634 commits

Author	SHA1	Message	Date
Danny Avila	f7e47f6012	🪢 feat: Enable Tool-Output References for Bash Tool (#12830) ... * chore: Update `@librechat/agents` to v3.1.71-dev.0 across package-lock and package.json files This commit updates the version of the `@librechat/agents` package from `3.1.70` to `3.1.71-dev.0` in the `package-lock.json` and relevant `package.json` files. Additionally, it marks several dependencies as peer dependencies, ensuring better compatibility and integration across the project. * 🔗 feat: Enable Tool-Output References for bash_tool when codeenv is on Wires `@librechat/agents`' `RunConfig.toolOutputReferences` into `createRun()` and the bash tool's LLM-facing description, gated by the per-agent `effectiveCodeEnvAvailable` flag. The feature auto-activates for any run where the bