MODELS_CONFIG cache layers — all derive from `getAppConfig()` with cheap computation - Enhance MODEL_QUERIES cache: hash(baseURL+apiKey) keys, 2-minute TTL, caching centralized in `fetchModels()` base function - Support fetching models with user-provided API keys in `loadConfigModels` via `getUserKeyValues` lookup (no caching for user keys) - Update all affected tests Closes #1028 * ♻️ refactor: Migrate config services to TypeScript in packages/api Move core config logic from CJS /api wrappers to typed TypeScript in packages/api using dependency injection factories: - `createEndpointsConfigService` — endpoint config merging + checkCapability - `createLoadConfigModels` — custom endpoint model loading with user key support - `createMCPToolCacheService` — MCP tool cache operations (update, merge, cache) /api files become thin wrappers that wire dependencies (getAppConfig, loadDefaultEndpointsConfig, getUserKeyValues, getCachedTools, etc.) into the typed factories. Also moves existing `endpoints/config.ts` → `endpoints/config/providers.ts` to accommodate the new `config/` directory structure. * 🔄 fix: Invalidate models query when user API key is set or revoked Without this, users had to refresh the page after entering their API key to see the updated model list fetched with their credentials. - Invalidate QueryKeys.models in useUpdateUserKeysMutation onSuccess - Invalidate QueryKeys.models in useRevokeUserKeyMutation onSuccess - Invalidate QueryKeys.models in useRevokeAllUserKeysMutation onSuccess * 🗺️ fix: Remap YAML-level override keys to AppConfig equivalents in mergeConfigOverrides Config overrides stored in the DB use YAML-level keys (TCustomConfig), but they're merged into the already-processed AppConfig where some fields have been renamed by AppService. This caused mcpServers overrides to land on a nonexistent key instead of mcpConfig, so config-override MCP servers never appeared in the UI. - Add OVERRIDE_KEY_MAP to remap mcpServers→mcpConfig, interface→interfaceConfig - Apply remapping before deep merge in mergeConfigOverrides - Add test for YAML-level key remapping behavior - Update existing tests to use AppConfig field names in assertions * 🧪 test: Update service.spec to use AppConfig field names after override key remapping * 🛡️ fix: Address code review findings — reliability, types, tests, and performance - Pass tenant context (getTenantId) in importers.js getEndpointsConfig call - Add 5 tests for user-provided API key model fetching (key found, no key, DB error, missing userId, apiKey-only with fixed baseURL) - Distinguish NO_USER_KEY (debug) from infrastructure errors (warn) in catch - Switch fetchPromisesMap from Promise.all to Promise.allSettled so one failing provider doesn't kill the entire model config - Parallelize getUserKeyValues DB lookups via batched Promise.allSettled instead of sequential awaits in the loop - Hoist standardCache instance in fetchModels to avoid double instantiation - Replace Record<string, unknown> types with Partial<TConfig>-based types; remove as unknown as T double-cast in endpoints config - Narrow Bedrock availableRegions to typed destructure - Narrow version field from string|number|undefined to string|undefined - Fix import ordering in mcp/tools.ts and config/models.ts per AGENTS.md - Add JSDoc to getModelsConfig alias clarifying caching semantics * fix: Guard against null getCachedTools in mergeAppTools * 🔍 fix: Address follow-up review — deduplicate extractEnvVariable, fix error discrimination, add log-level tests - Deduplicate extractEnvVariable calls: resolve apiKey/baseURL once, reuse for both the entry and isUserProvided checks (Finding A) - Move ResolvedEndpoint interface from function closure to module scope (Finding B) - Replace fragile msg.includes('NO_USER_KEY') with ErrorTypes.NO_USER_KEY enum check against actual error message format (Finding C). Also handle ErrorTypes.INVALID_USER_KEY as an expected "no key" case. - Add test asserting logger.warn is called for infra errors (not debug) - Add test asserting logger.debug is called for NO_USER_KEY errors (not warn) * fix: Preserve numeric assistants version via String() coercion * 🐛 fix: Address secondary review — Ollama cache bypass, cache tests, type safety - Fix Ollama success path bypassing cache write in fetchModels (CRITICAL): store result before returning so Ollama models benefit from 2-minute TTL - Add 4 fetchModels cache behavior tests: cache write with TTL, cache hit short-circuits HTTP, skipCache bypasses read+write, empty results not cached - Type-safe OVERRIDE_KEY_MAP: Partial<Record<keyof TCustomConfig, keyof AppConfig>> so compiler catches future field rename mismatches - Fix import ordering in config/models.ts (package types longest→shortest) - Rename ToolCacheDeps → MCPToolCacheDeps for naming consistency - Expand getModelsConfig JSDoc to explain caching granularity * fix: Narrow OVERRIDE_KEY_MAP index to satisfy strict tsconfig * 🧩 fix: Add allowedProviders to TConfig, remove Record<string, unknown> from PartialEndpointEntry The agents endpoint config includes allowedProviders (used by the frontend AgentPanel to filter available providers), but it was missing from TConfig. This forced PartialEndpointEntry to use & Record<string, unknown> as an escape hatch, violating AGENTS.md type policy. - Add allowedProviders?: (string | EModelEndpoint)[] to TConfig - Remove Record<string, unknown> from PartialEndpointEntry — now just Partial<TConfig> * 🛡️ fix: Isolate Ollama cache write from fetch try-catch, add Ollama cache tests - Separate Ollama fetch and cache write into distinct scopes so a cache failure (e.g., Redis down) doesn't misattribute the error as an Ollama API failure and fall through to the OpenAI-compatible path (Issue A) - Add 2 Ollama-specific cache tests: models written with TTL on fetch, cached models returned without hitting server (Issue B) - Replace hardcoded 120000 with Time.TWO_MINUTES constant in cache TTL test assertion (Issue C) - Fix OVERRIDE_KEY_MAP JSDoc to accurately describe runtime vs compile-time type enforcement (Issue D) - Add global beforeEach for cache mock reset to prevent cross-test leakage * 🧪 fix: Address third review — DI consistency, cache key width, MCP tests - Inject loadCustomEndpointsConfig via EndpointsConfigDeps with default fallback, matching loadDefaultEndpointsConfig DI pattern (Finding 3) - Widen modelsCacheKey from 64-bit (.slice(0,16)) to 128-bit (.slice(0,32)) for collision-sensitive cross-credential cache key (Finding 4) - Add fetchModels.mockReset() in loadConfigModels.spec beforeEach to prevent mock implementation leaks across tests (Finding 5) - Add 11 unit tests for createMCPToolCacheService covering all three functions: null/empty input, successful ops, error propagation, cold-cache merge (Finding 2) - Simplify getModelsConfig JSDoc to @see reference (Finding 10) * ♻️ refactor: Address remaining follow-ups from reviews OVERRIDE_KEY_MAP completeness: - Add missing turnstile→turnstileConfig mapping - Add exhaustiveness test verifying all three renamed keys are remapped and original YAML keys don't leak through Import role context: - Pass userRole through importConversations job → importLibreChatConvo so role-based endpoint overrides are honored during conversation import - Update convos.js route to include req.user.role in the job payload createEndpointsConfigService unit tests: - Add 8 tests covering: default+custom merge, Azure/AzureAssistants/ Anthropic Vertex/Bedrock config enrichment, assistants version coercion, agents allowedProviders, req.config bypass Plugins/tools efficiency: - Use Set for includedTools/filteredTools lookups (O(1) vs O(n) per plugin) - Combine auth check + filter into single pass (eliminates intermediate array) - Pre-compute toolDefKeys Set for O(1) tool definition lookups * fix: Scope model query cache by user when userIdQuery is enabled * fix: Skip model cache for userIdQuery endpoints, fix endpoints test types - When userIdQuery is true, skip caching entirely (like user_provided keys) to avoid cross-user model list leakage without duplicating cache data - Fix AgentCapabilities type error in endpoints.spec.ts — use enum values and appConfig() helper for partial mock typing * 🐛 fix: Restore filteredTools+includedTools composition, add checkCapability tests - Fix filteredTools regression: whitelist and blacklist are now applied independently (two flat guards), matching original behavior where includedTools=['a','b'] + filteredTools=['b'] produces ['a'] (Finding A) - Fix Set spread in toolkit loop: pre-compute toolDefKeysList array once alongside the Set, reuse for .some() without per-plugin allocation (Finding B) - Add 2 filteredTools tests: blacklist-only path and combined whitelist+blacklist composition (Finding C) - Add 3 checkCapability tests: capability present, capability absent, fallback to defaultAgentCapabilities for non-agents endpoints (Finding D) * 🔑 fix: Include config-override MCP servers in filterAuthorizedTools Config-override MCP servers (defined via admin config overrides for roles/groups) were rejected by filterAuthorizedTools because it called getAllServerConfigs(userId) without the configServers parameter. Only YAML and DB-backed user servers were included in the access check. - Add configServers parameter to filterAuthorizedTools - Resolve config servers via resolveConfigServers(req) at all 4 callsites (create, update, duplicate, revert) using parallel Promise.all - Pass configServers through to getAllServerConfigs(userId, configServers) so the registry merges config-source servers into the access check - Update filterAuthorizedTools.spec.js mock for resolveConfigServers * fix: Skip model cache for userIdQuery endpoints, fix endpoints test types For user-provided key endpoints (userProvide: true), skip the full model list re-fetch during message validation — the user already selected from a list we served them, and re-fetching with skipCache:true on every message send is both slow and fragile (5s provider timeout = rejected model). Instead, validate the model string format only: - Must be a string, max 256 chars - Must match [a-zA-Z0-9][a-zA-Z0-9_.:\-/@+ ]* (covers all known provider model ID formats while rejecting injection attempts) System-configured endpoints still get full model list validation as before. * 🧪 test: Add regression tests for filterAuthorizedTools configServers and validateModel filterAuthorizedTools: - Add test verifying configServers is passed to getAllServerConfigs and config-override server tools are allowed through - Guard resolveConfigServers in createAgentHandler to only run when MCP tools are present (skip for tool-free agent creates) validateModel (12 new tests): - Format validation: missing model, non-string, length overflow, leading special char, script injection, standard model ID acceptance - userProvide early-return: next() called immediately, getModelsConfig not invoked (regression guard for the exact bug this fixes) - System endpoint list validation: reject unknown model, accept known model, handle null/missing models config Also fix unnecessary backslash escape in MODEL_PATTERN regex. * 🧹 fix: Remove space from MODEL_PATTERN, trim input, clean up nits - Remove space character from MODEL_PATTERN regex — no real model ID uses spaces; prevents spurious violation logs from whitespace artifacts - Add model.trim() before validation to handle accidental whitespace - Remove redundant filterUniquePlugins call on already-deduplicated output - Add comment documenting intentional whitelist+blacklist composition - Add getUserKeyValues.mockReset() in loadConfigModels.spec beforeEach - Remove narrating JSDoc from getModelsConfig one-liner - Add 2 tests: trim whitespace handling, reject spaces in model ID * fix: Match startup tool loader semantics — includedTools takes precedence over filteredTools The startup tool loader (loadAndFormatTools) explicitly ignores filteredTools when includedTools is set, with a warning log. The PluginController was applying both independently, creating inconsistent behavior where the same config produced different results at startup vs plugin listing time. Restored mutually exclusive semantics: when includedTools is non-empty, filteredTools is not evaluated. * 🧹 chore: Simplify validateModel flow, note auth requirement on endpoints route - Separate missing-model from invalid-model checks cleanly: type+presence guard first, then trim+format guard (reviewer NIT) - Add route comment noting auth is required for role/tenant scoping * fix: Write trimmed model back to req.body.model for downstream consumers	2026-03-30 16:49:48 -04:00
Danny Avila	877c2efc85	🏗️ feat: bulkWrite isolation, pre-auth context, strict-mode fixes (#12445) ... * fix: wrap seedDatabase() in runAsSystem() for strict tenant mode seedDatabase() was called without tenant context at startup, causing every Mongoose operation inside it to throw when TENANT_ISOLATION_STRICT=true. Wrapping in runAsSystem() gives it the SYSTEM_TENANT_ID sentinel so the isolation plugin skips filtering, matching the pattern already used for performStartupChecks and updateInterfacePermissions. * fix: chain tenantContextMiddleware in optionalJwtAuth optionalJwtAuth populated req.user but never established ALS tenant context, unlike requireJwtAuth which chains tenantContextMiddleware after successful auth. Authenticated users hitting routes with optionalJwtAuth (e.g. /api/banner) had no tenant isolation. * feat: tenant-safe bulkWrite wrapper and call-site migration Mongoose's bulkWrite() does not trigger schema-level middleware hooks, so the applyTenantIsolation plugin cannot intercept it. This adds a tenantSafeBulkWrite() utility that injects the current ALS tenant context into every operation's filter/document before delegating to native bulkWrite. Migrates all 8 runtime bulkWrite call sites: - agentCategory (seedCategories, ensureDefaultCategories) - conversation (bulkSaveConvos) - message (bulkSaveMessages) - file (batchUpdateFiles) - conversationTag (updateTagsForConversation, bulkIncrementTagCounts) - aclEntry (bulkWriteAclEntries) systemGrant.seedSystemGrants is intentionally not migrated — it uses explicit tenantId: { $exists: false } filters and is exempt from the isolation plugin. * feat: pre-auth tenant middleware and tenant-scoped config cache Adds preAuthTenantMiddleware that reads X-Tenant-Id from the request header and wraps downstream in tenantStorage ALS context. Wired onto /oauth, /api/auth, /api/config, and /api/share — unauthenticated routes that need tenant scoping before JWT auth runs. The /api/config cache key is now tenant-scoped (STARTUP_CONFIG:${tenantId}) so multi-tenant deployments serve the correct login page config per tenant. The middleware is intentionally minimal — no subdomain parsing, no OIDC claim extraction. The private fork's reverse proxy or auth gateway sets the header. * feat: accept optional tenantId in updateInterfacePermissions When tenantId is provided, the function re-enters inside tenantStorage.run({ tenantId }) so all downstream Mongoose queries target that tenant's roles instead of the system context. This lets the private fork's tenant provisioning flow call updateInterfacePermissions per-tenant after creating tenant-scoped ADMIN/USER roles. * fix: tenant-filter $lookup in getPromptGroup aggregation The $lookup stage in getPromptGroup() queried the prompts collection without tenant filtering. While the outer PromptGroup aggregate is protected by the tenantIsolation plugin's pre('aggregate') hook, $lookup runs as an internal MongoDB operation that bypasses Mongoose hooks entirely. Converts from simple field-based $lookup to pipeline-based $lookup with an explicit tenantId match when tenant context is active. * fix: replace field-level unique indexes with tenant-scoped compounds Field-level unique:true creates a globally-unique single-field index in MongoDB, which would cause insert failures across tenants sharing the same ID values. - agent.id: removed field-level unique, added { id, tenantId } compound - convo.conversationId: removed field-level unique (compound at line 50 already exists: { conversationId, user, tenantId }) - message.messageId: removed field-level unique (compound at line 165 already exists: { messageId, user, tenantId }) - preset.presetId: removed field-level unique, added { presetId, tenantId } compound * fix: scope MODELS_CONFIG, ENDPOINT_CONFIG, PLUGINS, TOOLS caches by tenant These caches store per-tenant configuration (available models, endpoint settings, plugin availability, tool definitions) but were using global cache keys. In multi-tenant mode, one tenant's cached config would be served to all tenants. Appends :${tenantId} to cache keys when tenant context is active. Falls back to the unscoped key when no tenant context exists (backward compatible for single-tenant OSS deployments). Covers all read, write, and delete sites: - ModelController.js: get/set MODELS_CONFIG - PluginController.js: get/set PLUGINS, get/set TOOLS - getEndpointsConfig.js: get/set/delete ENDPOINT_CONFIG - app.js: delete ENDPOINT_CONFIG (clearEndpointConfigCache) - mcp.js: delete TOOLS (updateMCPTools, mergeAppTools) - importers.js: get ENDPOINT_CONFIG * fix: add getTenantId to PluginController spec mock The data-schemas mock was missing getTenantId, causing all PluginController tests to throw when the controller calls getTenantId() for tenant-scoped cache keys. * fix: address review findings — migration, strict-mode, DRY, types Addresses all CRITICAL, MAJOR, and MINOR review findings: F1 (CRITICAL): Add agents, conversations, messages, presets to SUPERSEDED_INDEXES in tenantIndexes.ts so dropSupersededTenantIndexes() drops the old single-field unique indexes that block multi-tenant inserts. F2 (CRITICAL): Unknown bulkWrite op types now throw in strict mode instead of silently passing through without tenant injection. F3 (MAJOR): Replace wildcard export with named export for tenantSafeBulkWrite, hiding _resetBulkWriteStrictCache from the public package API. F5 (MAJOR): Restore AnyBulkWriteOperation<IAclEntry>[] typing on bulkWriteAclEntries — the unparameterized wrapper accepts parameterized ops as a subtype. F7 (MAJOR): Fix config.js tenant precedence — JWT-derived req.user.tenantId now takes priority over the X-Tenant-Id header for authenticated requests. F8 (MINOR): Extract scopedCacheKey() helper into tenantContext.ts and replace all 11 inline occurrences across 7 files. F9 (MINOR): Use simple localField/foreignField $lookup for the non-tenant getPromptGroup path (more efficient index seeks). F12 (NIT): Remove redundant BulkOp type alias. F13 (NIT): Remove debug log that leaked raw tenantId. * fix: add new superseded indexes to tenantIndexes test fixture The test creates old indexes to verify the migration drops them. Missing fixture entries for agents.id_1, conversations.conversationId_1, messages.messageId_1, and presets.presetId_1 caused the count assertion to fail (expected 22, got 18). * fix: restore logger.warn for unknown bulk op types in non-strict mode * fix: block SYSTEM_TENANT_ID sentinel from external header input CRITICAL: preAuthTenantMiddleware accepted any string as X-Tenant-Id, including '__SYSTEM__'. The tenantIsolation plugin treats SYSTEM_TENANT_ID as an explicit bypass — skipping ALL query filters. A client sending X-Tenant-Id: __SYSTEM__ to pre-auth routes (/api/share, /api/config, /api/auth, /oauth) would execute Mongoose operations without tenant isolation. Fixes: - preAuthTenantMiddleware rejects SYSTEM_TENANT_ID in header - scopedCacheKey returns the base key (not key:__SYSTEM__) in system context, preventing stale cache entries during runAsSystem() - updateInterfacePermissions guards tenantId against SYSTEM_TENANT_ID - $lookup pipeline separates $expr join from constant tenantId match for better index utilization - Regression test for sentinel rejection in preAuthTenant.spec.ts - Remove redundant getTenantId() call in config.js * test: add missing deleteMany/replaceOne coverage, fix vacuous ALS assertions bulkWrite spec: - deleteMany: verifies tenant-scoped deletion leaves other tenants untouched - replaceOne: verifies tenantId injected into both filter and replacement - replaceOne overwrite: verifies a conflicting tenantId in the replacement document is overwritten by the ALS tenant (defense-in-depth) - empty ops array: verifies graceful handling preAuthTenant spec: - All negative-case tests now use the capturedNext pattern to verify getTenantId() inside the middleware's execution context, not the test runner's outer frame (which was always undefined regardless) * feat: tenant-isolate MESSAGES cache, FLOWS cache, and GenerationJobManager MESSAGES cache (streamAudio.js): - Cache key now uses scopedCacheKey(messageId) to prefix with tenantId, preventing cross-tenant message content reads during TTS streaming. FLOWS cache (FlowStateManager): - getFlowKey() now generates ${type}:${tenantId}:${flowId} when tenant context is active, isolating OAuth flow state per tenant. GenerationJobManager: - tenantId added to SerializableJobData and GenerationJobMetadata - createJob() captures the current ALS tenant context (excluding SYSTEM_TENANT_ID) and stores it in job metadata - SSE subscription endpoint validates job.metadata.tenantId matches req.user.tenantId, blocking cross-tenant stream access - Both InMemoryJobStore and RedisJobStore updated to accept tenantId * fix: add getTenantId and SYSTEM_TENANT_ID to MCP OAuth test mocks FlowStateManager.getFlowKey() now calls getTenantId() for tenant-scoped flow keys. The 4 MCP OAuth test files mock @librechat/data-schemas without these exports, causing TypeError at runtime. * fix: correct import ordering per AGENTS.md conventions Package imports sorted shortest to longest line length, local imports sorted longest to shortest — fixes ordering violations introduced by our new imports across 8 files. * fix: deserialize tenantId in RedisJobStore — cross-tenant SSE guard was no-op in Redis mode serializeJob() writes tenantId to the Redis hash via Object.entries, but deserializeJob() manually enumerates fields and omitted tenantId. Every getJob() from Redis returned tenantId: undefined, causing the SSE route's cross-tenant guard to short-circuit (undefined && ... → false). * test: SSE tenant guard, FlowStateManager key consistency, ALS scope docs SSE stream tenant tests (streamTenant.spec.js): - Cross-tenant user accessing another tenant's stream → 403 - Same-tenant user accessing own stream → allowed - OSS mode (no tenantId on job) → tenant check skipped FlowStateManager tenant tests (manager.tenant.spec.ts): - completeFlow finds flow created under same tenant context - completeFlow does NOT find flow under different tenant context - Unscoped flows are separate from tenant-scoped flows Documentation: - JSDoc on getFlowKey documenting ALS context consistency requirement - Comment on streamAudio.js scopedCacheKey capture site * fix: SSE stream tests hang on success path, remove internal fork references The success-path tests entered the SSE streaming code which never closes, causing timeout. Mock subscribe() to end the response immediately. Restructured assertions to verify non-403/non-404. Removed "private fork" and "OSS" references from code and test descriptions — replaced with "deployment layer", "multi-tenant deployments", and "single-tenant mode". * fix: address review findings — test rigor, tenant ID validation, docs F1: SSE stream tests now mock subscribe() with correct signature (streamId, writeEvent, onDone, onError) and assert 200 status, verifying the tenant guard actually allows through same-tenant users. F2: completeFlow logs the attempted key and ALS tenantId when flow is not found, so reverse proxy misconfiguration (missing X-Tenant-Id on OAuth callback) produces an actionable warning. F3/F10: preAuthTenantMiddleware validates tenant ID format — rejects colons, special characters, and values exceeding 128 chars. Trims whitespace. Prevents cache key collisions via crafted headers. F4: Documented cache invalidation scope limitation in clearEndpointConfigCache — only the calling tenant's key is cleared; other tenants expire via TTL. F7: getFlowKey JSDoc now lists all 8 methods requiring consistent ALS context. F8: Added dedicated scopedCacheKey unit tests — base key without context, base key in system context, scoped key with tenant, no ALS leakage across scope boundaries. * fix: revert flow key tenant scoping, fix SSE test timing FlowStateManager: Reverts tenant-scoped flow keys. OAuth callbacks arrive without tenant ALS context (provider redirects don't carry X-Tenant-Id), so completeFlow/failFlow would never find flows created under tenant context. Flow IDs are random UUIDs with no collision risk, and flow data is ephemeral (TTL-bounded). SSE tests: Use process.nextTick for onDone callback so Express response headers are flushed before res.write/res.end are called. * fix: restore getTenantId import for completeFlow diagnostic log * fix: correct completeFlow warning message, add missing flow test The warning referenced X-Tenant-Id header consistency which was only relevant when flow keys were tenant-scoped (since reverted). Updated to list actual causes: TTL expiry, missing flow, or routing to a different instance without shared Keyv storage. Removed the getTenantId() call and import — no longer needed since flow keys are unscoped. Added test for the !flowState branch in completeFlow — verifies return false and logger.warn on nonexistent flow ID. * fix: add explicit return type to recursive updateInterfacePermissions The recursive call (tenantId branch calls itself without tenantId) causes TypeScript to infer circular return type 'any'. Adding explicit Promise<void> satisfies the rollup typescript plugin. * fix: update MCPOAuthRaceCondition test to match new completeFlow warning * fix: clearEndpointConfigCache deletes both scoped and unscoped keys Unauthenticated /api/endpoints requests populate the unscoped ENDPOINT_CONFIG key. Admin config mutations clear only the tenant-scoped key, leaving the unscoped entry stale indefinitely. Now deletes both when in tenant context. * fix: tenant guard on abort/status endpoints, warn logs, test coverage F1: Add tenant guard to /chat/status/:conversationId and /chat/abort matching the existing guard on /chat/stream/:streamId. The status endpoint exposes aggregatedContent (AI response text) which requires tenant-level access control. F2: preAuthTenantMiddleware now logs warn for rejected __SYSTEM__ sentinel and malformed tenant IDs, providing observability for bypass probing attempts. F3: Abort fallback path (getActiveJobIdsForUser) now has tenant check after resolving the job. F4: Test for strict mode + SYSTEM_TENANT_ID — verifies runAsSystem bypasses tenantSafeBulkWrite without throwing in strict mode. F5: Test for job with tenantId + user without tenantId → 403. F10: Regex uses idiomatic hyphen-at-start form. F11: Test descriptions changed from "rejects" to "ignores" since middleware calls next() (not 4xx). Also fixes MCPOAuthRaceCondition test assertion to match updated completeFlow warning message. * fix: test coverage for logger.warn, status/abort guards, consistency A: preAuthTenant spec now mocks logger and asserts warn calls for __SYSTEM__ sentinel, malformed characters, and oversized headers. B: streamTenant spec expanded with status and abort endpoint tests — cross-tenant status returns 403, same-tenant returns 200 with body, cross-tenant abort returns 403. C: Abort endpoint uses req.user.tenantId (not req.user?.tenantId) matching stream/status pattern — requireJwtAuth guarantees req.user. D: Malformed header warning now includes ip in log metadata, matching the sentinel warning for consistent SOC correlation. * fix: assert ip field in malformed header warn tests * fix: parallelize cache deletes, document tenant guard, fix import order - clearEndpointConfigCache uses Promise.all for independent cache deletes instead of sequential awaits - SSE stream tenant guard has inline comment explaining backward-compat behavior for untenanted legacy jobs - conversation.ts local imports reordered longest-to-shortest per AGENTS.md * fix: tenant-qualify userJobs keys, document tenant guard backward-compat Job store userJobs keys now include tenantId when available: - Redis: stream:user:{tenantId:userId}:jobs (falls back to stream:user:{userId}:jobs when no tenant) - InMemory: composite key tenantId:userId in userJobMap getActiveJobIdsByUser/getActiveJobIdsForUser accept optional tenantId parameter, threaded through from req.user.tenantId at all call sites (/chat/active and /chat/abort fallback). Added inline comments on all three SSE tenant guards explaining the backward-compat design: untenanted legacy jobs remain accessible when the userId check passes. * fix: parallelize cache deletes, document tenant guard, fix import order Fix InMemoryJobStore.getActiveJobIdsByUser empty-set cleanup to use the tenant-qualified userKey instead of bare userId — prevents orphaned empty Sets accumulating in userJobMap for multi-tenant users. Document cross-tenant staleness in clearEndpointConfigCache JSDoc — other tenants' scoped keys expire via TTL, not active invalidation. * fix: cleanup userJobMap leak, startup warning, DRY tenant guard, docs F1: InMemoryJobStore.cleanup() now removes entries from userJobMap before calling deleteJob, preventing orphaned empty Sets from accumulating with tenant-qualified composite keys. F2: Startup warning when TENANT_ISOLATION_STRICT is active — reminds operators to configure reverse proxy to control X-Tenant-Id header. F3: mergeAppTools JSDoc documents that tenant-scoped TOOLS keys are not actively invalidated (matching clearEndpointConfigCache pattern). F5: Abort handler getActiveJobIdsForUser call uses req.user.tenantId (not req.user?.tenantId) — consistent with stream/status handlers. F6: updateInterfacePermissions JSDoc clarifies SYSTEM_TENANT_ID behavior — falls through to caller's ALS context. F7: Extracted hasTenantMismatch() helper, replacing three identical inline tenant guard blocks across stream/status/abort endpoints. F9: scopedCacheKey JSDoc documents both passthrough cases (no context and SYSTEM_TENANT_ID context). * fix: clean userJobMap in evictOldest — same leak as cleanup()	2026-03-28 16:43:50 -04:00
Danny Avila	935288f841	🏗️ feat: 3-Tier MCP Server Architecture with Config-Source Lazy Init (#12435) ... * feat: add MCPServerSource type, tenantMcpPolicy schema, and source-based dbSourced wiring - Add `tenantMcpPolicy` to `mcpSettings` in YAML config schema with `enabled`, `maxServersPerTenant`, `allowedTransports`, and `allowedDomains` - Add `MCPServerSource` type ('yaml' | 'config' | 'user') and `source` field to `ParsedServerConfig` - Change `dbSourced` determination from `!!config.dbId` to `config.source === 'user'` across MCPManager, ConnectionsRepository, UserConnectionManager, and MCPServerInspector - Set `source: 'user'` on all DB-sourced servers in ServerConfigsDB * feat: three-layer MCPServersRegistry with config cache and lazy init - Add `configCacheRepo` as third repository layer between YAML cache and DB for admin-defined config-source MCP servers - Implement `ensureConfigServers()` that identifies config-override servers from resolved `getAppConfig()` mcpConfig, lazily inspects them, and caches parsed configs with `source: 'config'` - Add `lazyInitConfigServer()` with timeout, stub-on-failure, and concurrent-init deduplication via `pendingConfigInits` map - Extend `getAllServerConfigs()` with optional `configServers` param for three-way merge: YAML → Config → User - Add `getServerConfig()` lookup through config cache layer - Add `invalidateConfigCache()` for clearing config-source inspection results on admin config mutations - Tag `source: 'yaml'` on CACHE-stored servers and `source: 'user'` on DB-stored servers in `addServer()` and `addServerStub()` * feat: wire tenant context into MCP controllers, services, and cache invalidation - Resolve config-source servers via `getAppConfig({ role, tenantId })` in `getMCPTools()` and `getMCPServersList()` controllers - Pass `ensureConfigServers()` results through `getAllServerConfigs()` for three-way merge of YAML + Config + User servers - Add tenant/role context to `getMCPSetupData()` and connection status routes via `getTenantId()` from ALS - Add `clearMcpConfigCache()` to `invalidateConfigCaches()` so admin config mutations trigger re-inspection of config-source MCP servers * feat: enforce tenantMcpPolicy on admin config mcpServers mutations - Add `validateMcpServerPolicy()` helper that checks mcpServers against operator-defined `tenantMcpPolicy` (enabled, maxServersPerTenant, allowedTransports, allowedDomains) - Wire validation into `upsertConfigOverrides` and `patchConfigField` handlers — rejects with 403 when policy is violated - Infer transport type from config shape (command → stdio, url protocol → websocket/sse, type field → streamable-http) - Validate server domains against policy allowlist when configured * revert: remove tenantMcpPolicy schema and enforcement The existing admin config CRUD routes already provide the mechanism for granular MCP server prepopulation (groups, roles, users). The tenantMcpPolicy gating adds unnecessary complexity that can be revisited if needed in the future. - Remove tenantMcpPolicy from mcpSettings Zod schema - Remove validateMcpServerPolicy helper and TenantMcpPolicy interface - Remove policy enforcement from upsertConfigOverrides and patchConfigField handlers * test: update test assertions for source field and config-server wiring - Use objectContaining in MCPServersRegistry reset test to account for new source: 'yaml' field on CACHE-stored configs - Add getTenantId and ensureConfigServers mocks to MCP route tests - Add getAppConfig mock to route test Config service mock - Update getMCPSetupData assertion to expect second options argument - Update getAllServerConfigs assertions for new configServers parameter * fix: disconnect active connections when config-source servers are evicted When admin config overrides change and config-source MCP servers are removed, the invalidation now proactively disconnects active connections for evicted servers instead of leaving them lingering until timeout. - Return evicted server names from invalidateConfigCache() - Disconnect app-level connections for evicted servers in clearMcpConfigCache() via MCPManager.appConnections.disconnect() * fix: address code review findings (CRITICAL, MAJOR, MINOR) CRITICAL fixes: - Scope configCacheRepo keys by config content hash to prevent cross-tenant cache poisoning when two tenants define the same server name with different configurations - Change dbSourced checks from `source === 'user'` to `source !== 'yaml' && source !== 'config'` so undefined source (pre-upgrade cached configs) fails closed to restricted mode MAJOR fixes: - Derive OAuth servers from already-computed mcpConfig instead of calling getOAuthServers() separately — config-source OAuth servers are now properly detected - Add parseInt radix (10) and NaN guard with fallback to 30_000 for CONFIG_SERVER_INIT_TIMEOUT_MS - Add CONFIG_CACHE_NAMESPACE to aggregate-key branch in ServerConfigsCacheFactory to avoid SCAN-based Redis stalls - Remove `if (role || tenantId)` guard in getMCPSetupData — config servers now always resolve regardless of tenant context MINOR fixes: - Extract resolveAllMcpConfigs() helper in mcp controller to eliminate 3x copy-pasted config resolution boilerplate - Distinguish "not initialized" from real errors in clearMcpConfigCache — log actual failures instead of swallowing - Remove narrative inline comments per style guide - Remove dead try/catch inside Promise.allSettled in ensureConfigServers (inner method never throws) - Memoize YAML server names to avoid repeated cacheConfigsRepo.getAll() calls per request Test updates: - Add ensureConfigServers mock to registry test fixtures - Update getMCPSetupData assertions for inline OAuth derivation * fix: address code review findings (CRITICAL, MAJOR, MINOR) CRITICAL fixes: - Break circular dependency: move CONFIG_CACHE_NAMESPACE from MCPServersRegistry to ServerConfigsCacheFactory - Fix dbSourced fail-closed: use source field when present, fall back to legacy dbId check when absent (backward-compatible with pre-upgrade cached configs that lack source field) MAJOR fixes: - Add CONFIG_CACHE_NAMESPACE to aggregate-key set in ServerConfigsCacheFactory to avoid SCAN-based Redis stalls - Add comprehensive test suite (ensureConfigServers.test.ts, 18 tests) covering lazy init, stub-on-failure, cross-tenant isolation via config hash keys, concurrent deduplication, merge order, and cache invalidation MINOR fixes: - Update MCPServerInspector test assertion for dbSourced change * fix: restore getServerConfig lookup for config-source servers (NEW-1) Add configNameToKey map that indexes server name → hash-based cache key for O(1) lookup by name in getServerConfig. This restores the config cache layer that was dropped when hash-based keys were introduced. Without this fix, config-source servers appeared in tool listings (via getAllServerConfigs) but getServerConfig returned undefined, breaking all connection and tool call paths. - Populate configNameToKey in ensureSingleConfigServer - Clear configNameToKey in invalidateConfigCache and reset - Clear stale read-through cache entries after lazy init - Remove dead code in invalidateConfigCache (config.title, key parsing) - Add getServerConfig tests for config-source server lookup * fix: eliminate configNameToKey race via caller-provided configServers param Replace the process-global configNameToKey map (last-writer-wins under concurrent multi-tenant load) with a configServers parameter on getServerConfig. Callers pass the pre-resolved config servers map directly — no shared mutable state, no cross-tenant race. - Add optional configServers param to getServerConfig; when provided, returns matching config directly without any global lookup - Remove configNameToKey map entirely (was the source of the race) - Extract server names from cache keys via lastIndexOf in invalidateConfigCache (safe for names containing colons) - Use mcpConfig[serverName] directly in getMCPTools instead of a redundant getServerConfig call - Add cross-tenant isolation test for getServerConfig * fix: populate read-through cache after config server lazy init After lazyInitConfigServer succeeds, write the parsed config to readThroughCache keyed by serverName so that getServerConfig calls from ConnectionsRepository, UserConnectionManager, and MCPManager.callTool find the config without needing configServers. Without this, config-source servers appeared in tool listings but every connection attempt and tool call returned undefined. * fix: user-scoped getServerConfig fallback to server-only cache key When getServerConfig is called with a userId (e.g., from callTool or UserConnectionManager), the cache key is serverName::userId. Config-source servers are cached under the server-only key (no userId). Add a fallback so user-scoped lookups find config-source servers in the read-through cache. * fix: configCacheRepo fallback, isUserSourced DRY, cross-process race CRITICAL: Add findInConfigCache fallback in getServerConfig so config-source servers remain reachable after readThroughCache TTL expires (5s). Without this, every tool call after 5s returned undefined for config-source servers. MAJOR: Extract isUserSourced() helper to mcp/utils.ts and replace all 5 inline dbSourced ternary expressions (MCPManager x2, ConnectionsRepository, UserConnectionManager, MCPServerInspector). MAJOR: Fix cross-process Redis race in lazyInitConfigServer — when configCacheRepo.add throws (key exists from another process), fall back to reading the existing entry instead of returning undefined. MINOR: Parallelize invalidateConfigCache awaits with Promise.all. Remove redundant .catch(() => {}) inside Promise.allSettled. Tighten dedup test assertion to toBe(1). Add TTL-expiry tests for getServerConfig (with and without userId). * feat: thread configServers through getAppToolFunctions and formatInstructionsForContext Add optional configServers parameter to getAppToolFunctions, getInstructions, and formatInstructionsForContext so config-source server tools and instructions are visible to agent initialization and context injection paths. Existing callers (boot-time init, tests) pass no argument and continue to work unchanged. Agent runtime paths can now thread resolved config servers from request context. * fix: stale failure stubs retry after 5 min, upsert for cross-process races - Add CONFIG_STUB_RETRY_MS (5 min) — stale failure stubs are retried instead of permanently disabling config-source servers after transient errors (DNS outage, cold-start race) - Extract upsertConfigCache() helper that tries add then falls back to update, preventing cross-process Redis races where a second instance's successful inspection result was discarded - Add test for stale-stub retry after CONFIG_STUB_RETRY_MS * fix: stamp updatedAt on failure stubs, null-guard callTool config, test cleanup - Add updatedAt: Date.now() to failure stubs in lazyInitConfigServer so CONFIG_STUB_RETRY_MS (5 min) window works correctly — without it, stubs were always considered stale (updatedAt ?? 0 → epoch → always expired) - Add null guard for rawConfig in MCPManager.callTool before passing to preProcessGraphTokens — prevents unsafe `as` cast on undefined - Log double-failure in upsertConfigCache instead of silently swallowing - Replace module-scope Date.now monkey-patch with jest.useFakeTimers / jest.setSystemTime / jest.useRealTimers in ensureConfigServers tests * fix: server-only readThrough fallback only returns truthy values Prevents a cached undefined from a prior no-userId lookup from short-circuiting the DB query on a subsequent userId-scoped lookup. * fix: remove findInConfigCache to eliminate cross-tenant config leakage The findInConfigCache prefix scan (serverName:*) could return any tenant's config after readThrough TTL expires, violating tenant isolation. Config-source servers are now ONLY resolvable through: 1. The configServers param (callers with tenant context from ALS) 2. The readThrough cache (populated by ensureSingleConfigServer, 5s TTL, repopulated on every HTTP request via resolveAllMcpConfigs) Connection/tool-call paths without tenant context rely exclusively on the readThrough cache. If it expires before the next HTTP request repopulates it, the server is not found — which is correct because there is no tenant context to determine which config to return. - Remove findInConfigCache method and its call in getServerConfig - Update server-only readThrough fallback to only return truthy values (prevents cached undefined from short-circuiting user-scoped DB lookup) - Update tests to document tenant isolation behavior after cache expiry * style: fix import order per AGENTS.md conventions Sort package imports shortest-to-longest, local imports longest-to-shortest across MCPServersRegistry, ConnectionsRepository, MCPManager, UserConnectionManager, and MCPServerInspector. * fix: eliminate cross-tenant readThrough contamination and TTL-expiry tool failures Thread pre-resolved serverConfig from tool creation context into callTool, removing dependency on the readThrough cache for config-source servers. This fixes two issues: - Cross-tenant contamination: the readThrough cache key was unscoped (just serverName), so concurrent multi-tenant requests for same-named servers would overwrite each other's entries - TTL expiry: tool calls happening >5s after config resolution would fail with "Configuration not found" because the readThrough entry had expired Changes: - Add optional serverConfig param to MCPManager.callTool — uses provided config directly, falling back to getServerConfig lookup for YAML/user servers - Thread serverConfig from createMCPTool through createToolInstance closure to callTool - Remove readThrough write from ensureSingleConfigServer — config-source servers are only accessible via configServers param (tenant-scoped) - Remove server-only readThrough fallback from getServerConfig - Increase config cache hash from 8 to 16 hex chars (64-bit) - Add isUserSourced boundary tests for all source/dbId combinations - Fix double Object.keys call in getMCPTools controller - Update test assertions for new getServerConfig behavior * fix: cache base configs for config-server users; narrow upsertConfigCache error handling - Refactor getAllServerConfigs to separate base config fetch (YAML + DB) from config-server layering. Base configs are cached via readThroughCacheAll regardless of whether configServers is provided, eliminating uncached MongoDB queries per request for config-server users - Narrow upsertConfigCache catch to duplicate-key errors only; infrastructure errors (Redis timeouts, network failures) now propagate instead of being silently swallowed, preventing inspection storms during outages * fix: restore correct merge order and document upsert error matching - Restore YAML → Config → User DB precedence in getAllServerConfigs (user DB servers have highest precedence, matching the JSDoc contract) - Add source comment on upsertConfigCache duplicate-key detection linking to the two cache implementations that define the error message * feat: complete config-source server support across all execution paths Wire configServers through the entire agent execution pipeline so config-source MCP servers are fully functional — not just visible in listings but executable in agent sessions. - Thread configServers into handleTools.js agent tool pipeline: resolve config servers from tenant context before MCP tool iteration, pass to getServerConfig, createMCPTools, and createMCPTool - Thread configServers into agent instructions pipeline: applyContextToAgent → getMCPInstructionsForServers → formatInstructionsForContext, resolved in client.js before agent context application - Add configServers param to createMCPTool and createMCPTools for reconnect path fallback - Add source field to redactServerSecrets allowlist for client UI differentiation of server tiers - Narrow invalidateConfigCache to only clear readThroughCacheAll (merged results), preserving YAML individual-server readThrough entries - Update context.spec.ts assertions for new configServers parameter * fix: add missing mocks for config-source server dependencies in client.test.js Mock getMCPServersRegistry, getAppConfig, and getTenantId that were added to client.js but not reflected in the test file's jest.mock declarations. * fix: update formatInstructionsForContext assertions for configServers param The test assertions expected formatInstructionsForContext to be called with only the server names array, but it now receives configServers as a second argument after the config-source server feature wiring. * fix: move configServers resolution before MCP tool loop to avoid TDZ configServers was declared with `let` after the first tool loop but referenced inside it via getServerConfig(), causing a ReferenceError temporal dead zone. Move declaration and resolution before the loop, using tools.some(mcpToolPattern) to gate the async resolution. * fix: address review findings — cache bypass, discoverServerTools gap, DRY - #2: getAllServerConfigs now always uses getBaseServerConfigs (cached via readThroughCacheAll) instead of bypassing it when configServers is present. Extracts user-DB entries from cached base by diffing against YAML keys to maintain YAML → Config → User DB merge order without extra MongoDB calls. - #3: Add configServers param to ToolDiscoveryOptions and thread it through discoverServerTools → getServerConfig so config-source servers are discoverable during OAuth reconnection flows. - #6: Replace inline import() type annotations in context.ts with proper import type { ParsedServerConfig } per AGENTS.md conventions. - #7: Extract resolveConfigServers(req) helper in MCP.js and use it from handleTools.js and client.js, eliminating the duplicated 6-line config resolution pattern. - #10: Restore removed "why" comment explaining getLoaded() vs getAll() choice in getMCPSetupData — documents non-obvious correctness constraint. - #11: Fix incomplete JSDoc param type on resolveAllMcpConfigs. * fix: consolidate imports, reorder constants, fix YAML-DB merge edge case - Merge duplicate @librechat/data-schemas requires in MCP.js into one - Move resolveConfigServers after module-level constants - Fix getAllServerConfigs edge case where user-DB entry overriding a YAML entry with the same name was excluded from userDbConfigs; now uses reference equality check to detect DB-overwritten YAML keys * fix: replace fragile string-match error detection with proper upsert method Add upsert() to IServerConfigsRepositoryInterface and all implementations (InMemory, Redis, RedisAggregateKey, DB). This eliminates the brittle error message string match ('already exists in cache') in upsertConfigCache that was the only thing preventing cross-process init races from silently discarding inspection results. Each implementation handles add-or-update atomically: - InMemory: direct Map.set() - Redis: direct cache.set() - RedisAggregateKey: read-modify-write under write lock - DB: delegates to update() (DB servers use explicit add() with ACL setup) * fix: wire configServers through remaining HTTP endpoints - getMCPServerById: use resolveAllMcpConfigs instead of bare getServerConfig - reinitialize route: resolve configServers before getServerConfig - auth-values route: resolve configServers before getServerConfig - getOAuthHeaders: accept configServers param, thread from callers - Update mcp.spec.js tests to mock getAllServerConfigs for GET by name * fix: thread serverConfig through getConnection for config-source servers Config-source servers exist only in configCacheRepo, not in YAML cache or DB. When callTool → getConnection → getUserConnection → getServerConfig runs without configServers, it returns undefined and throws. Fix by threading the pre-resolved serverConfig (providedConfig) from callTool through getConnection → getUserConnection → createUserConnectionInternal, using it as a fallback before the registry lookup. * fix: thread configServers through reinit, reconnect, and tool definition paths Wire configServers through every remaining call chain that creates or reconnects MCP server connections: - reinitMCPServer: accepts serverConfig and configServers, uses them for getServerConfig fallback, getConnection, and discoverServerTools - reconnectServer: accepts and passes configServers to reinitMCPServer - createMCPTools/createMCPTool: pass configServers to reconnectServer - ToolService.loadToolDefinitionsWrapper: resolves configServers from req, passes to both reinitMCPServer call sites - reinitialize route: passes serverConfig and configServers to reinitMCPServer * fix: address review findings — simplify merge, harden error paths, fix log labels - Simplify getAllServerConfigs merge: replace fragile reference-equality loop with direct spread { ...yamlConfigs, ...configServers, ...base } - Guard upsertConfigCache in lazyInitConfigServer catch block so cache failures don't mask the original inspection error - Deduplicate getYamlServerNames cold-start with promise dedup pattern - Remove dead `if (!mcpConfig)` guard in getMCPSetupData - Fix hardcoded "App server" in ServerConfigsCacheRedisAggregateKey error messages — now uses this.namespace for correct Config/App labeling - Remove misleading OAuth callback comment about readThrough cache - Move resolveConfigServers after module-level constants in MCP.js * fix: clear rejected yamlServerNames promise, fix config-source reinspect, fix reset log label - Clear yamlServerNamesPromise on rejection so transient cache errors don't permanently prevent ensureConfigServers from working - Skip reinspectServer for config-source servers (source: 'config') in reinitMCPServer — they lack a CACHE/DB storage location; retry is handled by CONFIG_STUB_RETRY_MS in ensureConfigServers - Use source field instead of dbId for storageLocation derivation - Fix remaining hardcoded "App" in reset() leaderCheck message * fix: persist oauthHeaders in flow state for config-source OAuth servers The OAuth callback route has no JWT auth context and cannot resolve config-source server configs. Previously, getOAuthHeaders would silently return {} for config-source servers, dropping custom token exchange headers. Now oauthHeaders are persisted in MCPOAuthFlowMetadata during flow initiation (which has auth context), and the callback reads them from the stored flow state with a fallback to the registry lookup for YAML/user-DB servers. * fix: update tests for getMCPSetupData null guard removal and ToolService mock - MCP.spec.js: update test to expect graceful handling of null mcpConfig instead of a throw (getAllServerConfigs always returns an object) - MCP.js: add defensive || {} for Object.entries(mcpConfig) in case of null from test mocks - ToolService.spec.js: add missing mock for ~/server/services/MCP (resolveConfigServers) * fix: address review findings — DRY, naming, logging, dead code, defensive guards - #1: Simplify getAllServerConfigs to single getBaseServerConfigs call, eliminating redundant double-fetch of cacheConfigsRepo.getAll() - #2: Add warning log when oauthHeaders absent from OAuth callback flow state - #3: Extract resolveAllMcpConfigs to MCP.js service layer; controller imports shared helper instead of reimplementing - #4: Rename _serverConfig/_provider to capturedServerConfig/capturedProvider in createToolInstance — these are actively used, not unused - #5: Log rejected results from ensureConfigServers Promise.allSettled so cache errors are visible instead of silently dropped - #6: Remove dead 'MCP config not found' error handlers from routes - #7: Document circular-dependency reason for dynamic require in clearMcpConfigCache - #8: Remove logger.error from withTimeout to prevent double-logging timeouts - #10: Add explicit userId guard in ServerConfigsDB.upsert with clear error message - #12: Use spread instead of mutation in addServer for immutability consistency - Add upsert mock to ensureConfigServers.test.ts DB mock - Update route tests for resolveAllMcpConfigs import change * fix: restore correct merge priority, use immutable spread, fix test mock - getAllServerConfigs: { ...configServers, ...base } so userDB wins over configServers, matching documented "User DB (highest)" priority - lazyInitConfigServer: use immutable spread instead of direct mutation for parsedConfig.source, consistent with addServer fix - Fix test to mock getAllServerConfigs as {} instead of null, remove unnecessary || {} defensive guard in getMCPSetupData * fix: error handling, stable hashing, flatten nesting, remove dead param - Wrap resolveConfigServers/resolveAllMcpConfigs in try/catch with graceful {} fallback so transient DB/cache errors don't crash tool pipeline - Sort keys in configCacheKey JSON.stringify for deterministic hashing regardless of object property insertion order - Flatten clearMcpConfigCache from 3 nested try-catch to early returns; document that user connections are cleaned up lazily (accepted tradeoff) - Remove dead configServers param from getAppToolFunctions (never passed) - Add security rationale comment for source field in redactServerSecrets * fix: use recursive key-sorting replacer in configCacheKey to prevent cross-tenant cache collision The array replacer in JSON.stringify acts as a property allowlist at every nesting depth, silently dropping nested keys like headers['X-API-Key'], oauth.client_secret, etc. Two configs with different nested values but identical top-level structure produced the same hash, causing cross-tenant cache hits and potential credential contamination. Switch to a function replacer that recursively sorts keys at all depths without dropping any properties. Also document the known gap in getOAuthServers: config-source OAuth servers are not covered by auto-reconnection or uninstall cleanup because callers lack request context. * fix: move clearMcpConfigCache to packages/api to eliminate circular dependency The function only depends on MCPServersRegistry and MCPManager, both of which live in packages/api. Import it directly from @librechat/api in the CJS layer instead of using dynamic require('~/config'). * chore: imports/fields ordering * fix: address review findings — error handling, targeted lookup, test gaps - Narrow resolveAllMcpConfigs catch to only wrap ensureConfigServers so getAppConfig/getAllServerConfigs failures propagate instead of masking infrastructure errors as empty server lists. - Use targeted getServerConfig in getMCPServerById instead of fetching all server configs for a single-server lookup. - Forward configServers to inner createMCPTool calls so reconnect path works for config-source servers. - Update getAllServerConfigs JSDoc to document disjoint-key design. - Add OAuth callback oauthHeaders fallback tests (flow state present vs registry fallback). - Add resolveConfigServers/resolveAllMcpConfigs unit tests covering happy path and error propagation. * fix: add getOAuthReconnectionManager mock to OAuth callback tests * chore: imports ordering	2026-03-28 10:36:43 -04:00
Danny Avila	77712c825f	🏢 feat: Tenant-Scoped App Config in Auth Login Flows (#12434) ... * feat: add resolveAppConfigForUser utility for tenant-scoped auth config TypeScript utility in packages/api that wraps getAppConfig in tenantStorage.run() when the user has a tenantId, falling back to baseOnly for new users or non-tenant deployments. Uses DI pattern (getAppConfig passed as parameter) for testability. Auth flows apply role-level overrides only (userId not passed) because user/group principal resolution is deferred to post-auth. * feat: tenant-scoped app config in auth login flows All auth strategies (LDAP, SAML, OpenID, social login) now use a two-phase domain check consistent with requestPasswordReset: 1. Fast-fail with base config (memory-cached, zero DB queries) 2. DB user lookup 3. Tenant-scoped re-check via resolveAppConfigForUser (only when user has a tenantId; otherwise reuse base config) This preserves the original fast-fail protection against globally blocked domains while enabling tenant-specific config overrides. OpenID error ordering preserved: AUTH_FAILED checked before domain re-check so users with wrong providers get the correct error type. registerUser unchanged (baseOnly, no user identity yet). * test: add tenant-scoped config tests for auth strategies Add resolveAppConfig.spec.ts in packages/api with 8 tests: - baseOnly fallback for null/undefined/no-tenant users - tenant-scoped config with role and tenantId - ALS context propagation verified inside getAppConfig callback - undefined role with tenantId edge case Update strategy and AuthService tests to mock resolveAppConfigForUser via @librechat/api. Tests verify two-phase domain check behavior: fast-fail before DB, tenant re-check after. Non-tenant users reuse base config without calling resolveAppConfigForUser. * refactor: skip redundant domain re-check for non-tenant users Guard the second isEmailDomainAllowed call with appConfig !== baseConfig in SAML, OpenID, and social strategies. For non-tenant users the tenant config is the same base config object, so the second check is a no-op. Narrow eslint-disable in resolveAppConfig.spec.ts to the specific require line instead of blanket file-level suppression. * fix: address review findings — consistency, tests, and ordering - Consolidate duplicate require('@librechat/api') in AuthService.js - Add two-phase domain check to LDAP (base fast-fail before findUser), making all strategies consistent with PR description - Add appConfig !== baseConfig guard to requestPasswordReset second domain check, consistent with SAML/OpenID/social strategies - Move SAML provider check before tenant config resolution to avoid unnecessary resolveAppConfigForUser call for wrong-provider users - Add tenant domain rejection tests to SAML, OpenID, and social specs verifying that tenant config restrictions actually block login - Add error propagation tests to resolveAppConfig.spec.ts - Remove redundant mockTenantStorage alias in resolveAppConfig.spec.ts - Narrow eslint-disable to specific require line * test: add tenant domain rejection test for LDAP strategy Covers the appConfig !== baseConfig && !isEmailDomainAllowed path, consistent with SAML, OpenID, and social strategy specs. * refactor: rename resolveAppConfig to app/resolve per AGENTS.md Rename resolveAppConfig.ts → resolve.ts and resolveAppConfig.spec.ts → resolve.spec.ts to align with the project's concise naming convention. * fix: remove fragile reference-equality guard, add logging and docs Remove appConfig !== baseConfig guard from all strategies and requestPasswordReset. The guard relied on implicit cache-backend identity semantics (in-memory Keyv returns same object reference) that would silently break with Redis or cloned configs. The second isEmailDomainAllowed call is a cheap synchronous check — always running it is clearer and eliminates the coupling. Add audit logging to requestPasswordReset domain blocks (base and tenant), consistent with all auth strategies. Extract duplicated error construction into makeDomainDeniedError(). Wrap resolveAppConfigForUser in requestPasswordReset with try/catch to prevent DB errors from leaking to the client via the controller's generic catch handler. Document the dual tenantId propagation (ALS for DB isolation, explicit param for cache key) in resolveAppConfigForUser JSDoc. Add comment documenting the LDAP error-type ordering change (cross-provider users from blocked domains now get 'domain not allowed' instead of AUTH_FAILED). Assert resolveAppConfigForUser is not called on LDAP provider mismatch path. * fix: return generic response for tenant domain block in password reset Tenant-scoped domain rejection in requestPasswordReset now returns the same generic "If an account with that email exists..." response instead of an Error. This prevents user-enumeration: an attacker cannot distinguish between "email not found" and "tenant blocks this domain" by comparing HTTP responses. The base-config fast-fail (pre-user-lookup) still returns an Error since it fires before any user existence is revealed. * docs: document phase 1 vs phase 2 domain check behavior in JSDoc Phase 1 (base config, pre-findUser) intentionally returns Error/400 to reveal globally blocked domains without confirming user existence. Phase 2 (tenant config, post-findUser) returns generic 200 to prevent user-enumeration. This distinction is now explicit in the JSDoc.	2026-03-27 16:08:43 -04:00
Danny Avila	9f6d8c6e93	🧵 feat: ALS Context Middleware, Tenant Threading, and Config Cache Invalidation (#12407) ... * feat: add tenant context middleware for ALS-based isolation Introduces tenantContextMiddleware that propagates req.user.tenantId into AsyncLocalStorage, activating the Mongoose applyTenantIsolation plugin for all downstream DB queries within a request. - Strict mode (TENANT_ISOLATION_STRICT=true) returns 403 if no tenantId - Non-strict mode passes through for backward compatibility - No-op for unauthenticated requests - Includes 6 unit tests covering all paths * feat: register tenant middleware and wrap startup/auth in runAsSystem() - Register tenantContextMiddleware in Express app after capability middleware - Wrap server startup initialization in runAsSystem() for strict mode compat - Wrap auth strategy getAppConfig() calls in runAsSystem() since they run before user context is established (LDAP, SAML, OpenID, social login, AuthService) * feat: thread tenantId through all getAppConfig callers Pass tenantId from req.user to getAppConfig() across all callers that have request context, ensuring correct per-tenant cache key resolution. Also fixes getBaseConfig admin endpoint to scope to requesting admin's tenant instead of returning the unscoped base config. Files updated: - Controllers: UserController, PluginController - Middleware: checkDomainAllowed, balance - Routes: config - Services: loadConfigModels, loadDefaultModels, getEndpointsConfig, MCP - Audio services: TTSService, STTService, getVoices, getCustomConfigSpeech - Admin: getBaseConfig endpoint * feat: add config cache invalidation on admin mutations - Add clearOverrideCache(tenantId?) to flush per-principal override caches by enumerating Keyv store keys matching _OVERRIDE_: prefix - Add invalidateConfigCaches() helper that clears base config, override caches, tool caches, and endpoint config cache in one call - Wire invalidation into all 5 admin config mutation handlers (upsert, patch, delete field, delete overrides, toggle active) - Add strict mode warning when __default__ tenant fallback is used - Add 3 new tests for clearOverrideCache (all/scoped/base-preserving) * chore: update getUserPrincipals comment to reflect ALS-based tenant filtering The TODO(#12091) about missing tenantId filtering is resolved by the tenant context middleware + applyTenantIsolation Mongoose plugin. Group queries are now automatically scoped by tenantId via ALS. * fix: replace runAsSystem with baseOnly for pre-tenant code paths App configs are tenant-owned — runAsSystem() would bypass tenant isolation and return cross-tenant DB overrides. Instead, add baseOnly option to getAppConfig() that returns YAML-derived config only, with zero DB queries. All startup code, auth strategies, and MCP initialization now use getAppConfig({ baseOnly: true }) to get the YAML config without touching the Config collection. * fix: address PR review findings — middleware ordering, types, cache safety - Chain tenantContextMiddleware inside requireJwtAuth after passport auth instead of global app.use() where req.user is always undefined (Finding 1) - Remove global tenantContextMiddleware registration from index.js - Update BalanceMiddlewareOptions to include tenantId, remove redundant cast (Finding 4) - Add warning log when clearOverrideCache cannot enumerate keys on Redis (Finding 3) - Use startsWith instead of includes for cache key filtering (Finding 12) - Use generator loop instead of Array.from for key enumeration (Finding 3) - Selective barrel export — exclude _resetTenantMiddlewareStrictCache (Finding 5) - Move isMainThread check to module level, remove per-request check (Finding 9) - Move mid-file require to top of app.js (Finding 8) - Parallelize invalidateConfigCaches with Promise.all (Finding 10) - Remove clearOverrideCache from public app.js exports (internal only) - Strengthen getUserPrincipals comment re: ALS dependency (Finding 2) * fix: restore runAsSystem for startup DB ops, consolidate require, clarify baseOnly - Restore runAsSystem() around performStartupChecks, updateInterfacePermissions, initializeMCPs, and initializeOAuthReconnectManager — these make Mongoose queries that need system context in strict tenant mode (NEW-3) - Consolidate duplicate require('@librechat/api') in requireJwtAuth.js (NEW-1) - Document that baseOnly ignores role/userId/tenantId in JSDoc (NEW-2) * test: add requireJwtAuth tenant chaining + invalidateConfigCaches tests - requireJwtAuth: 5 tests verifying ALS tenant context is set after passport auth, isolated between concurrent requests, and not set when user has no tenantId (Finding 6) - invalidateConfigCaches: 4 tests verifying all four caches are cleared, tenantId is threaded through, partial failure is handled gracefully, and operations run in parallel via Promise.all (Finding 11) * fix: address Copilot review — passport errors, namespaced cache keys, /base scoping - Forward passport errors in requireJwtAuth before entering tenant middleware — prevents silent auth failures from reaching handlers (P1) - Account for Keyv namespace prefix in clearOverrideCache — stored keys are namespaced as "APP_CONFIG:_OVERRIDE_:..." not "_OVERRIDE_:...", so override caches were never actually matched/cleared (P2) - Remove role from getBaseConfig — /base should return tenant-scoped base config, not role-merged config that drifts per admin role (P2) - Return tenantStorage.run() for cleaner async semantics - Update mock cache in service.spec.ts to simulate Keyv namespacing * fix: address second review — cache safety, code quality, test reliability - Decouple cache invalidation from mutation response: fire-and-forget with logging so DB mutation success is not masked by cache failures - Extract clearEndpointConfigCache helper from inline IIFE - Move isMainThread check to lazy once-per-process guard (no import side effect) - Memoize process.env read in overrideCacheKey to avoid per-request env lookups and log flooding in strict mode - Remove flaky timer-based parallelism assertion, use structural check - Merge orphaned double JSDoc block on getUserPrincipals - Fix stale [getAppConfig] log prefix → [ensureBaseConfig] - Fix import order in tenant.spec.ts (package types before local values) - Replace "Finding 1" reference with self-contained description - Use real tenantStorage primitives in requireJwtAuth spec mock * fix: move JSDoc to correct function after clearEndpointConfigCache extraction * refactor: remove Redis SCAN from clearOverrideCache, rely on TTL expiry Redis SCAN causes 60s+ stalls under concurrent load (see #12410). APP_CONFIG defaults to FORCED_IN_MEMORY_CACHE_NAMESPACES, so the in-memory store.keys() path handles the standard case. When APP_CONFIG is Redis-backed, overrides expire naturally via overrideCacheTtl (60s default) — an acceptable window for admin config mutations. * fix: remove return from tenantStorage.run to satisfy void middleware signature * fix: address second review — cache safety, code quality, test reliability - Switch invalidateConfigCaches from Promise.all to Promise.allSettled so partial failures are logged individually instead of producing one undifferentiated error (Finding 3) - Gate overrideCacheKey strict-mode warning behind a once-per-process flag to prevent log flooding under load (Finding 4) - Add test for passport error forwarding in requireJwtAuth — the if (err) { return next(err) } branch now has coverage (Finding 5) - Add test for real partial failure in invalidateConfigCaches where clearAppConfigCache rejects (not just the swallowed endpoint error) * chore: reorder imports in index.js and app.js for consistency - Moved logger and runAsSystem imports to maintain a consistent import order across files. - Improved code readability by ensuring related imports are grouped together.	2026-03-26 17:35:00 -04:00
Danny Avila	8e2721011e	🔑 fix: Robust MCP OAuth Detection in Tool-Call Flow (#12418) ... * fix(api): add buildOAuthToolCallName utility for MCP OAuth flows Extract a shared utility that builds the synthetic tool-call name used during MCP OAuth flows (oauth_mcp_{normalizedServerName}). Uses startsWith on the raw serverName (not the normalized form) to guard against double-wrapping, so names that merely normalize to start with oauth_mcp_ (e.g., oauth@mcp@server) are correctly prefixed while genuinely pre-wrapped names are left as-is. Add 8 unit tests covering normal names, pre-wrapped names, _mcp_ substrings, special characters, non-ASCII, and empty string inputs. * fix(backend): use buildOAuthToolCallName in MCP OAuth flows Replace inline tool-call name construction in both reconnectServer (MCP.js) and createOAuthEmitter (ToolService.js) with the shared buildOAuthToolCallName utility. Remove unused normalizeServerName import from ToolService.js. Fix import ordering in both files. This ensures the oauth_mcp_ prefix is consistently applied so the client correctly identifies MCP OAuth flows and binds the CSRF cookie to the right server. * fix(client): robust MCP OAuth detection and split handling in ToolCall - Fix split() destructuring to preserve tail segments for server names containing _mcp_ (e.g., foo_mcp_bar no longer truncated to foo). - Add auth URL redirect_uri fallback: when the tool-call name lacks the _mcp_ delimiter, parse redirect_uri for the MCP callback path. Set function_name to the extracted server name so progress text shows the server, not the raw tool-call ID. - Display server name instead of literal "oauth" as function_name, gated on auth presence to avoid misidentifying real tools named "oauth". - Consolidate three independent new URL(auth) parses into a single parsedAuthUrl useMemo shared across detection, actionId, and authDomain hooks. - Replace any type on ProgressText test mock with structural type. - Add 8 tests covering delimiter detection, multi-segment names, function_name display, redirect_uri fallback, normalized _mcp_ server names, and non-MCP action auth exclusion. * chore: fix import order in utils.test.ts * fix(client): drop auth gate on OAuth displayName so completed flows show server name The createOAuthEnd handler re-emits the toolCall delta without auth, so auth is cleared on the client after OAuth completes. Gating displayName on `func === 'oauth' && auth` caused completed OAuth steps to render "Completed oauth" instead of "Completed my-server". Remove the `&& auth` gate — within the MCP delimiter branch the func="oauth" check alone is sufficient. Also remove `auth` from the useMemo dep array since only `parsedAuthUrl` is referenced. Update the test to assert correct post-completion display.	2026-03-26 14:45:13 -04:00
Danny Avila	4b6d68b3b5	🎛️ feat: DB-Backed Per-Principal Config System (#12354) ... * ✨ feat: Add Config schema, model, and methods for role-based DB config overrides Add the database foundation for principal-based configuration overrides (user, group, role) in data-schemas. Includes schema with tenantId and tenant isolation, CRUD methods, and barrel exports. * 🔧 fix: Add shebang and enforce LF line endings for git hooks The pre-commit hook was missing #!/bin/sh, and core.autocrlf=true was converting it to CRLF, both causing "Exec format error" on Windows. Add .gitattributes to force LF for .husky/* and *.sh files. * ✨ feat: Add admin config API routes with section-level capability checks Add /api/admin/config endpoints for managing per-principal config overrides (user, group, role). Handlers in @librechat/api use DI pattern with section-level hasConfigCapability checks for granular access control. Supports full overrides replacement, per-field PATCH via dot-paths, field deletion, toggle active, and listing. * 🐛 fix: Move deleteConfigField fieldPath from URL param to request body The path-to-regexp wildcard syntax (:fieldPath(*)) is not supported by the version used in Express. Send fieldPath in the DELETE request body instead, which also avoids URL-encoding issues with dotted paths. * ✨ feat: Wire config resolution into getAppConfig with override caching Add mergeConfigOverrides utility in data-schemas for deep-merging DB config overrides into base AppConfig by priority order. Update getAppConfig to query DB for applicable configs when role/userId is provided, with short-TTL caching and a hasAnyConfigs feature flag for zero-cost when no DB configs exist. Also: add unique compound index on Config schema, pass userId from config middleware, and signal config changes from admin API handlers. * 🔄 refactor: Extract getAppConfig logic into packages/api as TS service Move override resolution, caching strategy, and signalConfigChange from api/server/services/Config/app.js into packages/api/src/app/appConfigService.ts using the DI factory pattern (createAppConfigService). The JS file becomes a thin wiring layer injecting loadBaseConfig, cache, and DB dependencies. * 🧹 chore: Rename configResolution.ts to resolution.ts * ✨ feat: Move admin types & capabilities to librechat-data-provider Move SystemCapabilities, CapabilityImplications, and utility functions (hasImpliedCapability, expandImplications) from data-schemas to data-provider so they are available to external consumers like the admin panel without a data-schemas dependency. Add API-friendly admin types: TAdminConfig, TAdminSystemGrant, TAdminAuditLogEntry, TAdminGroup, TAdminMember, TAdminUserSearchResult, TCapabilityCategory, and CAPABILITY_CATEGORIES. data-schemas re-exports these from data-provider and extends with config-schema-derived types (ConfigSection, SystemCapability union). Bump version to 0.8.500. * feat: Add JSON-serializable admin config API response types to data-schemas Add AdminConfig, AdminConfigListResponse, AdminConfigResponse, and AdminConfigDeleteResponse types so both LibreChat API handlers and the admin panel can share the same response contract. Bump version to 0.0.41. * refactor: Move admin capabilities & types from data-provider to data-schemas SystemCapabilities, CapabilityImplications, utility functions, CAPABILITY_CATEGORIES, and admin API response types should not be in data-provider as it gets compiled into the frontend bundle, exposing the capability surface. Moved everything to data-schemas (server-only). All consumers already import from @librechat/data-schemas, so no import changes needed elsewhere. Consolidated duplicate AdminConfig type (was in both config.ts and admin.ts). * chore: Bump @librechat/data-schemas to 0.0.42 * refactor: Reorganize admin capabilities into admin/ and types/admin.ts Split systemCapabilities.ts following data-schemas conventions: - Types (BaseSystemCapability, SystemCapability, AdminConfig, etc.) → src/types/admin.ts - Runtime code (SystemCapabilities, CapabilityImplications, utilities) → src/admin/capabilities.ts Revert data-provider version to 0.8.401 (no longer modified). * chore: Fix import ordering, rename appConfigService to service - Rename app/appConfigService.ts → app/service.ts (directory provides context) - Fix import order in admin/config.ts, types/admin.ts, types/config.ts - Add naming convention to AGENTS.md * feat: Add DB base config support (role/__base__) - Add BASE_CONFIG_PRINCIPAL_ID constant for reserved base config doc - getApplicableConfigs always includes __base__ in queries - getAppConfig queries DB even without role/userId when DB configs exist - Bump @librechat/data-schemas to 0.0.43 * fix: Address PR review issues for admin config - Add listAllConfigs method; listConfigs endpoint returns all active configs instead of only __base__ - Normalize principalId to string in all config methods to prevent ObjectId vs string mismatch on user/group lookups - Block __proto__ and all dunder-prefixed segments in field path validation to prevent prototype pollution - Fix configVersion off-by-one: default to 0, guard pre('save') with !isNew, use $inc on findOneAndUpdate - Remove unused getApplicableConfigs from admin handler deps * fix: Enable tree-shaking for data-schemas, bump packages - Switch data-schemas Rollup output to preserveModules so each source file becomes its own chunk; consumers (admin panel) can now import just the modules they need without pulling in winston/mongoose/etc. - Add sideEffects: false to data-schemas package.json - Bump data-schemas to 0.0.44, data-provider to 0.8.402 * feat: add capabilities subpath export to data-schemas Adds `@librechat/data-schemas/capabilities` subpath export so browser consumers can import BASE_CONFIG_PRINCIPAL_ID and capability constants without pulling in Node.js-only modules (winston, async_hooks, etc.). Bump version to 0.0.45. * fix: include dist/ in data-provider npm package Add explicit files field so npm includes dist/types/ in the published package. Without this, the root .gitignore exclusion of dist/ causes npm to omit type declarations, breaking TypeScript consumers. * chore: bump librechat-data-provider to 0.8.403 * feat: add GET /api/admin/config/base for raw AppConfig Returns the full AppConfig (YAML + DB base merged) so the admin panel can display actual config field values and structure. The startup config endpoint (/api/config) returns TStartupConfig which is a different shape meant for the frontend app. * chore: imports order * fix: address code review findings for admin config Critical: - Fix clearAppConfigCache: was deleting from wrong cache store (CONFIG_STORE instead of APP_CONFIG), now clears BASE and HAS_DB_CONFIGS keys - Eliminate race condition: patchConfigField and deleteConfigField now use atomic MongoDB $set/$unset with dot-path notation instead of read-modify-write cycles, removing the lost-update bug entirely - Add patchConfigFields and unsetConfigField atomic DB methods Major: - Reorder cache check before principal resolution in getAppConfig so getUserPrincipals DB query only fires on cache miss - Replace '' as ConfigSection with typed BROAD_CONFIG_ACCESS constant - Parallelize capability checks with Promise.all instead of sequential awaits in for loops - Use loose equality (== null) for cache miss check to handle both null and undefined returns from cache implementations - Set HAS_DB_CONFIGS_KEY to true on successful config fetch Minor: - Remove dead pre('save') hook from config schema (all writes use findOneAndUpdate which bypasses document hooks) - Consolidate duplicate type imports in resolution.ts - Remove dead deepGet/deepSet/deepUnset functions (replaced by atomic ops) - Add .sort({ priority: 1 }) to getApplicableConfigs query - Rename _impliedBy to impliedByMap * fix: self-referencing BROAD_CONFIG_ACCESS constant * fix: replace type-cast sentinel with proper null parameter Update hasConfigCapability to accept ConfigSection | null where null means broad access check (MANAGE_CONFIGS or READ_CONFIGS only). Removes the '' as ConfigSection type lie from admin config handlers. * fix: remaining review findings + add tests - listAllConfigs accepts optional { isActive } filter so admin listing can show inactive configs (#9) - Standardize session application to .session(session ?? null) across all config DB methods (#15) - Export isValidFieldPath and getTopLevelSection for testability - Add 38 tests across 3 spec files: - config.spec.ts (api): path validation, prototype pollution rejection - resolution.spec.ts: deep merge, priority ordering, array replacement - config.spec.ts (data-schemas): full CRUD, ObjectId normalization, atomic $set/$unset, configVersion increment, toggle, __base__ query * fix: address second code review findings - Fix cross-user cache contamination: overrideCacheKey now handles userId-without-role case with its own cache key (#1) - Add broad capability check before DB lookup in getConfig to prevent config existence enumeration (#2/#3) - Move deleteConfigField fieldPath from request body to query parameter for proxy/load balancer compatibility (#5) - Derive BaseSystemCapability from SystemCapabilities const instead of manual string union (#6) - Return 201 on upsert creation, 200 on update (#11) - Remove inline narration comments per AGENTS.md (#12) - Type overrides as Partial<TCustomConfig> in DB methods and handler deps (#13) - Replace double as-unknown-as casts in resolution.ts with generic deepMerge<T> (#14) - Make override cache TTL injectable via AppConfigServiceDeps (#16) - Add exhaustive never check in principalModel switch (#17) * fix: remaining review findings — tests, rename, semantics - Rename signalConfigChange → markConfigsDirty with JSDoc documenting the stale-window tradeoff and overrideCacheTtl knob - Fix DEFAULT_OVERRIDE_CACHE_TTL naming convention - Add createAppConfigService tests (14 cases): cache behavior, feature flag, cross-user key isolation, fallback on error, markConfigsDirty - Add admin handler integration tests (13 cases): auth ordering, 201/200 on create/update, fieldPath from query param, markConfigsDirty calls, capability checks * fix: global flag corruption + empty overrides auth bypass - Remove HAS_DB_CONFIGS_KEY=false optimization: a scoped query returning no configs does not mean no configs exist globally. Setting the flag false from a per-principal query short-circuited all subsequent users. - Add broad manage capability check before section checks in upsertConfigOverrides: empty overrides {} no longer bypasses auth. * test: add regression and invariant tests for config system Regression tests: - Bug 1: User A's empty result does not short-circuit User B's overrides - Bug 2: Empty overrides {} returns 403 without MANAGE_CONFIGS Invariant tests (applied across ALL handlers): - All 5 mutation handlers call markConfigsDirty on success - All 5 mutation handlers return 401 without auth - All 5 mutation handlers return 403 without capability - All 3 read handlers return 403 without capability * fix: third review pass — all findings addressed Service (service.ts): - Restore HAS_DB_CONFIGS=false for base-only queries (no role/userId) so deployments with zero DB configs skip DB queries (#1) - Resolve cache once at factory init instead of per-invocation (#8) - Use BASE_CONFIG_PRINCIPAL_ID constant in overrideCacheKey (#10) - Add JSDoc to clearAppConfigCache documenting stale-window (#4) - Fix log message to not say "from YAML" (#14) Admin handlers (config.ts): - Use configVersion===1 for 201 vs 200, eliminating TOCTOU race (#2) - Add Array.isArray guard on overrides body (#5) - Import CapabilityUser from capabilities.ts, remove duplicate (#6) - Replace as-unknown-as cast with targeted type assertion (#7) - Add MAX_PATCH_ENTRIES=100 cap on entries array (#15) - Reorder deleteConfigField to validate principalType first (#12) - Export CapabilityUser from middleware/capabilities.ts DB methods (config.ts): - Remove isActive:true from patchConfigFields to prevent silent reactivation of disabled configs (#3) Schema (config.ts): - Change principalId from Schema.Types.Mixed to String (#11) Tests: - Add patchConfigField unsafe fieldPath rejection test (#9) - Add base-only HAS_DB_CONFIGS=false test (#1) - Update 201/200 tests to use configVersion instead of findConfig (#2) * fix: add read handler 401 invariant tests + document flag behavior - Add invariant: all 3 read handlers return 401 without auth - Document on markConfigsDirty that HAS_DB_CONFIGS stays true after all configs are deleted until clearAppConfigCache or restart * fix: remove HAS_DB_CONFIGS false optimization entirely getApplicableConfigs([]) only queries for __base__, not all configs. A deployment with role/group configs but no __base__ doc gets the flag poisoned to false by a base-only query, silently ignoring all scoped overrides. The optimization is not safe without a comprehensive Config.exists() check, which adds its own DB cost. Removed entirely. The flag is now write-once-true (set when configs are found or by markConfigsDirty) and only cleared by clearAppConfigCache/restart. * chore: reorder import statements in app.js for clarity * refactor: remove HAS_DB_CONFIGS_KEY machinery entirely The three-state flag (false/null/true) was the source of multiple bugs across review rounds. Every attempt to safely set it to false was defeated by getApplicableConfigs querying only a subset of principals. Removed: HAS_DB_CONFIGS_KEY constant, all reads/writes of the flag, markConfigsDirty (now a no-op concept), notifyChange wrapper, and all tests that seeded false manually. The per-user/role TTL cache (overrideCacheTtl, default 60s) is the sole caching mechanism. On cache miss, getApplicableConfigs queries the DB. This is one indexed query per user per TTL window — acceptable for the config override use case. * docs: rewrite admin panel remaining work with current state * perf: cache empty override results to avoid repeated DB queries When getApplicableConfigs returns no configs for a principal, cache baseConfig under their override key with TTL. Without this, every user with no per-principal overrides hits MongoDB on every request after the 60s cache window expires. * fix: add tenantId to cache keys + reject PUBLIC principal type - Include tenantId in override cache keys to prevent cross-tenant config contamination. Single-tenant deployments (tenantId undefined) use '_' as placeholder — no behavior change for them. - Reject PrincipalType.PUBLIC in admin config validation — PUBLIC has no PrincipalModel and is never resolved by getApplicableConfigs, so config docs for it would be dead data. - Config middleware passes req.user.tenantId to getAppConfig. * fix: fourth review pass findings DB methods (config.ts): - findConfigByPrincipal accepts { includeInactive } option so admin GET can retrieve inactive configs (#5) - upsertConfig catches E11000 duplicate key on concurrent upserts and retries without upsert flag (#2) - unsetConfigField no longer filters isActive:true, consistent with patchConfigFields (#11) - Typed filter objects replace Record<string, unknown> (#12) Admin handlers (config.ts): - patchConfigField: serial broad capability check before Promise.all to pre-warm ALS principal cache, preventing N parallel DB calls (#3) - isValidFieldPath rejects leading/trailing dots and consecutive dots (#7) - Duplicate fieldPaths in patch entries return 400 (#8) - DEFAULT_PRIORITY named constant replaces hardcoded 10 (#14) - Admin getConfig and patchConfigField pass includeInactive to findConfigByPrincipal (#5) - Route import uses barrel instead of direct file path (#13) Resolution (resolution.ts): - deepMerge has MAX_MERGE_DEPTH=10 guard to prevent stack overflow from crafted deeply nested configs (#4) * fix: final review cleanup - Remove ADMIN_PANEL_REMAINING.md (local dev notes with Windows paths) - Add empty-result caching regression test - Add tenantId to AdminConfigDeps.getAppConfig type - Restore exhaustive never check in principalModel switch - Standardize toggleConfigActive session handling to options pattern * fix: validate priority in patchConfigField handler Add the same non-negative number validation for priority that upsertConfigOverrides already has. Without this, invalid priority values could be stored via PATCH and corrupt merge ordering. * chore: remove planning doc from PR * fix: correct stale cache key strings in service tests * fix: clean up service tests and harden tenant sentinel - Remove no-op cache delete lines from regression tests - Change no-tenant sentinel from '_' to '__default__' to avoid collision with a real tenant ID when multi-tenancy is enabled - Remove unused CONFIG_STORE from AppConfigServiceDeps * chore: bump @librechat/data-schemas to 0.0.46 * fix: block prototype-poisoning keys in deepMerge Skip __proto__, constructor, and prototype keys during config merge to prevent prototype pollution via PUT /api/admin/config overrides.	2026-03-25 19:39:29 -04:00
Marco Beretta	0c66823c26	🧩 feat: Redesign Tool Call UI with Contextual Icons, Smart Grouping, and Rich Output Rendering (#12163) ... * feat: redesign tool call UI with type-specific icons, smart grouping, and rich output rendering Replace the generic spinner/checkmark tool call UI with a modern, Cursor-inspired design: - Add per-tool-type icons (Plug for MCP, Terminal for code, Globe for web search, etc.) - Group 2+ consecutive tool calls into collapsible "Used N tools" sections - Stack unique tool icons in grouped headers with overlapping circle design - Replace raw JSON output with intelligent renderers (table, error, text) - Restructure ToolCallInfo: output first, parameters collapsible at bottom - Add shared useExpandCollapse hook for consistent animations - Add CodeWindowHeader for ExecuteCode windowed view - Remove FinishedIcon (purple checkmark) entirely * feat: display custom MCP server icons in tool calls Add useMCPIconMap hook to resolve MCP server names to their configured icon paths. ToolIcon and StackedToolIcons now accept custom icon URLs, showing actual server logos (e.g., Home Assistant, GitHub) instead of the generic Plug icon for MCP tool calls. * refactor: unify container styling across code blocks, mermaid, and tool output Replace hardcoded gray colors with theme tokens throughout: - CodeBlock: bg-gray-900/700 -> bg-surface-secondary/tertiary + border-border-light - Mermaid dialog: bg-gray-700 -> bg-surface-secondary, text-gray-200 -> text-text-secondary - Mermaid containers: rounded-xl -> rounded-lg, remove shadow-md for consistency - ResultSwitcher: bg-gray-700 -> bg-surface-secondary with border separator - RunCode: hover:bg-gray-700 -> hover:bg-surface-hover - ErrorOutput: add border for visual consistency - MermaidHeader/CodeWindowHeader: consistent focus outlines using border-heavy * refactor: simplify tool output to plain text, remove custom renderers Remove over-engineered tool output system (TableOutput, ErrorOutput, detectOutputType) in favor of simple text extraction. Tool output now extracts the text content from MCP content blocks and displays it as clean readable text — no tables, no error styling, no JSON formatting. Parameters only show key-value badges for simple objects; complex JSON is hidden instead of dumped raw. Matches Cursor-style simplicity. * fix: handle error messages and format JSON arrays in tool output - Strip verbose MCP error prefixes (Error: [MCP][server][tool] tool call failed: Error POSTing...) and show just the meaningful error message - Display errors in red text - Format uniform JSON arrays as readable lists (name — path) instead of raw JSON dumps - Format plain JSON objects as key: value lines * feat: improve JSON display in tool call output and parameters - Replace flat formatObject with recursive formatValue for proper indented display of nested JSON structures - Add ComplexInput component for tool parameters with nested objects, arrays, or long strings (previously hidden) - Broaden hasParams check to show parameters for all object types - Add font-mono to output renderer for better alignment * feat: add localization keys for tool errors, web search, and code UI * refactor: move Mermaid components into dedicated directory module * refactor: extract CodeBar, FloatingCodeBar, and copy utilities from CodeBlock * feat: replace manual SVG icons with @icons-pack/react-simple-icons Supports 50+ programming languages with tree-shaken brand icons instead of hand-crafted SVGs for 19 languages. * refactor: simplify code execution UI with persistent code toggle * refactor: use useExpandCollapse hook in Thinking and Reasoning * feat: improve tool call error states, subtitles, and group summaries * feat: redesign web search with inline source display * feat: improve agent handoff with keyboard accessibility * feat: reorganize exports order in hooks and utils * refactor: unify CopyCodeButton with animated icon transitions and iconOnly support * feat: add run code state machine with animated success/error feedback * refactor: improve ResultSwitcher with lucide icons and accessibility * refactor: update CopyButton component * refactor: replace CopyCodeButton with CopyButton component across multiple files * test: add ImageGen test stubs * test: add RetrievalCall test stubs * feat: merge ImageGen with ToolIcon and localized progress text * feat: modernize RetrievalCall with ToolIcon and collapsible output * test: add getToolIconType action delimiter tests * test: add ImageGen collapsible output tests * feat: add action ToolIcon type with Zap icon * fix: replace AgentHandoff div with semantic button * feat: add aria-live regions to tool components * feat: redesign execute_code tool UI with syntax highlighting and language icons - Remove filename labels (script.py, main.rs) and line counter from CodeWindowHeader - Replace generic FileCode icon with language-specific LangIcon - Add syntax highlighting via highlight.js to code blocks - Add SquareTerminal icon to ExecuteCode progress text - Use shared CopyButton component in CodeWindowHeader - Remove active:scale-95 press animation from CopyButton and RunCode * feat: dynamic tool status text sizing based on markdown font-size variable - Add tool-status-text CSS class using calc(0.9 * --markdown-font-size) - Update progress-text-wrapper to use dynamic sizing instead of base size - Apply tool-status-text to WebSearch, ToolCallGroup, AgentHandoff, ImageGen - Replace hardcoded text-sm/text-xs with dynamic class across all tools - Animate chevron rotation in ProgressText and ToolCallGroup - Update subtitle text color from tertiary to secondary * fix: consistent spacing and text styles across all tool components - Standardize tool status row spacing to my-1/my-1.5 across all components - Update ToolCallInfo text from tertiary to secondary, add vertical padding - Animate ToolCallInfo parameters chevron rotation - Update OutputRenderer link colors from tertiary to secondary * feat: unify tool call grouping for all tool types All consecutive tool calls (MCP, execute_code, web_search, image_gen, file_search, code_interpreter) are now grouped under a single collapsible "Used N tools" header instead of only grouping generic tool calls. - Remove SPECIAL_TOOL_NAMES blacklist from groupToolCalls - Replace getToolCallData with getToolMeta to handle all tool types - Use renderPart callback in ToolCallGroup for proper component routing - Add file_search and code_interpreter mappings to getToolIconType * feat: friendly tool group labels, more icons, and output copy button - Show friendly names in group summary (Code, Web Search, Image Generation) instead of raw tool names - Display MCP server names instead of individual function names - Deduplicate labels and show up to 3 with +N overflow - Increase stacked icons from 3 to 4 - Add icon-only copy button to tool output (OutputRenderer) * fix: execute_code spacing and syntax-highlighted code visibility Match ToolCall spacing by using my-1.5 on status line and moving my-2 inside overflow-hidden. Replace broken hljs.highlight() with lowlight (same engine used by rehype-highlight for markdown code blocks) to render syntax-highlighted code as React elements. Handle object args in useParseArgs to support both string and Record arg formats. * feat: replace showCode with auto-expand tools setting Replace the execute_code-only "Always show code when using code interpreter" global toggle with a new "Auto-expand tool details" setting that controls all tool types. Each tool instance now uses independent local state initialized from the setting, so expanding one tool no longer affects others. Applies to ToolCall, ExecuteCode, ToolCallGroup, and CodeAnalyze components. * fix: apply auto-expand tools setting to WebSearch and RetrievalCall * fix: only auto-expand tools when content is available Defer auto-expansion until tool output or content arrives, preventing empty bordered containers from showing while tools are still running. Uses useEffect to expand when output becomes available during streaming. * feat: redesign file_search tool output, citations, and file preview - Redesign RetrievalCall with per-file cards using OutputRenderer (truncated content with show more/less, copy button) matching MCP tool pattern - Route file_search tool calls from Agents API to RetrievalCall instead of generic ToolCall - Add FilePreviewDialog for viewing files (PDF iframe, text content) with download option, opened from clickable filenames - Redesign file citations: FileText icon in badge, relevance and page numbers in hovercard, click opens file preview instead of downloading - Add file preview to message file attachments (Files.tsx) - Fix hovercard animation to slide top-to-bottom and dismiss instantly on file click to prevent glitching over dialog - Add localization keys for relevance, extracted content, preview - Add top margin to ToolCallGroup * chore: remove leftover .planning files * fix: polish FilePreviewDialog, CodeBlock, LangIcon, and Sources * fix: prevent keyboard focus on collapsed tool content Add inert attribute to all expand/collapse wrapper divs so collapsed content is removed from tab order and hidden from assistive technology. Skip disabled ProgressText buttons from tab order with tabIndex={-1}. * feat: integrate file metadata into file_search UI Pass fileType (MIME) and fileBytes from backend file records through to the frontend. Add file-type-specific icons, file size display, pages sorted by relevance, multi-snippet content per file, smart preview detection by MIME type, and copy button in file preview dialog. * fix: review fixes — inverted type check, wrong dimension, missing import, fail-open perms, timer leaks, dead code cleanup * fix: update CodeBlock styling for improved visual consistency * fix(chat): open composite file citations in preview * fix(chat): restore file previews for parsed search results * chore(git): ignore bg-shell artifacts * fix(chat): restore readable code content in light theme * style(chat): align code and output surfaces by theme * chore(i18n): remove 6 unused translation keys * fix(deps): replace private registry URL with public npm registry in lockfile * fix: CI lint, build, and test failures - Add missing scaleImage utility (fixes Vite build error) - Export scaleImage from utils/index.ts - Remove unused imports from Part.tsx (FunctionToolCall, CodeToolCall, Agents) - Fix prettier formatting in Part.tsx (multi-line → single-line imports, conditions) - Remove excess blank lines in Part.tsx - Remove unused CodeEditorRef import from Artifacts.tsx - Add useProgress mock to OpenAIImageGen.test.tsx - Add scaleImage mock to OpenAIImageGen.test.tsx - Update OpenAIImageGen tests to match redesigned component structure - Remove dead collapsible output panel tests from ImageGen.test.tsx - Add @icons-pack/react-simple-icons to Jest transformIgnorePatterns (ESM fix) * refactor: reorganize imports order across multiple components for consistency * fix: add scaleImage tests, delete dead ImageGen wrapper, wire up onUIAction in ToolCallInfo - Add 7 unit tests for scaleImage utility covering null ref, scaling, no-upscale, height clamping, landscape, and panoramic images - Delete unused Content/ImageGen.tsx re-export wrapper (ImageGen is imported from Parts/OpenAIImageGen via the Parts barrel) - Wire up onUIAction in ToolCallInfo to use handleUIAction + ask from useMessagesOperations, matching UIResourceCarousel's behavior (was previously a silent no-op) * refactor: optimize imports and enhance lazy loading for language icons * fix: address review findings for tool call UI redesign - Fix unstable array-index keys in ToolCallGroup (streaming state corruption) - Add plain-text fallback in InputRenderer for non-JSON tool args - Localize FRIENDLY_NAMES via translation keys instead of hardcoded English - Guard autoCollapse against user-initiated manual expansion - Fix CODE_INTERPRETER hasOutput to check actual outputs instead of hardcoding true - Add logger.warn for Citations fail-closed behavior on permission errors - Add Terminal icon to CodeAnalyze ProgressText for visual consistency - Fix getMCPServerName to use indexOf instead of fragile split - Use useLayoutEffect for inert attribute in useExpandCollapse (a11y) - Memoize style object in useExpandCollapse to avoid defeating React.memo - Memoize groupSequentialToolCalls in ContentParts to avoid recomputation - Use source.link as stable key instead of array index in WebSearch - Hoist rehypePlugins outside CodeMarkdown to prevent per-render recreation * fix: revert useMemo after conditional returns in ContentParts The useMemo placed after early returns violated React Rules of Hooks — hook call count would change when transitioning between edit/view mode. Reverted to the original plain forEach which is correct and equally performant since content changes on every streaming token anyway. * chore: remove unused com_ui_variables_info translation key * fix: update tests and jest config for ESM compatibility after rebase - Add ESM-only packages to transformIgnorePatterns (@dicebear, unified ecosystem, react-dnd, lowlight, etc.) to fix Jest parse failures introduced by dev rebase - Update ToolCall.test.tsx to match new component API (CSS expand/collapse instead of conditional rendering, simplified props) - Update ToolCallInfo.test.tsx to mock OutputRenderer (avoids ESM chain), align with current component interface (input/output/attachments) * refactor: replace @icons-pack/react-simple-icons with inline SVGs Inline the 51 Simple Icons SVG paths used by LangIcon directly into langIconPaths.ts, eliminating the runtime dependency on @icons-pack/react-simple-icons (which requires Node >= 24). - LangIcon now renders a plain <svg> with the path data instead of lazy-loading React components from the package - Removes Suspense/React.lazy overhead for code block language icons - SVG paths sourced from Simple Icons (CC0 1.0 license) - Package kept in package.json for now (will be removed separately) * fix: replace Plug icon with Wrench for MCP tools, remove unused i18n keys - MCP tools without a custom iconPath now show Wrench instead of Plug, matching the generic tool fallback and avoiding the "plugin" metaphor - Remove unused translation keys: com_assistants_action_attempt, com_assistants_attempt_info, com_assistants_domain_info, com_ui_ui_resources * fix: address second review findings - Combine 3x getToolMeta loop into single toolMetadata pass (ToolCallGroup) - Extract sortPagesByRelevance to shared util (was duplicated in FilePreviewDialog and RetrievalCall) - Deduplicate AGENT_STYLE_TOOLS Set (export from OpenAIImageGen/index.ts) - Localize "source/sources" in WebSearch aria-label - Add autoExpand useEffect to CodeAnalyze for live setting changes - Log download errors in FilePreviewDialog instead of silently swallowing - Replace @ts-ignore with @ts-expect-error + explanation in Code.tsx - Remove dead currentContent alias in CodeMarkdown * chore: remove @icons-pack/react-simple-icons dependency from package.json and package-lock.json - Deleted the @icons-pack/react-simple-icons entry from both package.json and package-lock.json, following the previous refactor to use inline SVGs for icons. * fix: address triage audit findings - Remove unused gIdx variable (ESLint error) - Fix singular/plural in web search sources aria-label - Separate inline type import in ToolCallGroup per AGENTS.md * fix: remove invalid placeholderDimensions prop from Image component * chore: import order * chore: import order * fix: resolve TypeScript errors in PR-touched files - Remove non-existent placeholderDimensions prop from Image in Files.tsx - Fix localize count param type (number, not string) in WebSearch.tsx - Pass full resource object instead of partial in UIResourceCarousel.tsx - Add 'as const' to toggleSwitchConfigs localizationKey in General.tsx - Fix SearchResultData type in Citation.test.tsx - Fix TAttachment and UIResource test fixture types across test files * docs: document formatBytes difference in FilePreviewDialog The local formatBytes returns a human-readable string with units ("1.5 MB"), while ~/utils/formatBytes returns a raw number. They serve different purposes, so the local copy is retained with a JSDoc comment explaining the distinction. * fix: address remaining review items - Replace cancelled IIFE with documented ternary in OpenAIImageGen, explaining the agent vs legacy path distinction - Add .catch() fallback to loadLowlight() in useLazyHighlight — falls back to plain text if the chunk fails to load - Fix import ordering in ToolCallGroup.tsx (type imports grouped before local value imports per AGENTS.md) * fix: blob URL leak and useGetFiles over-fetch - FilePreviewDialog: add cancelledRef guard to loadPreview so blob URLs are never created after the dialog closes (prevents orphaned object URLs on unmount during async PDF fetch) - RetrievalCall: filter useGetFiles by fileIds from fileSources instead of fetching the entire user file corpus for display-only name matching * chore: fix com_nav_auto_expand_tools alphabetical order in translation.json * fix: render non-object JSON params instead of returning null in InputRenderer * refactor: render JSON tool output as syntax-highlighted code block Replace the custom YAML-ish formatValue/formatObjectArray rendering with JSON.stringify + hljs language-json styling. Structured API responses (like GitHub search results) now display as proper syntax-highlighted JSON with indentation instead of a flat key-value text dump. - Remove formatValue, formatObjectArray, isUniformObjectArray helpers - Add isJson flag to extractText return type - JSON output rendered in <code class="hljs language-json"> block - Text content blocks (type: "text") still extracted and rendered as plain text - Error output unchanged * fix: extract cancelled IIFE to named function in OpenAIImageGen Replace nested ternary with a named computeCancelled() function that documents the agent vs legacy path branching. Resolves eslint no-nested-ternary warning. --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2026-03-25 12:31:39 -04:00
Danny Avila	87a3b8221a	🧹 chore: Consolidate getSoleOwnedResourceIds into data-schemas and use db object in PermissionService ... Move getSoleOwnedResourceIds from PermissionService to data-schemas aclEntry methods, update PermissionService to use the db object pattern instead of destructured imports from ~/models, and update UserController + tests accordingly.	2026-03-21 14:28:57 -04:00
Danny Avila	7829fa9eca	🪄 refactor: Simplify MCP Tool Content Formatting to Unified String Output (#12352) ... * refactor: Simplify content formatting in MCP service and parser - Consolidated content handling in `formatToolContent` to return a plain-text string instead of an array for all providers, enhancing clarity and consistency. - Removed unnecessary checks for content array providers, streamlining the logic for handling text and image artifacts. - Updated related tests to reflect changes in expected output format, ensuring comprehensive coverage for the new implementation. * fix: Return empty string for image-only tool responses instead of '(No response)' When artifacts exist (images/UI resources) but no text content is present, return an empty string rather than the misleading '(No response)' fallback. Adds missing test assertions for image-only content and standardizes length checks to explicit `> 0` comparisons.	2026-03-21 14:28:56 -04:00
Danny Avila	b5c097e5c7	⚗️ feat: Agent Context Compaction/Summarization (#12287) ... * chore: imports/types Add summarization config and package-level summarize handler contracts Register summarize handlers across server controller paths Port cursor dual-read/dual-write summary support and UI status handling Selectively merge cursor branch files for BaseClient summary content block detection (last-summary-wins), dual-write persistence, summary block unit tests, and on_summarize_status SSE event handling with started/completed/failed branches. Co-authored-by: Cursor <cursoragent@cursor.com> refactor: type safety feat: add localization for summarization status messages refactor: optimize summary block detection in BaseClient Updated the logic for identifying existing summary content blocks to use a reverse loop for improved efficiency. Added a new test case to ensure the last summary content block is updated correctly when multiple summary blocks exist. chore: add runName to chainOptions in AgentClient refactor: streamline summarization configuration and handler integration Removed the deprecated summarizeNotConfigured function and replaced it with a more flexible createSummarizeFn. Updated the summarization handler setup across various controllers to utilize the new function, enhancing error handling and configuration resolution. Improved overall code clarity and maintainability by consolidating summarization logic. feat(summarization): add staged chunk-and-merge fallback feat(usage): track summarization usage separately from messages feat(summarization): resolve prompt from config in runtime fix(endpoints): use @librechat/api provider config loader refactor(agents): import getProviderConfig from @librechat/api chore: code order feat(app-config): auto-enable summarization when configured feat: summarization config refactor(summarization): streamline persist summary handling and enhance configuration validation Removed the deprecated createDeferredPersistSummary function and integrated a new createPersistSummary function for MongoDB persistence. Updated summarization handlers across various controllers to utilize the new persistence method. Enhanced validation for summarization configuration to ensure provider, model, and prompt are properly set, improving error handling and overall robustness. refactor(summarization): update event handling and remove legacy summarize handlers Replaced the deprecated summarization handlers with new event-driven handlers for summarization start and completion across multiple controllers. This change enhances the clarity of the summarization process and improves the integration of summarization events in the application. Additionally, removed unused summarization functions and streamlined the configuration loading process. refactor(summarization): standardize event names in handlers Updated event names in the summarization handlers to use constants from GraphEvents for consistency and clarity. This change improves maintainability and reduces the risk of errors related to string literals in event handling. feat(summarization): enhance usage tracking for summarization events Added logic to track summarization usage in multiple controllers by checking the current node type. If the node indicates a summarization task, the usage type is set accordingly. This change improves the granularity of usage data collected during summarization processes. feat(summarization): integrate SummarizationConfig into AppSummarizationConfig type Enhanced the AppSummarizationConfig type by extending it with the SummarizationConfig type from librechat-data-provider. This change improves type safety and consistency in the summarization configuration structure. test: add end-to-end tests for summarization functionality Introduced a comprehensive suite of end-to-end tests for the summarization feature, covering the full LibreChat pipeline from message creation to summarization. This includes a new setup file for environment configuration and a Jest configuration specifically for E2E tests. The tests utilize real API keys and ensure proper integration with the summarization process, enhancing overall test coverage and reliability. refactor(summarization): include initial summary in formatAgentMessages output Updated the formatAgentMessages function to return an initial summary alongside messages and index token count map. This change is reflected in multiple controllers and the corresponding tests, enhancing the summarization process by providing additional context for each agent's response. refactor: move hydrateMissingIndexTokenCounts to tokenMap utility Extracted the hydrateMissingIndexTokenCounts function from the AgentClient and related tests into a new tokenMap utility file. This change improves code organization and reusability, allowing for better management of token counting logic across the application. refactor(summarization): standardize step event handling and improve summary rendering Refactored the step event handling in the useStepHandler and related components to utilize constants for event names, enhancing consistency and maintainability. Additionally, improved the rendering logic in the Summary component to conditionally display the summary text based on its availability, providing a better user experience during the summarization process. feat(summarization): introduce baseContextTokens and reserveTokensRatio for improved context management Added baseContextTokens to the InitializedAgent type to calculate the context budget based on agentMaxContextNum and maxOutputTokensNum. Implemented reserveTokensRatio in the createRun function to allow configurable context token management. Updated related tests to validate these changes and ensure proper functionality. feat(summarization): add minReserveTokens, context pruning, and overflow recovery configurations Introduced new configuration options for summarization, including minReserveTokens, context pruning settings, and overflow recovery parameters. Updated the createRun function to accommodate these new options and added a comprehensive test suite to validate their functionality and integration within the summarization process. feat(summarization): add updatePrompt and reserveTokensRatio to summarization configuration Introduced an updatePrompt field for updating existing summaries with new messages, enhancing the flexibility of the summarization process. Additionally, added reserveTokensRatio to the configuration schema, allowing for improved management of token allocation during summarization. Updated related tests to validate these new features. feat(logging): add on_agent_log event handler for structured logging Implemented an on_agent_log event handler in both the agents' callbacks and responses to facilitate structured logging of agent activities. This enhancement allows for better tracking and debugging of agent interactions by logging messages with associated metadata. Updated the summarization process to ensure proper handling of log events. fix: remove duplicate IBalanceUpdate interface declaration perf(usage): single-pass partition of collectedUsage Replace two Array.filter() passes with a single for-of loop that partitions message vs. summarization usages in one iteration. fix(BaseClient): shallow-copy message content before mutating and preserve string content Avoid mutating the original message.content array in-place when appending a summary block. Also convert string content to a text content part instead of silently discarding it. fix(ui): fix Part.tsx indentation and useStepHandler summarize-complete handling - Fix SUMMARY else-if branch indentation in Part.tsx to match chain level - Guard ON_SUMMARIZE_COMPLETE with didFinalize flag to avoid unnecessary re-renders when no summarizing parts exist - Protect against undefined completeData.summary instead of unsafe spread fix(agents): use strict enabled check for summarization handlers Change summarizationConfig?.enabled !== false to === true so handlers are not registered when summarizationConfig is undefined. chore: fix initializeClient JSDoc and move DEFAULT_RESERVE_RATIO to module scope refactor(Summary): align collapse/expand behavior with Reasoning component - Single render path instead of separate streaming vs completed branches - Use useMessageContext for isSubmitting/isLatestMessage awareness so the "Summarizing..." label only shows during active streaming - Default to collapsed (matching Reasoning), user toggles to expand - Add proper aria attributes (aria-hidden, role, aria-controls, contentId) - Hide copy button while actively streaming feat(summarization): default to self-summarize using agent's own provider/model When no summarization config is provided (neither in librechat.yaml nor on the agent), automatically enable summarization using the agent's own provider and model. The agents package already provides default prompts, so no prompt configuration is needed. Also removes the dead resolveSummarizationLLMConfig in summarize.ts (and its spec) — run.ts buildAgentContext is the single source of truth for summarization config resolution. Removes the duplicate RuntimeSummarizationConfig local type in favor of the canonical SummarizationConfig from data-provider. chore: schema and type cleanup for summarization - Add trigger field to summarizationAgentOverrideSchema so per-agent trigger overrides in librechat.yaml are not silently stripped by Zod - Remove unused SummarizationStatus type from runs.ts - Make AppSummarizationConfig.enabled non-optional to reflect the invariant that loadSummarizationConfig always sets it refactor(responses): extract duplicated on_agent_log handler refactor(run): use agents package types for summarization config Import SummarizationConfig, ContextPruningConfig, and OverflowRecoveryConfig from @librechat/agents and use them to type-check the translation layer in buildAgentContext. This ensures the config object passed to the agent graph matches what it expects. - Use `satisfies AgentSummarizationConfig` on the config object - Cast contextPruningConfig and overflowRecoveryConfig to agents types - Properly narrow trigger fields from DeepPartial to required shape feat(config): add maxToolResultChars to base endpoint schema Add maxToolResultChars to baseEndpointSchema so it can be configured on any endpoint in librechat.yaml. Resolved during agent initialization using getProviderConfig's endpoint resolution: custom endpoint config takes precedence, then the provider-specific endpoint config, then the shared `all` config. Passed through to the agents package ToolNode, which uses it to cap tool result length before it enters the context window. When not configured, the agents package computes a sensible default from maxContextTokens. fix(summarization): forward agent model_parameters in self-summarize default When no explicit summarization config exists, the self-summarize default now forwards the agent's model_parameters as the summarization parameters. This ensures provider-specific settings (e.g. Bedrock region, credentials, endpoint host) are available when the agents package constructs the summarization LLM. fix(agents): register summarization handlers by default Change the enabled gate from === true to !== false so handlers register when no explicit summarization config exists. This aligns with the self-summarize default where summarization is always on unless explicitly disabled via enabled: false. refactor(summarization): let agents package inherit clientOptions for self-summarize Remove model_parameters forwarding from the self-summarize default. The agents package now reuses the agent's own clientOptions when the summarization provider matches the agent's provider, inheriting all provider-specific settings (region, credentials, proxy, etc.) automatically. refactor(summarization): use MessageContentComplex[] for summary content Unify summary content to always use MessageContentComplex[] arrays, matching the pattern used by on_message_delta. No more string | array unions — content is always an array of typed blocks ({ type: 'text', text: '...' } for text, { type: 'reasoning_content', ... } for reasoning). Agents package: - SummaryContentBlock.content: MessageContentComplex[] (was string) - tokenCount now optional (not sent on deltas) - Removed reasoning field — reasoning is now a content block type - streamAndCollect normalizes all chunks to content block arrays - Delta events pass content blocks directly LibreChat: - SummaryContentPart.content: Agents.MessageContentComplex[] - Updated Part.tsx, Summary.tsx, useStepHandler.ts, BaseClient.js - Summary.tsx derives display text from content blocks via useMemo - Aggregator uses simple array spread refactor(summarization): enhance summary handling and text extraction - Updated BaseClient.js to improve summary text extraction, accommodating both legacy and new content formats. - Modified summarization logic to ensure consistent handling of summary content across different message formats. - Adjusted test cases in summarization.e2e.spec.js to utilize the new summary text extraction method. - Refined SSE useStepHandler to initialize summary content as an array. - Updated configuration schema by removing unused minReserveTokens field. - Cleaned up SummaryContentPart type by removing rangeHash property. These changes streamline the summarization process and ensure compatibility with various content structures. refactor(summarization): streamline usage tracking and logging - Removed direct checks for summarization nodes in ModelEndHandler and replaced them with a dedicated markSummarizationUsage function for better readability and maintainability. - Updated OpenAIChatCompletionController and responses handlers to utilize the new markSummarizationUsage function for setting usage types. - Enhanced logging functionality by ensuring the logger correctly handles different log levels. - Introduced a new useCopyToClipboard hook in the Summary component to encapsulate clipboard copy logic, improving code reusability and clarity. These changes improve the overall structure and efficiency of the summarization handling and logging processes. refactor(summarization): update summary content block documentation - Removed outdated comment regarding the last summary content block in BaseClient.js. - Added a new comment to clarify the purpose of the findSummaryContentBlock method, ensuring consistency in documentation. These changes enhance code clarity and maintainability by providing accurate descriptions of the summarization logic. refactor(summarization): update summary content structure in tests - Modified the summarization content structure in e2e tests to use an array format for text, aligning with recent changes in summary handling. - Updated test descriptions to clarify the behavior of context token calculations, ensuring consistency and clarity in the tests. These changes enhance the accuracy and maintainability of the summarization tests by reflecting the updated content structure. refactor(summarization): remove legacy E2E test setup and configuration - Deleted the e2e-setup.js and jest.e2e.config.js files, which contained legacy configurations for E2E tests using real API keys. - Introduced a new summarization.e2e.ts file that implements comprehensive E2E backend integration tests for the summarization process, utilizing real AI providers and tracking summaries throughout the run. These changes streamline the testing framework by consolidating E2E tests into a single, more robust file while removing outdated configurations. refactor(summarization): enhance E2E tests and error handling - Added a cleanup step to force exit after all tests to manage Redis connections. - Updated the summarization model to 'claude-haiku-4-5-20251001' for consistency across tests. - Improved error handling in the processStream function to capture and return processing errors. - Enhanced logging for cross-run tests and tight context scenarios to provide better insights into test execution. These changes improve the reliability and clarity of the E2E tests for the summarization process. refactor(summarization): enhance test coverage for maxContextTokens behavior - Updated run-summarization.test.ts to include a new test case ensuring that maxContextTokens does not exceed user-defined limits, even when calculated ratios suggest otherwise. - Modified summarization.e2e.ts to replace legacy UsageMetadata type with a more appropriate type for collectedUsage, improving type safety and clarity in the test setup. These changes improve the robustness of the summarization tests by validating context token constraints and refining type definitions. feat(summarization): add comprehensive E2E tests for summarization process - Introduced a new summarization.e2e.test.ts file that implements extensive end-to-end integration tests for the summarization pipeline, covering the full flow from LibreChat to agents. - The tests utilize real AI providers and include functionality to track summaries during and between runs. - Added necessary cleanup steps to manage Redis connections post-tests and ensure proper exit. These changes enhance the testing framework by providing robust coverage for the summarization process, ensuring reliability and performance under real-world conditions. fix(service): import logger from winston configuration - Removed the import statement for logger from '@librechat/data-schemas' and replaced it with an import from '~/config/winston'. - This change ensures that the logger is correctly sourced from the updated configuration, improving consistency in logging practices across the application. refactor(summary): simplify Summary component and enhance token display - Removed the unused `meta` prop from the `SummaryButton` component to streamline its interface. - Updated the token display logic to use a localized string for better internationalization support. - Adjusted the rendering of the `meta` information to improve its visibility within the `Summary` component. These changes enhance the clarity and usability of the Summary component while ensuring better localization practices. feat(summarization): add maxInputTokens configuration for summarization - Introduced a new `maxInputTokens` property in the summarization configuration schema to control the amount of conversation context sent to the summarizer, with a default value of 10000. - Updated the `createRun` function to utilize the new `maxInputTokens` setting, allowing for more flexible summarization based on agent context. These changes enhance the summarization capabilities by providing better control over input token limits, improving the overall summarization process. refactor(summarization): simplify maxInputTokens logic in createRun function - Updated the logic for the `maxInputTokens` property in the `createRun` function to directly use the agent's base context tokens when the resolved summarization configuration does not specify a value. - This change streamlines the configuration process and enhances clarity in how input token limits are determined for summarization. These modifications improve the maintainability of the summarization configuration by reducing complexity in the token calculation logic. feat(summary): enhance Summary component to display meta information - Updated the SummaryContent component to accept an optional `meta` prop, allowing for additional contextual information to be displayed above the main content. - Adjusted the rendering logic in the Summary component to utilize the new `meta` prop, improving the visibility of supplementary details. These changes enhance the user experience by providing more context within the Summary component, making it clearer and more informative. refactor(summarization): standardize reserveRatio configuration in summarization logic - Replaced instances of `reserveTokensRatio` with `reserveRatio` in the `createRun` function and related tests to unify the terminology across the codebase. - Updated the summarization configuration schema to reflect this change, ensuring consistency in how the reserve ratio is defined and utilized. - Removed the per-agent override logic for summarization configuration, simplifying the overall structure and enhancing clarity. These modifications improve the maintainability and readability of the summarization logic by standardizing the configuration parameters. * fix: circular dependency of `~/models` * chore: update logging scope in agent log handlers Changed log scope from `[agentus:${data.scope}]` to `[agents:${data.scope}]` in both the callbacks and responses controllers to ensure consistent logging format across the application. * feat: calibration ratio * refactor(tests): update summarizationConfig tests to reflect changes in enabled property Modified tests to check for the new `summarizationEnabled` property instead of the deprecated `enabled` field in the summarization configuration. This change ensures that the tests accurately validate the current configuration structure and behavior of the agents. * feat(tests): add markSummarizationUsage mock for improved test coverage Introduced a mock for the markSummarizationUsage function in the responses unit tests to enhance the testing of summarization usage tracking. This addition supports better validation of summarization-related functionalities and ensures comprehensive test coverage for the agents' response handling. * refactor(tests): simplify event handler setup in createResponse tests Removed redundant mock implementations for event handlers in the createResponse unit tests, streamlining the setup process. This change enhances test clarity and maintainability while ensuring that the tests continue to validate the correct behavior of usage tracking during on_chat_model_end events. * refactor(agents): move calibration ratio capture to finally block Reorganized the logic for capturing the calibration ratio in the AgentClient class to ensure it is executed in the finally block. This change guarantees that the ratio is captured even if the run is aborted, enhancing the reliability of the response message persistence. Removed redundant code and improved clarity in the handling of context metadata. * refactor(agents): streamline bulk write logic in recordCollectedUsage function Removed redundant bulk write operations and consolidated document handling in the recordCollectedUsage function. The logic now combines all documents into a single bulk write operation, improving efficiency and reducing error handling complexity. Updated logging to provide consistent error messages for bulk write failures. * refactor(agents): enhance summarization configuration resolution in createRun function Streamlined the summarization configuration logic by introducing a base configuration and allowing for overrides from agent-specific settings. This change improves clarity and maintainability, ensuring that the summarization configuration is consistently applied while retaining flexibility for customization. Updated the handling of summarization parameters to ensure proper integration with the agent's model and provider settings. * refactor(agents): remove unused tokenCountMap and streamline calibration ratio handling Eliminated the unused tokenCountMap variable from the AgentClient class to enhance code clarity. Additionally, streamlined the logic for capturing the calibration ratio by using optional chaining and a fallback value, ensuring that context metadata is consistently defined. This change improves maintainability and reduces potential confusion in the codebase. * refactor(agents): extract agent log handler for improved clarity and reusability Refactored the agent log handling logic by extracting it into a dedicated function, `agentLogHandler`, enhancing code clarity and reusability across different modules. Updated the event handlers in both the OpenAI and responses controllers to utilize the new handler, ensuring consistent logging behavior throughout the application. * test: add summarization event tests for useStepHandler Implemented a series of tests for the summarization events in the useStepHandler hook. The tests cover scenarios for ON_SUMMARIZE_START, ON_SUMMARIZE_DELTA, and ON_SUMMARIZE_COMPLETE events, ensuring proper handling of summarization logic, including message accumulation and finalization. This addition enhances test coverage and validates the correct behavior of the summarization process within the application. * refactor(config): update summarizationTriggerSchema to use enum for type validation Changed the type of the `type` field in the summarizationTriggerSchema from a string to an enum with a single value 'token_count'. This modification enhances type safety and ensures that only valid types are accepted in the configuration, improving overall clarity and maintainability of the schema. * test(usage): add bulk write tests for message and summarization usage Implemented tests for the bulk write functionality in the recordCollectedUsage function, covering scenarios for combined message and summarization usage, summarization-only usage, and message-only usage. These tests ensure correct document handling and token rollup calculations, enhancing test coverage and validating the behavior of the usage tracking logic. * refactor(Chat): enhance clipboard copy functionality and type definitions in Summary component Updated the Summary component to improve the clipboard copy functionality by handling clipboard permission errors. Refactored type definitions for SummaryProps to use a more specific type, enhancing type safety. Adjusted the SummaryButton and FloatingSummaryBar components to accept isCopied and onCopy props, promoting better separation of concerns and reusability. * chore(translations): remove unused "Expand Summary" key from English translations Deleted the "Expand Summary" key from the English translation file to streamline the localization resources and improve clarity in the user interface. This change helps maintain an organized and efficient translation structure. * refactor: adjust token counting for Claude model to account for API discrepancies Implemented a correction factor for token counting when using the Claude model, addressing discrepancies between Anthropic's API and local tokenizer results. This change ensures accurate token counts by applying a scaling factor, improving the reliability of token-related functionalities. * refactor(agents): implement token count adjustment for Claude model messages Added a method to adjust token counts for messages processed by the Claude model, applying a correction factor to align with API expectations. This enhancement improves the accuracy of token counting, ensuring reliable functionality when interacting with the Claude model. * refactor(agents): token counting for media content in messages Introduced a new method to estimate token costs for image and document blocks in messages, improving the accuracy of token counting. This enhancement ensures that media content is properly accounted for, particularly for the Claude model, by integrating additional token estimation logic for various content types. Updated the token counting function to utilize this new method, enhancing overall reliability and functionality. * chore: fix missing import * fix(agents): clamp baseContextTokens and document reserve ratio change Prevent negative baseContextTokens when maxOutputTokens exceeds the context window (misconfigured models). Document the 10%→5% default reserve ratio reduction introduced alongside summarization. * fix(agents): include media tokens in hydrated token counts Add estimateMediaTokensForMessage to createTokenCounter so the hydration path (used by hydrateMissingIndexTokenCounts) matches the precomputed path in AgentClient.getTokenCountForMessage. Without this, messages containing images or documents were systematically undercounted during hydration, risking context window overflow. Add 34 unit tests covering all block-type branches of estimateMediaTokensForMessage. * fix(agents): include summarization output tokens in usage return value The returned output_tokens from recordCollectedUsage now reflects all billed LLM calls (message + summarization). Previously, summarization completions were billed but excluded from the returned metadata, causing a discrepancy between what users were charged and what the response message reported. * fix(tests): replace process.exit with proper Redis cleanup in e2e test The summarization E2E test used process.exit(0) to work around a Redis connection opened at import time, which killed the Jest runner and bypassed teardown. Use ioredisClient.quit() and keyvRedisClient.disconnect() for graceful cleanup instead. * fix(tests): update getConvo imports in OpenAI and response tests Refactor test files to import getConvo from the main models module instead of the Conversation submodule. This change ensures consistency across tests and simplifies the import structure, enhancing maintainability. * fix(clients): improve summary text validation in BaseClient Refactor the summary extraction logic to ensure that only non-empty summary texts are considered valid. This change enhances the robustness of the message processing by utilizing a dedicated method for summary text retrieval, improving overall reliability. * fix(config): replace z.any() with explicit union in summarization schema Model parameters (temperature, top_p, etc.) are constrained to primitive types rather than the policy-violating z.any(). * refactor(agents): deduplicate CLAUDE_TOKEN_CORRECTION constant Export from the TS source in packages/api and import in the JS client, eliminating the static class property that could drift out of sync. * refactor(agents): eliminate duplicate selfProvider in buildAgentContext selfProvider and provider were derived from the same expression with different type casts. Consolidated to a single provider variable. * refactor(agents): extract shared SSE handlers and restrict log levels - buildSummarizationHandlers() factory replaces triplicated handler blocks across responses.js and openai.js - agentLogHandlerObj exported from callbacks.js for consistent reuse - agentLogHandler restricted to an allowlist of safe log levels (debug, info, warn, error) instead of accepting arbitrary strings * fix(SSE): batch summarize deltas, add exhaustiveness check, conditional error announcement - ON_SUMMARIZE_DELTA coalesces rapid-fire renders via requestAnimationFrame instead of calling setMessages per chunk - Exhaustive never-check on TStepEvent catches unhandled variants at compile time when new StepEvents are added - ON_SUMMARIZE_COMPLETE error announcement only fires when a summary part was actually present and removed * feat(agents): persist instruction overhead in contextMeta and seed across runs Extend contextMeta with instructionOverhead and toolCount so the provider-observed instruction overhead is persisted on the response message and seeded into the pruner on subsequent runs. This enables the pruner to use a calibrated budget from the first call instead of waiting for a provider observation, preventing the ratio collapse caused by local tokenizer overestimating tool schema tokens. The seeded overhead is only used when encoding and tool count match between runs, ensuring stale values from different configurations are discarded. * test(agents): enhance OpenAI test mocks for summarization handlers Updated the OpenAI test suite to include additional mock implementations for summarization handlers, including buildSummarizationHandlers, markSummarizationUsage, and agentLogHandlerObj. This improves test coverage and ensures consistent behavior during testing. * fix(agents): address review findings for summarization v2 Cancel rAF on unmount to prevent stale Recoil writes from dead component context. Clear orphaned summarizing:true parts when ON_SUMMARIZE_COMPLETE arrives without a summary payload. Add null guard and safe spread to agentLogHandler. Handle Anthropic-format base64 image/* documents in estimateMediaTokensForMessage. Use role="region" for expandable summary content. Add .describe() to contextMeta Zod fields. Extract duplicate usage loop into helper. * refactor: simplify contextMeta to calibrationRatio + encoding only Remove instructionOverhead and toolCount from cross-run persistence — instruction tokens change too frequently between runs (prompt edits, tool changes) for a persisted seed to be reliable. The intra-run calibration in the pruner still self-corrects via provider observations. contextMeta now stores only the tokenizer-bias ratio and encoding, which are stable across instruction changes. * test(SSE): enhance useStepHandler tests for ON_SUMMARIZE_COMPLETE behavior Updated the test for ON_SUMMARIZE_COMPLETE to clarify that it finalizes the existing part with summarizing set to false when the summary is undefined. Added assertions to verify the correct behavior of message updates and the state of summary parts. * refactor(BaseClient): remove handleContextStrategy and truncateToolCallOutputs functions Eliminated the handleContextStrategy method from BaseClient to streamline message handling. Also removed the truncateToolCallOutputs function from the prompts module, simplifying the codebase and improving maintainability. * refactor: add AGENT_DEBUG_LOGGING option and refactor token count handling in BaseClient Introduced AGENT_DEBUG_LOGGING to .env.example for enhanced debugging capabilities. Refactored token count handling in BaseClient by removing the handleTokenCountMap method and simplifying token count updates. Updated AgentClient to log detailed token count recalculations and adjustments, improving traceability during message processing. * chore: update dependencies in package-lock.json and package.json files Bumped versions of several dependencies, including @librechat/agents to ^3.1.62 and various AWS SDK packages to their latest versions. This ensures compatibility and incorporates the latest features and fixes. * chore: imports order * refactor: extract summarization config resolution from buildAgentContext * refactor: rename and simplify summarization configuration shaping function * refactor: replace AgentClient token counting methods with single-pass pure utility Extract getTokenCount() and getTokenCountForMessage() from AgentClient into countFormattedMessageTokens(), a pure function in packages/api that handles text, tool_call, image, and document content types in one loop. - Decompose estimateMediaTokensForMessage into block-level helpers (estimateImageDataTokens, estimateImageBlockTokens, estimateDocumentBlockTokens) shared by both estimateMediaTokensForMessage and the new single-pass function - Remove redundant per-call getEncoding() resolution (closure captures once) - Remove deprecated gpt-3.5-turbo-0301 model branching - Drop this.getTokenCount guard from BaseClient.sendMessage * refactor: streamline token counting in createTokenCounter function Simplified the createTokenCounter function by removing the media token estimation and directly calculating the token count. This change enhances clarity and performance by consolidating the token counting logic into a single pass, while maintaining compatibility with Claude's token correction. * refactor: simplify summarization configuration types Removed the AppSummarizationConfig type and directly used SummarizationConfig in the AppConfig interface. This change streamlines the type definitions and enhances consistency across the codebase. * chore: import order * fix: summarization event handling in useStepHandler - Cancel pending summarizeDeltaRaf in clearStepMaps to prevent stale frames firing after map reset or component unmount - Move announcePolite('summarize_completed') inside the didFinalize guard so screen readers only announce when finalization actually occurs - Remove dead cleanup closure returned from stepHandler useCallback body that was never invoked by any caller * fix: estimate tokens for non-PDF/non-image base64 document blocks Previously estimateDocumentBlockTokens returned 0 for unrecognized MIME types (e.g. text/plain, application/json), silently underestimating context budget. Fall back to character-based heuristic or countTokens. * refactor: return cloned usage from markSummarizationUsage Avoid mutating LangChain's internal usage_metadata object by returning a shallow clone with the usage_type tag. Update all call sites in callbacks, openai, and responses controllers to use the returned value. * refactor: consolidate debug logging loops in buildMessages Merge the two sequential O(n) debug-logging passes over orderedMessages into a single pass inside the map callback where all data is available. * refactor: narrow SummaryContentPart.content type Replace broad Agents.MessageContentComplex[] with the specific Array<{ type: ContentTypes.TEXT; text: string }> that all producers and consumers already use, improving compile-time safety. * refactor: use single output array in recordCollectedUsage Have processUsageGroup append to a shared array instead of returning separate arrays that are spread into a third, reducing allocations. * refactor: use for...in in hydrateMissingIndexTokenCounts Replace Object.entries with for...in to avoid allocating an intermediate tuple array during token map hydration.	2026-03-21 14:28:56 -04:00
Danny Avila	dd72b7b17e	🔄 chore: Consolidate agent model imports across middleware and tests from rebase ... - Updated imports for `createAgent` and `getAgent` to streamline access from a unified `~/models` path. - Enhanced test files to reflect the new import structure, ensuring consistency and maintainability across the codebase. - Improved clarity by removing redundant imports and aligning with the latest model updates.	2026-03-21 14:28:55 -04:00
Atef Bellaaj	a0fed6173c	🗂️ refactor: Migrate S3 Storage to TypeScript in packages/api (#11947) ... * Migrate S3 storage module with unit and integration tests - Migrate S3 CRUD and image operations to packages/api/src/storage/s3/ - Add S3ImageService class with dependency injection - Add unit tests using aws-sdk-client-mock - Add integration tests with real s3 bucket (condition presence of AWS_TEST_BUCKET_NAME) * AI Review Findings Fixes * chore: tests and refactor S3 storage types - Added mock implementations for the 'sharp' library in various test files to improve image processing testing. - Updated type references in S3 storage files from MongoFile to TFile for consistency and type safety. - Refactored S3 CRUD operations to ensure proper handling of file types and improve code clarity. - Enhanced integration tests to validate S3 file operations and error handling more effectively. * chore: rename test file * Remove duplicate import of refreshS3Url * chore: imports order * fix: remove duplicate imports for S3 URL handling in UserController * fix: remove duplicate import of refreshS3FileUrls in files.js * test: Add mock implementations for 'sharp' and '@librechat/api' in UserController tests - Introduced mock functions for the 'sharp' library to facilitate image processing tests, including metadata retrieval and buffer conversion. - Enhanced mocking for '@librechat/api' to ensure consistent behavior in tests, particularly for the needsRefresh and getNewS3URL functions. --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2026-03-21 14:28:55 -04:00
Danny Avila	9e0592a236	📜 feat: Implement System Grants for Capability-Based Authorization (#11896) ... * feat: Implement System Grants for Role-Based Capabilities - Added a new `systemGrant` model and associated methods to manage role-based capabilities within the application. - Introduced middleware functions `hasCapability` and `requireCapability` to check user permissions based on their roles. - Updated the database seeding process to include system grants for the ADMIN role, ensuring all necessary capabilities are assigned on startup. - Enhanced type definitions and schemas to support the new system grant functionality, improving overall type safety and clarity in the codebase. * test: Add unit tests for capabilities middleware and system grant methods - Introduced comprehensive unit tests for the capabilities middleware, including `hasCapability` and `requireCapability`, ensuring proper permission checks based on user roles. - Added tests for the `SystemGrant` methods, verifying the seeding of system grants, capability granting, and revocation processes. - Enhanced test coverage for edge cases, including idempotency of grant operations and handling of unexpected errors in middleware. - Utilized mocks for database interactions to isolate tests and improve reliability. * refactor: Transition to Capability-Based Access Control - Replaced role-based access checks with capability-based checks across various middleware and routes, enhancing permission management. - Introduced `hasCapability` and `requireCapability` functions to streamline capability verification for user actions. - Updated relevant routes and middleware to utilize the new capability system, ensuring consistent permission enforcement. - Enhanced type definitions and added tests for the new capability functions, improving overall code reliability and maintainability. * test: Enhance capability-based access tests for ADMIN role - Updated tests to reflect the new capability-based access control, specifically for the ADMIN role. - Modified test descriptions to clarify that users with the MANAGE_AGENTS capability can bypass permission checks. - Seeded capabilities for the ADMIN role in multiple test files to ensure consistent permission checks across different routes and middleware. - Improved overall test coverage for capability verification, ensuring robust permission management. * test: Update capability tests for MCP server access - Renamed test to reflect the correct capability for bypassing permission checks, changing from MANAGE_AGENTS to MANAGE_MCP_SERVERS. - Updated seeding of capabilities for the ADMIN role to align with the new capability structure. - Ensured consistency in capability definitions across tests and middleware for improved permission management. * feat: Add hasConfigCapability for enhanced config access control - Introduced `hasConfigCapability` function to check user permissions for managing or reading specific config sections. - Updated middleware to export the new capability function, ensuring consistent access control across the application. - Enhanced unit tests to cover various scenarios for the new capability, improving overall test coverage and reliability. * fix: Update tenantId filter in createSystemGrantMethods - Added a condition to set tenantId filter to { $exists: false } when tenantId is null, ensuring proper handling of cases where tenantId is not provided. - This change improves the robustness of the system grant methods by explicitly managing the absence of tenantId in the filter logic. * fix: account deletion capability check - Updated the `canDeleteAccount` middleware to ensure that the `hasManageUsers` capability check only occurs if a user is present, preventing potential errors when the user object is undefined. - This change improves the robustness of the account deletion logic by ensuring proper handling of user permissions. * refactor: Optimize seeding of system grants for ADMIN role - Replaced sequential capability granting with parallel execution using Promise.all in the seedSystemGrants function. - This change improves performance and efficiency during the initialization of system grants, ensuring all capabilities are granted concurrently. * refactor: Simplify systemGrantSchema index definition - Removed the sparse option from the unique index on principalType, principalId, capability, and tenantId in the systemGrantSchema. - This change streamlines the index definition, potentially improving query performance and clarity in the schema design. * refactor: Reorganize role capability check in roles route - Moved the capability check for reading roles to occur after parsing the roleName, improving code clarity and structure. - This change ensures that the authorization logic is consistently applied before fetching role details, enhancing overall permission management. * refactor: Remove unused ISystemGrant interface from systemCapabilities.ts - Deleted the ISystemGrant interface as it was no longer needed, streamlining the code and improving clarity. - This change helps reduce clutter in the file and focuses on relevant capabilities for the system. * refactor: Migrate SystemCapabilities to data-schemas - Replaced imports of SystemCapabilities from 'librechat-data-provider' with imports from '@librechat/data-schemas' across multiple files. - This change centralizes the management of system capabilities, improving code organization and maintainability. * refactor: Update account deletion middleware and capability checks - Modified the `canDeleteAccount` middleware to ensure that the account deletion permission is only granted to users with the `MANAGE_USERS` capability, improving security and clarity in permission management. - Enhanced error logging for unauthorized account deletion attempts, providing better insights into permission issues. - Updated the `capabilities.ts` file to ensure consistent handling of user authentication checks, improving robustness in capability verification. - Refined type definitions in `systemGrant.ts` and `systemGrantMethods.ts` to utilize the `PrincipalType` enum, enhancing type safety and code clarity. * refactor: Extract principal ID normalization into a separate function - Introduced `normalizePrincipalId` function to streamline the normalization of principal IDs based on their type, enhancing code clarity and reusability. - Updated references in `createSystemGrantMethods` to utilize the new normalization function, improving maintainability and reducing code duplication. * test: Add unit tests for principalId normalization in systemGrant - Introduced tests for the `grantCapability`, `revokeCapability`, and `getCapabilitiesForPrincipal` methods to verify correct handling of principalId normalization between string and ObjectId formats. - Enhanced the `capabilities.ts` middleware to utilize the `PrincipalType` enum for improved type safety. - Added a new utility function `normalizePrincipalId` to streamline principal ID normalization logic, ensuring consistent behavior across the application. * feat: Introduce capability implications and enhance system grant methods - Added `CapabilityImplications` to define relationships between broader and implied capabilities, allowing for more intuitive permission checks. - Updated `createSystemGrantMethods` to expand capability queries to include implied capabilities, improving authorization logic. - Enhanced `systemGrantSchema` to include an `expiresAt` field for future TTL enforcement of grants, and added validation to ensure `tenantId` is not set to null. - Documented authorization requirements for prompt group and prompt deletion methods to clarify access control expectations. * test: Add unit tests for canDeleteAccount middleware - Introduced unit tests for the `canDeleteAccount` middleware to verify account deletion permissions based on user roles and capabilities. - Covered scenarios for both allowed and blocked account deletions, including checks for ADMIN users with the `MANAGE_USERS` capability and handling of undefined user cases. - Enhanced test structure to ensure clarity and maintainability of permission checks in the middleware. * fix: Add principalType enum validation to SystemGrant schema Without enum validation, any string value was accepted for principalType and silently stored. Invalid documents would never match capability queries, creating phantom grants impossible to diagnose without raw DB inspection. All other ACL models in the codebase validate this field. * fix: Replace seedSystemGrants Promise.all with bulkWrite for concurrency safety When two server instances start simultaneously (K8s rolling deploy, PM2 cluster), both call seedSystemGrants. With Promise.all + findOneAndUpdate upsert, both instances may attempt to insert the same documents, causing E11000 duplicate key errors that crash server startup. bulkWrite with ordered:false handles concurrent upserts gracefully and reduces 17 individual round trips to a single network call. The returned documents (previously discarded) are no longer fetched. * perf: Add AsyncLocalStorage per-request cache for capability checks Every hasCapability call previously required 2 DB round trips (getUserPrincipals + SystemGrant.exists) — replacing what were O(1) string comparisons. Routes like patchPromptGroup triggered this twice, and hasConfigCapability's fallback path resolved principals twice. This adds a per-request AsyncLocalStorage cache that: - Caches resolved principals (same for all checks within one request) - Caches capability check results (same user+cap = same answer) - Automatically scoped to request lifetime (no stale grants) - Falls through to DB when no store exists (background jobs, tests) - Requires no signature changes to hasCapability The capabilityContextMiddleware is registered at the app level before all routes, initializing a fresh store per request. * fix: Add error handling for inline hasCapability calls canDeleteAccount, fetchAssistants, and validateAuthor all call hasCapability without try-catch. These were previously O(1) string comparisons that could never throw. Now they hit the database and can fail on connection timeout or transient errors. Wrap each call in try-catch, defaulting to deny (false) on error. This ensures a DB hiccup returns a clean 403 instead of an unhandled 500 with a stack trace. * test: Add canDeleteAccount DB-error resilience test Tests that hasCapability rejection (e.g., DB timeout) results in a clean 403 rather than an unhandled exception. Validates the error handling added in the previous commit. * refactor: Use barrel import for hasCapability in validateAuthor Import from ~/server/middleware barrel instead of directly from ~/server/middleware/roles/capabilities for consistency with other non-middleware consumers. Files within the middleware barrel itself must continue using direct imports to avoid circular requires. * refactor: Remove misleading pre('save') hook from SystemGrant schema The pre('save') hook normalized principalId for USER/GROUP principals, but the primary write path (grantCapability) uses findOneAndUpdate — which does not trigger save hooks. The normalization was already handled explicitly in grantCapability itself. The hook created a false impression of schema-level enforcement that only covered save()/create() paths. Replace with a comment documenting that all writes must go through grantCapability. * feat: Add READ_ASSISTANTS capability to complete manage/read pair Every other managed resource had a paired READ_X / MANAGE_X capability except assistants. This adds READ_ASSISTANTS and registers the MANAGE_ASSISTANTS → READ_ASSISTANTS implication in CapabilityImplications, enabling future read-only assistant visibility grants. * chore: Reorder systemGrant methods for clarity Moved hasCapabilityForPrincipals to a more logical position in the returned object of createSystemGrantMethods, improving code readability. This change also maintains the inclusion of seedSystemGrants in the export, ensuring all necessary methods are available. * fix: Wrap seedSystemGrants in try-catch to avoid blocking startup Seeding capabilities is idempotent and will succeed on the next restart. A transient DB error during seeding should not prevent the server from starting — log the error and continue. * refactor: Improve capability check efficiency and add audit logging Move hasCapability calls after cheap early-exits in validateAuthor and fetchAssistants so the DB check only runs when its result matters. Add logger.debug on every capability bypass grant across all 7 call sites for auditability, and log errors in catch blocks instead of silently swallowing them. * test: Add integration tests for AsyncLocalStorage capability caching Exercises the full vertical — ALS context, generateCapabilityCheck, real getUserPrincipals, real hasCapabilityForPrincipals, real MongoDB via MongoMemoryServer. Covers per-request caching, cross-context isolation, concurrent request isolation, negative caching, capability implications, tenant scoping, group-based grants, and requireCapability middleware. * test: Add systemGrant data-layer and ALS edge-case integration tests systemGrant.spec.ts (51 tests): Full integration tests for all systemGrant methods against real MongoDB — grant/revoke lifecycle, principalId normalization (string→ObjectId for USER/GROUP, string for ROLE), capability implications (both directions), tenant scoping, schema validation (null tenantId, invalid enum, required fields, unique compound index). capabilities.integration.spec.ts (27 tests): Adds ALS edge cases — missing context degrades gracefully with no caching (background jobs, child processes), nested middleware creates independent inner context, optional-chaining safety when store is undefined, mid-request grant changes are invisible due to result caching, requireCapability works without ALS, and interleaved concurrent contexts maintain isolation. * fix: Add worker thread guards to capability ALS usage Detect when hasCapability or capabilityContextMiddleware is called from a worker thread (where ALS context does not propagate from the parent). hasCapability logs a warn-once per factory instance; the middleware logs an error since mounting Express middleware in a worker is likely a misconfiguration. Both continue to function correctly — the guard is observability, not a hard block. * fix: Include tenantId in ALS principal cache key for tenant isolation The principal cache key was user.id:user.role, which would reuse cached principals across tenants for the same user within a request. When getUserPrincipals gains tenant-scoped group resolution, principals from tenant-a would incorrectly serve tenant-b checks. Changed to user.id:user.role:user.tenantId to prevent cross-tenant cache hits. Adds integration test proving separate principal lookups per tenantId. * test: Remove redundant mocked capabilities.spec.js The JS wrapper test (7 tests, all mocked) is a strict subset of capabilities.integration.spec.ts (28 tests, real MongoDB). Every scenario it covered — hasCapability true/false, tenantId passthrough, requireCapability 403/500, error handling — is tested with higher fidelity in the integration suite. * test: Replace mocked canDeleteAccount tests with real MongoDB integration Remove hasCapability mock — tests now exercise the full capability chain against real MongoDB (getUserPrincipals, hasCapabilityForPrincipals, SystemGrant collection). Only mocks remaining are logger and cache. Adds new coverage: admin role without grant is blocked, user-level grant bypasses deletion restriction, null user handling. * test: Add comprehensive tests for ACL entry management and user group methods Introduces new tests for `deleteAclEntries`, `bulkWriteAclEntries`, and `findPublicResourceIds` in `aclEntry.spec.ts`, ensuring proper functionality for deleting and bulk managing ACL entries. Additionally, enhances `userGroup.spec.ts` with tests for finding groups by ID and name pattern, including external ID matching and source filtering. These changes improve coverage and validate the integrity of ACL and user group operations against real MongoDB interactions. * refactor: Update capability checks and logging for better clarity and error handling Replaced `MANAGE_USERS` with `ACCESS_ADMIN` in the `canDeleteAccount` middleware and related tests to align with updated permission structure. Enhanced logging in various middleware functions to use `logger.warn` for capability check failures, providing clearer error messages. Additionally, refactored capability checks in the `patchPromptGroup` and `validateAuthor` functions to improve readability and maintainability. This commit also includes adjustments to the `systemGrant` methods to implement retry logic for transient failures during capability seeding, ensuring robustness in the face of database errors. * refactor: Enhance logging and retry logic in seedSystemGrants method Updated the logging format in the seedSystemGrants method to include error messages for better clarity. Improved the retry mechanism by explicitly mocking multiple failures in tests, ensuring robust error handling during transient database issues. Additionally, refined imports in the systemGrant schema for better type management. * refactor: Consolidate imports in canDeleteAccount middleware Merged logger and SystemCapabilities imports from the data-schemas module into a single line for improved readability and maintainability of the code. This change streamlines the import statements in the canDeleteAccount middleware. * test: Enhance systemGrant tests for error handling and capability validation Added tests to the systemGrant methods to handle various error scenarios, including E11000 race conditions, invalid ObjectId strings for USER and GROUP principals, and invalid capability strings. These enhancements improve the robustness of the capability granting and revoking logic, ensuring proper error propagation and validation of inputs. * fix: Wrap hasCapability calls in deny-by-default try-catch at remaining sites canAccessResource, files.js, and roles.js all had hasCapability inside outer try-catch blocks that returned 500 on DB failure instead of falling through to the regular ACL check. This contradicts the deny-by-default pattern used everywhere else. Also removes raw error.message from the roles.js 500 response to prevent internal host/connection info leaking to clients. * fix: Normalize user ID in canDeleteAccount before passing to hasCapability requireCapability normalizes req.user.id via _id?.toString() fallback, but canDeleteAccount passed raw req.user directly. If req.user.id is absent (some auth layers only populate _id), getUserPrincipals received undefined, silently returning empty principals and blocking the bypass. * fix: Harden systemGrant schema and type safety - Reject empty string tenantId in schema validator (was only blocking null; empty string silently orphaned documents) - Fix reverseImplications to use BaseSystemCapability[] instead of string[], preserving the narrow discriminated type - Document READ_ASSISTANTS as reserved/unenforced * test: Use fake timers for seedSystemGrants retry tests and add tenantId validation - Switch retry tests to jest.useFakeTimers() to eliminate 3+ seconds of real setTimeout delays per test run - Add regression test for empty-string tenantId rejection * docs: Add TODO(#12091) comments for tenant-scoped capability gaps In multi-tenant mode, platform-level grants (no tenantId) won't match tenant-scoped queries, breaking admin access. getUserPrincipals also returns cross-tenant group memberships. Both need fixes in #12091.	2026-03-21 14:28:54 -04:00
Danny Avila	0412f05daf	🪢 chore: Consolidate Pricing and Tx Imports After tx.js Module Removal (#12086) ... * 🧹 chore: resolve imports due to rebase * chore: Update model mocks in unit tests for consistency - Consolidated model mock implementations across various test files to streamline setup and reduce redundancy. - Removed duplicate mock definitions for `getMultiplier` and `getCacheMultiplier`, ensuring a unified approach in `recordCollectedUsage.spec.js`, `openai.spec.js`, `responses.unit.spec.js`, and `abortMiddleware.spec.js`. - Enhanced clarity and maintainability of test files by aligning mock structures with the latest model updates. * fix: Safeguard token credit checks in transaction tests - Updated assertions in `transaction.spec.ts` to handle potential null values for `updatedBalance` by using optional chaining. - Enhanced robustness of tests related to token credit calculations, ensuring they correctly account for scenarios where the balance may not be found. * chore: transaction methods with bulk insert functionality - Introduced `bulkInsertTransactions` method in `transaction.ts` to facilitate batch insertion of transaction documents. - Updated test file `transactions.bulk-parity.spec.ts` to utilize new pricing function assignments and handle potential null values in calculations, improving test robustness. - Refactored pricing function initialization for clarity and consistency. * refactor: Enhance type definitions and introduce new utility functions for model matching - Added `findMatchingPattern` and `matchModelName` utility functions to improve model name matching logic in transaction methods. - Updated type definitions for `findMatchingPattern` to accept a more specific tokensMap structure, enhancing type safety. - Refactored `dbMethods` initialization in `transactions.bulk-parity.spec.ts` to include the new utility functions, improving test clarity and functionality. * refactor: Update database method imports and enhance transaction handling - Refactored `abortMiddleware.js` to utilize centralized database methods for message handling and conversation retrieval, improving code consistency. - Enhanced `bulkInsertTransactions` in `transaction.ts` to handle empty document arrays gracefully and added error logging for better debugging. - Updated type definitions in `transactions.ts` to enforce stricter typing for token types, enhancing type safety across transaction methods. - Improved test setup in `transactions.bulk-parity.spec.ts` by refining pricing function assignments and ensuring robust handling of potential null values. * refactor: Update database method references and improve transaction multiplier handling - Refactored `client.js` to update database method references for `bulkInsertTransactions` and `updateBalance`, ensuring consistency in method usage. - Enhanced transaction multiplier calculations in `transaction.spec.ts` to provide fallback values for write and read multipliers, improving robustness in cost calculations across structured token spending tests.	2026-03-21 14:28:53 -04:00
Danny Avila	8ba2bde5c1	📦 refactor: Consolidate DB models, encapsulating Mongoose usage in data-schemas (#11830) ... * chore: move database model methods to /packages/data-schemas * chore: add TypeScript ESLint rule to warn on unused variables * refactor: model imports to streamline access - Consolidated model imports across various files to improve code organization and reduce redundancy. - Updated imports for models such as Assistant, Message, Conversation, and others to a unified import path. - Adjusted middleware and service files to reflect the new import structure, ensuring functionality remains intact. - Enhanced test files to align with the new import paths, maintaining test coverage and integrity. * chore: migrate database models to packages/data-schemas and refactor all direct Mongoose Model usage outside of data-schemas * test: update agent model mocks in unit tests - Added `getAgent` mock to `client.test.js` to enhance test coverage for agent-related functionality. - Removed redundant `getAgent` and `getAgents` mocks from `openai.spec.js` and `responses.unit.spec.js` to streamline test setup and reduce duplication. - Ensured consistency in agent mock implementations across test files. * fix: update types in data-schemas * refactor: enhance type definitions in transaction and spending methods - Updated type definitions in `checkBalance.ts` to use specific request and response types. - Refined `spendTokens.ts` to utilize a new `SpendTxData` interface for better clarity and type safety. - Improved transaction handling in `transaction.ts` by introducing `TransactionResult` and `TxData` interfaces, ensuring consistent data structures across methods. - Adjusted unit tests in `transaction.spec.ts` to accommodate new type definitions and enhance robustness. * refactor: streamline model imports and enhance code organization - Consolidated model imports across various controllers and services to a unified import path, improving code clarity and reducing redundancy. - Updated multiple files to reflect the new import structure, ensuring all functionalities remain intact. - Enhanced overall code organization by removing duplicate import statements and optimizing the usage of model methods. * feat: implement loadAddedAgent and refactor agent loading logic - Introduced `loadAddedAgent` function to handle loading agents from added conversations, supporting multi-convo parallel execution. - Created a new `load.ts` file to encapsulate agent loading functionalities, including `loadEphemeralAgent` and `loadAgent`. - Updated the `index.ts` file to export the new `load` module instead of the deprecated `loadAgent`. - Enhanced type definitions and improved error handling in the agent loading process. - Adjusted unit tests to reflect changes in the agent loading structure and ensure comprehensive coverage. * refactor: enhance balance handling with new update interface - Introduced `IBalanceUpdate` interface to streamline balance update operations across the codebase. - Updated `upsertBalanceFields` method signatures in `balance.ts`, `transaction.ts`, and related tests to utilize the new interface for improved type safety. - Adjusted type imports in `balance.spec.ts` to include `IBalanceUpdate`, ensuring consistency in balance management functionalities. - Enhanced overall code clarity and maintainability by refining type definitions related to balance operations. * feat: add unit tests for loadAgent functionality and enhance agent loading logic - Introduced comprehensive unit tests for the `loadAgent` function, covering various scenarios including null and empty agent IDs, loading of ephemeral agents, and permission checks. - Enhanced the `initializeClient` function by moving `getConvoFiles` to the correct position in the database method exports, ensuring proper functionality. - Improved test coverage for agent loading, including handling of non-existent agents and user permissions. * chore: reorder memory method exports for consistency - Moved `deleteAllUserMemories` to the correct position in the exported memory methods, ensuring a consistent and logical order of method exports in `memory.ts`.	2026-03-21 14:28:53 -04:00
Danny Avila	58f128bee7	🗑️ chore: Remove Deprecated Project Model and Associated Fields (#11773) ... * chore: remove projects and projectIds usage * chore: empty line linting * chore: remove isCollaborative property across agent models and related tests - Removed the isCollaborative property from agent models, controllers, and tests, as it is deprecated in favor of ACL permissions. - Updated related validation schemas and data provider types to reflect this change. - Ensured all references to isCollaborative were stripped from the codebase to maintain consistency and clarity.	2026-03-21 14:28:53 -04:00
Danny Avila	38521381f4	🐘 feat: FerretDB Compatibility (#11769) ... * feat: replace unsupported MongoDB aggregation operators for FerretDB compatibility Replace $lookup, $unwind, $sample, $replaceRoot, and $addFields aggregation stages which are unsupported on FerretDB v2.x (postgres-documentdb backend). - Prompt.js: Replace $lookup/$unwind/$project pipelines with find().select().lean() + attachProductionPrompts() batch helper. Replace $group/$replaceRoot/$sample in getRandomPromptGroups with distinct() + Fisher-Yates shuffle. - Agent/Prompt migration scripts: Replace $lookup anti-join pattern with distinct() + $nin two-step queries for finding un-migrated resources. All replacement patterns verified against FerretDB v2.7.0. * fix: use $pullAll for simple array removals, fix memberIds type mismatches Replace $pull with $pullAll for exact-value scalar array removals. Both operators work on MongoDB and FerretDB, but $pullAll is more explicit for exact matching (no condition expressions). Fix critical type mismatch bugs where ObjectId values were used against String[] memberIds arrays in Group queries: - config/delete-user.js: use string uid instead of ObjectId user._id - e2e/setup/cleanupUser.ts: convert userId.toString() before query Harden PermissionService.bulkUpdateResourcePermissions abort handling to prevent crash when abortTransaction is called after commitTransaction. All changes verified against FerretDB v2.7.0 and MongoDB Memory Server. * fix: harden transaction support probe for FerretDB compatibility Commit the transaction before aborting in supportsTransactions probe, and wrap abortTransaction in try-catch to prevent crashes when abort is called after a successful commit (observed behavior on FerretDB). * feat: add FerretDB compatibility test suite, retry utilities, and CI config Add comprehensive FerretDB integration test suite covering: - $pullAll scalar array operations - $pull with subdocument conditions - $lookup replacement (find + manual join) - $sample replacement (distinct + Fisher-Yates) - $bit and $bitsAllSet operations - Migration anti-join pattern - Multi-tenancy (useDb, scaling, write amplification) - Sharding proof-of-concept - Production operations (backup/restore, schema migration, deadlock retry) Add production retryWithBackoff utility for deadlock recovery during concurrent index creation on FerretDB/DocumentDB backends. Add UserController.spec.js tests for deleteUserController (runs in CI). Configure jest and eslint to isolate FerretDB tests from CI pipelines: - packages/data-schemas/jest.config.mjs: ignore misc/ directory - eslint.config.mjs: ignore packages/data-schemas/misc/ Include Docker Compose config for local FerretDB v2.7 + postgres-documentdb, dedicated jest/tsconfig for the test files, and multi-tenancy findings doc. * style: brace formatting in aclEntry.ts modifyPermissionBits * refactor: reorganize retry utilities and update imports - Moved retryWithBackoff utility to a new file `retry.ts` for better structure. - Updated imports in `orgOperations.ferretdb.spec.ts` to reflect the new location of retry utilities. - Removed old import statement for retryWithBackoff from index.ts to streamline exports. * test: add $pullAll coverage for ConversationTag and PermissionService Add integration tests for deleteConversationTag verifying $pullAll removes tags from conversations correctly, and for syncUserEntraGroupMemberships verifying $pullAll removes user from non-matching Entra groups while preserving local group membership. ---------	2026-03-21 14:28:49 -04:00
Danny Avila	1ecff83b20	🪦 fix: ACL-Safe User Account Deletion for Agents, Prompts, and MCP Servers (#12314) ... * fix: use ACL ownership for prompt group cleanup on user deletion deleteUserPrompts previously called getAllPromptGroups with only an author filter, which defaults to searchShared=true and drops the author filter for shared/global project entries. This caused any user deleting their account to strip shared prompt group associations and ACL entries for other users. Replace the author-based query with ACL-based ownership lookup: - Find prompt groups where the user has OWNER permission (DELETE bit) - Only delete groups where the user is the sole owner - Preserve multi-owned groups and their ACL entries for other owners * fix: use ACL ownership for agent cleanup on user deletion deleteUserAgents used the deprecated author field to find and delete agents, then unconditionally removed all ACL entries for those agents. This could destroy ACL entries for agents shared with or co-owned by other users. Replace the author-based query with ACL-based ownership lookup: - Find agents where the user has OWNER permission (DELETE bit) - Only delete agents where the user is the sole owner - Preserve multi-owned agents and their ACL entries for other owners - Also clean up handoff edges referencing deleted agents * fix: add MCP server cleanup on user deletion User deletion had no cleanup for MCP servers, leaving solely-owned servers orphaned in the database with dangling ACL entries for other users. Add deleteUserMcpServers that follows the same ACL ownership pattern as prompt groups and agents: find servers with OWNER permission, check for sole ownership, and only delete those with no other owners. * style: fix prettier formatting in Prompt.spec.js * refactor: extract getSoleOwnedResourceIds to PermissionService The ACL sole-ownership detection algorithm was duplicated across deleteUserPrompts, deleteUserAgents, and deleteUserMcpServers. Centralizes the three-step pattern (find owned entries, find other owners, compute sole-owned set) into a single reusable utility. * refactor: use getSoleOwnedResourceIds in all deletion functions - Replace inline ACL queries with the centralized utility - Remove vestigial _req parameter from deleteUserPrompts - Use Promise.all for parallel project removal instead of sequential awaits - Disconnect live MCP sessions and invalidate tool cache before deleting sole-owned MCP server documents - Export deleteUserMcpServers for testability * test: improve deletion test coverage and quality - Move deleteUserPrompts call to beforeAll to eliminate execution-order dependency between tests - Standardize on test() instead of it() for consistency in Prompt.spec.js - Add assertion for deleting user's own ACL entry preservation on multi-owned agents - Add deleteUserMcpServers integration test suite with 6 tests covering sole-owner deletion, multi-owner preservation, session disconnect, cache invalidation, model-not-registered guard, and missing MCPManager - Add PermissionService mock to existing deleteUser.spec.js to fix import chain * fix: add legacy author-based fallback for unmigrated resources Resources created before the ACL system have author set but no AclEntry records. The sole-ownership detection returns empty for these, causing deleteUserPrompts, deleteUserAgents, and deleteUserMcpServers to silently skip them — permanently orphaning data on user deletion. Add a fallback that identifies author-owned resources with zero ACL entries (truly unmigrated) and includes them in the deletion set. This preserves the multi-owner safety of the ACL path while ensuring pre-ACL resources are still cleaned up regardless of migration status. * style: fix prettier formatting across all changed files * test: add resource type coverage guard for user deletion Ensures every ResourceType in the ACL system has a corresponding cleanup handler wired into deleteUserController. When a new ResourceType is added (e.g. WORKFLOW), this test fails immediately, preventing silent data orphaning on user account deletion. * style: fix import order in PermissionService destructure * test: add opt-out set and fix test lifecycle in coverage guard Add NO_USER_CLEANUP_NEEDED set for resource types that legitimately require no per-user deletion. Move fs.readFileSync into beforeAll so path errors surface as clean test failures instead of unhandled crashes.	2026-03-19 17:46:14 -04:00
Danny Avila	39f5f83a8a	🔌 fix: Isolate Code-Server HTTP Agents to Prevent Socket Pool Contamination (#12311) ... * 🔧 fix: Isolate HTTP agents for code-server axios requests Prevents socket hang up after 5s on Node 19+ when code executor has file attachments. follow-redirects (axios dep) leaks `socket.destroy` as a timeout listener on TCP sockets; with Node 19+ defaulting to keepAlive: true, tainted sockets re-enter the global pool and destroy active node-fetch requests in CodeExecutor after the idle timeout. Uses dedicated http/https agents with keepAlive: false for all axios calls targeting CODE_BASEURL in crud.js and process.js. Closes #12298 * ♻️ refactor: Extract code-server HTTP agents to shared module - Move duplicated agent construction from crud.js and process.js into a shared agents.js module to eliminate DRY violation - Switch process.js from raw `require('axios')` to `createAxiosInstance()` for proxy configuration parity with crud.js - Fix import ordering in process.js (agent constants no longer split imports) - Add 120s timeout to uploadCodeEnvFile (was the only code-server call without a timeout) * ✅ test: Add regression tests for code-server socket isolation - Add crud.spec.js covering getCodeOutputDownloadStream and uploadCodeEnvFile (agent options, timeout, URL, error handling) - Add socket pool isolation tests to process.spec.js asserting keepAlive:false agents are forwarded to axios - Update process.spec.js mocks for createAxiosInstance() migration * ♻️ refactor: Move code-server agents to packages/api Relocate agents.js from api/server/services/Files/Code/ to packages/api/src/utils/code.ts per workspace conventions. Consumers now import codeServerHttpAgent/codeServerHttpsAgent from @librechat/api.	2026-03-19 16:16:57 -04:00
Danny Avila	9a64791e3e	🪢 fix: Action Domain Encoding Collision for HTTPS URLs (#12271) ... * fix: strip protocol from domain before encoding in `domainParser` All https:// (and http://) domains produced the same 10-char base64 prefix due to ENCODED_DOMAIN_LENGTH truncation, causing tool name collisions for agents with multiple actions. Strip the protocol before encoding so the base64 key is derived from the hostname. Add `legacyDomainEncode` to preserve the old encoding logic for backward-compatible matching of existing stored actions. * fix: backward-compatible tool matching in ToolService Update `getActionToolDefinitions` to match stored tools against both new and legacy domain encodings. Update `loadActionToolsForExecution` to resolve model-called tool names via a `normalizedToDomain` map that includes both encoding variants, with legacy fallback for request builder lookup. * fix: action route save/delete domain encoding issues Save routes now remove old tools matching either new or legacy domain encoding, preventing stale entries when an action's encoding changes on update. Delete routes no longer re-encode the already-encoded domain extracted from the stored actions array, which was producing incorrect keys and leaving orphaned tools. * test: comprehensive coverage for action domain encoding Rewrite ActionService tests to cover real matching patterns used by ToolService and action routes. Tests verify encode/decode round-trips, protocol stripping, backward-compatible tool name matching at both definition and execution phases, save-route cleanup of old/new encodings, delete-route domain extraction, and the collision fix for multi-action agents. * fix: add legacy domain compat to all execution paths, make legacyDomainEncode sync CRITICAL: processRequiredActions (assistants path) was not updated with legacy domain matching — existing assistants with https:// domain actions would silently fail post-deployment because domainMap only had new encoding. MAJOR: loadAgentTools definitionsOnly=false path had the same issue. Both now use a normalizedToDomain map with legacy+new entries and extract function names via the matched key (not the canonical domain). Also: make legacyDomainEncode synchronous (no async operations), store legacyNormalized in processedActionSets to eliminate recomputation in the per-tool fallback, and hoist domainSeparatorRegex to module level. * refactor: clarify domain variable naming and tool-filter helpers in action routes Rename shadowed 'domain' to 'encodedDomain' to separate raw URL from encoded key in both agent and assistant save routes. Rename shouldRemoveTool to shouldRemoveAgentTool / shouldRemoveAssistantTool to make the distinct data-shape guards explicit. Remove await on now-synchronous legacyDomainEncode. * test: expand coverage for all review findings - Add validateAndUpdateTool tests (protocol-stripping match logic) - Restore unicode domain encode/decode/round-trip tests - Add processRequiredActions matching pattern tests (assistants path) - Add legacy guard skip test for short bare hostnames - Add pre-normalized Set test for definition-phase optimization - Fix corrupt-cache test to assert typeof instead of toBeDefined - Verify legacyDomainEncode is synchronous (not a Promise) - Remove all await on legacyDomainEncode (now sync) 58 tests, up from 44. * fix: address follow-up review findings A-E A: Fix stale JSDoc @returns {Promise<string>} on now-synchronous legacyDomainEncode — changed to @returns {string}. B: Rename normalizedToDomain to domainLookupMap in processRequiredActions and loadAgentTools where keys are raw encoded domains (not normalized), avoiding confusion with loadActionToolsForExecution where keys ARE normalized. C: Pre-normalize actionToolNames into a Set<string> in getActionToolDefinitions, replacing O(signatures × tools) per-check .some() + .replace() with O(1) Set.has() lookups. D: Remove stripProtocol from ActionService exports — it is a one-line internal helper. Spec tests for it removed; behavior is fully covered by domainParser protocol-stripping tests. E: Fix pre-existing bug where processRequiredActions re-loaded action sets on every missing-tool iteration. The guard !actionSets.length always re-triggered because actionSets was reassigned to a plain object (whose .length is undefined). Replaced with a null-check on a dedicated actionSetsData variable. * fix: strip path and query from domain URLs in stripProtocol URLs like 'https://api.example.com/v1/endpoint?foo=bar' previously retained the path after protocol stripping, contaminating the encoded domain key. Now strips everything after the first '/' following the host, using string indexing instead of URL parsing to avoid punycode normalization of unicode hostnames. Closes Copilot review comments 1, 2, and 5.	2026-03-17 01:38:51 -04:00
Danny Avila	8e8fb01d18	🧱 fix: Enforce Agent Access Control on Context and OCR File Loading (#12253) ... * 🔏 fix: Apply agent access control filtering to context/OCR resource loading The context/OCR file path in primeResources fetched files by file_id without applying filterFilesByAgentAccess, unlike the file_search and execute_code paths. Add filterFiles dependency injection to primeResources and invoke it after getFiles to enforce consistent access control. * fix: Wire filterFilesByAgentAccess into all agent initialization callers Pass the filterFilesByAgentAccess function from the JS layer into the TS initializeAgent → primeResources chain via dependency injection, covering primary, handoff, added-convo, and memory agent init paths. * test: Add access control filtering tests for primeResources Cover filterFiles invocation with context/OCR files, verify filtering rejects inaccessible files, and confirm graceful fallback when filterFiles, userId, or agentId are absent. * fix: Guard filterFilesByAgentAccess against ephemeral agent IDs Ephemeral agents have no DB document, so getAgent returns null and the access map defaults to all-false, silently blocking all non-owned files. Short-circuit with isEphemeralAgentId to preserve the pass-through behavior for inline-built agents (memory, tool agents). * fix: Clean up resources.ts and JS caller import order Remove redundant optional chain on req.user.role inside user-guarded block, update primeResources JSDoc with filterFiles and agentId params, and reorder JS imports to longest-to-shortest per project conventions. * test: Strengthen OCR assertion and add filterFiles error-path test Use toHaveBeenCalledWith for the OCR filtering test to verify exact arguments after the OCR→context merge step. Add test for filterFiles rejection to verify graceful degradation (logs error, returns original tool_resources). * fix: Correct import order in addedConvo.js and initialize.js Sort by total line length descending: loadAddedAgent (91) before filterFilesByAgentAccess (84), loadAgentTools (91) before filterFilesByAgentAccess (84). * test: Add unit tests for filterFilesByAgentAccess and hasAccessToFilesViaAgent Cover every branch in permissions.js: ephemeral agent guard, missing userId/agentId/files early returns, all-owned short-circuit, mixed owned + non-owned with VIEW/no-VIEW, agent-not-found fail-closed, author path scoped to attached files, EDIT gate on delete, DB error fail-closed, and agent with no tool_resources. * test: Cover file.user undefined/null in permissions spec Files with no user field fall into the non-owned path and get run through hasAccessToFilesViaAgent. Add two cases: attached file with no user field is returned, unattached file with no user field is excluded.	2026-03-15 23:02:36 -04:00
Danny Avila	6f87b49df8	🛂 fix: Enforce Actions Capability Gate Across All Event-Driven Tool Loading Paths (#12252) ... * fix: gate action tools by actions capability in all code paths Extract resolveAgentCapabilities helper to eliminate 3x-duplicated capability resolution. Apply early action-tool filtering in both loadToolDefinitionsWrapper and loadAgentTools non-definitions path. Gate loadActionToolsForExecution in loadToolsForExecution behind an actionsEnabled parameter with a cache-based fallback. Replace the late capability guard in loadAgentTools with a hasActionTools check to avoid unnecessary loadActionSets DB calls and duplicate warnings. * fix: thread actionsEnabled through InitializedAgent type Add actionsEnabled to the loadTools callback return type, InitializedAgent, and the initializeAgent destructuring/return so callers can forward the resolved value to loadToolsForExecution without redundant getEndpointsConfig cache lookups. * fix: pass actionsEnabled from callers to loadToolsForExecution Thread actionsEnabled through the agentToolContexts map in initialize.js (primary and handoff agents) and through primaryConfig in the openai.js and responses.js controllers, avoiding per-tool-call capability re-resolution on the hot path. * test: add regression tests for action capability gating Test the real exported functions (resolveAgentCapabilities, loadAgentTools, loadToolsForExecution) with mocked dependencies instead of shadow re-implementations. Covers definition filtering, execution gating, actionsEnabled param forwarding, and fallback capability resolution. * test: use Constants.EPHEMERAL_AGENT_ID in ephemeral fallback test Replaces a string guess with the canonical constant to avoid fragility if the ephemeral detection heuristic changes. * fix: populate agentToolContexts for addedConvo parallel agents After processAddedConvo returns, backfill agentToolContexts for any agents in agentConfigs not already present, so ON_TOOL_EXECUTE for added-convo agents receives actionsEnabled instead of falling back to a per-call cache lookup.	2026-03-15 23:01:36 -04:00
Danny Avila	ad08df4db6	🔏 fix: Scope Agent-Author File Access to Attached Files Only (#12251) ... * 🛡️ fix: Scope agent-author file access to attached files only The hasAccessToFilesViaAgent helper short-circuited for agent authors, granting access to all requested file IDs without verifying they were attached to the agent's tool_resources. This enabled an IDOR where any agent author could delete arbitrary files by supplying their agent_id alongside unrelated file IDs. Now both the author and non-author paths check file IDs against the agent's tool_resources before granting access. * chore: Use Object.values/for...of and add JSDoc in getAttachedFileIds * test: Add boundary cases for agent file access authorization - Agent with no tool_resources denies all access (fail-closed) - Files across multiple resource types are all reachable - Author + isDelete: true still scopes to attached files only	2026-03-15 18:54:34 -04:00
Danny Avila	bcf45519bd	🪪 fix: Enforce VIEW ACL on Agent Edge References at Write and Runtime (#12246) ... * 🛡️ fix: Enforce ACL checks on handoff edge and added-convo agent loading Edge-linked agents and added-convo agents were fetched by ID via getAgent without verifying the requesting user's access permissions. This allowed an authenticated user to reference another user's private agent in edges or addedConvo and have it initialized at runtime. Add checkPermission(VIEW) gate in processAgent before initializing any handoff agent, and in processAddedConvo for non-ephemeral added agents. Unauthorized agents are logged and added to skippedAgentIds so orphaned-edge filtering removes them cleanly. * 🛡️ fix: Validate edge agent access at agent create/update time Reject agent create/update requests that reference agents in edges the requesting user cannot VIEW. This provides early feedback and prevents storing unauthorized agent references as defense-in-depth alongside the runtime ACL gate in processAgent. Add collectEdgeAgentIds utility to extract all unique agent IDs from an edge array, and validateEdgeAgentAccess helper in the v1 handler. * 🧪 test: Improve ACL gate test coverage and correctness - Add processAgent ACL gate tests for initializeClient (skip/allow handoff agents) - Fix addedConvo.spec.js to mock loadAddedAgent directly instead of getAgent - Seed permMap with ownedAgent VIEW bits in v1.spec.js update-403 test * 🧹 chore: Remove redundant addedConvo ACL gate (now in middleware) PR #12243 moved the addedConvo agent ACL check upstream into canAccessAgentFromBody middleware, making the runtime check in processAddedConvo and its spec redundant. * 🧪 test: Rewrite processAgent ACL test with real DB and minimal mocking Replace heavy mock-based test (12 mocks, Providers.XAI crash) with MongoMemoryServer-backed integration test that exercises real getAgent, checkPermission, and AclEntry — only external I/O (initializeAgent, ToolService, AgentClient) remains mocked. Load edge utilities directly from packages/api/src/agents/edges to sidestep the config.ts barrel. * 🧪 fix: Use requireActual spread for @librechat/agents and @librechat/api mocks The Providers.XAI crash was caused by mocking @librechat/agents with a minimal replacement object, breaking the @librechat/api initialization chain. Match the established pattern from client.test.js and recordCollectedUsage.spec.js: spread jest.requireActual for both packages, overriding only the functions under test.	2026-03-15 18:08:57 -04:00
Danny Avila	f67bbb2bc5	🧹 fix: Sanitize Artifact Filenames in Code Execution Output (#12222) ... * fix: sanitize artifact filenames to prevent path traversal in code output * test: Mock sanitizeFilename function in process.spec.js to return the original filename - Added a mock implementation for the `sanitizeFilename` function in the `process.spec.js` test file to return the original filename, ensuring that tests can run without altering the filename during the testing process. * fix: use path.relative for traversal check, sanitize all filenames, add security logging - Replace startsWith with path.relative pattern in saveLocalBuffer, consistent with deleteLocalFile and getLocalFileStream in the same file - Hoist sanitizeFilename call before the image/non-image branch so both code paths store the sanitized name in MongoDB - Log a warning when sanitizeFilename mutates a filename (potential traversal) - Log a specific warning when saveLocalBuffer throws a traversal error, so security events are distinguishable from generic network errors in the catch * test: improve traversal test coverage and remove mock reimplementation - Remove partial sanitizeFilename reimplementation from process-traversal tests; use controlled mock returns to verify processCodeOutput wiring instead - Add test for image branch sanitization - Use mkdtempSync for test isolation in crud-traversal to avoid parallel worker collisions - Add prefix-collision bypass test case (../user10/evil vs user1 directory) * fix: use path.relative in isValidPath to prevent prefix-collision bypass Pre-existing startsWith check without path separator had the same class of prefix-collision vulnerability fixed in saveLocalBuffer.	2026-03-14 03:09:26 -04:00
Danny Avila	71a3b48504	🔑 fix: Require OTP Verification for 2FA Re-Enrollment and Backup Code Regeneration (#12223) ... * fix: require OTP verification for 2FA re-enrollment and backup code regeneration * fix: require OTP verification for account deletion when 2FA is enabled * refactor: Improve code formatting and readability in TwoFactorController and UserController - Reformatted code in TwoFactorController and UserController for better readability by aligning parameters and breaking long lines. - Updated test cases in deleteUser.spec.js and TwoFactorController.spec.js to enhance clarity by formatting object parameters consistently. * refactor: Consolidate OTP and backup code verification logic in TwoFactorController and UserController - Introduced a new `verifyOTPOrBackupCode` function to streamline the verification process for TOTP tokens and backup codes across multiple controllers. - Updated the `enable2FA`, `disable2FA`, and `deleteUserController` methods to utilize the new verification function, enhancing code reusability and readability. - Adjusted related tests to reflect the changes in verification logic, ensuring consistent behavior across different scenarios. - Improved error handling and response messages for verification failures, providing clearer feedback to users. * chore: linting * refactor: Update BackupCodesItem component to enhance OTP verification logic - Consolidated OTP input handling by moving the 2FA verification UI logic to a more consistent location within the component. - Improved the state management for OTP readiness, ensuring the regenerate button is only enabled when the OTP is ready. - Cleaned up imports by removing redundant type imports, enhancing code clarity and maintainability. * chore: lint * fix: stage 2FA re-enrollment in pending fields to prevent disarmament window enable2FA now writes to pendingTotpSecret/pendingBackupCodes instead of overwriting the live fields. confirm2FA performs the atomic swap only after the new TOTP code is verified. If the user abandons mid-flow, their existing 2FA remains active and intact.	2026-03-14 01:51:31 -04:00
Danny Avila	6167ce6e57	🧪 chore: MCP Reconnect Storm Follow-Up Fixes and Integration Tests (#12172) ... * 🧪 test: Add reconnection storm regression tests for MCPConnection Introduced a comprehensive test suite for reconnection storm scenarios, validating circuit breaker, throttling, cooldown, and timeout fixes. The tests utilize real MCP SDK transports and a StreamableHTTP server to ensure accurate behavior under rapid connect/disconnect cycles and error handling for SSE 400/405 responses. This enhances the reliability of the MCPConnection by ensuring proper handling of reconnection logic and circuit breaker functionality. * 🔧 fix: Update createUnavailableToolStub to return structured response Modified the `createUnavailableToolStub` function to return an array containing the unavailable message and a null value, enhancing the response structure. Additionally, added a debug log to skip tool creation when the result is null, improving the handling of reconnection scenarios in the MCP service. * 🧪 test: Enhance MCP tool creation tests for cache and throttle interactions Added new test cases for the `createMCPTool` function to validate the caching behavior when tools are unavailable or throttled. The tests ensure that tools are correctly cached as missing and prevent unnecessary reconnects across different users, improving the reliability of the MCP service under concurrent usage scenarios. Additionally, introduced a test for the `createMCPTools` function to verify that it returns an empty array when reconnect is throttled, ensuring proper handling of throttling logic. * 📝 docs: Update AGENTS.md with testing philosophy and guidelines Expanded the testing section in AGENTS.md to emphasize the importance of using real logic over mocks, advocating for the use of spies and real dependencies in tests. Added specific recommendations for testing with MongoDB and MCP SDK, highlighting the need to mock only uncontrollable external services. This update aims to improve testing practices and encourage more robust test implementations. * 🧪 test: Enhance reconnection storm tests with socket tracking and SSE handling Updated the reconnection storm test suite to include a new socket tracking mechanism for better resource management during tests. Improved the handling of SSE 400/405 responses by ensuring they are processed in the same branch as 404 errors, preventing unhandled cases. This enhances the reliability of the MCPConnection under rapid reconnect scenarios and ensures proper error handling. * 🔧 fix: Implement cache eviction for stale reconnect attempts and missing tools Added an `evictStale` function to manage the size of the `lastReconnectAttempts` and `missingToolCache` maps, ensuring they do not exceed a maximum cache size. This enhancement improves resource management by removing outdated entries based on a specified time-to-live (TTL), thereby optimizing the MCP service's performance during reconnection scenarios.	2026-03-10 17:44:13 -04:00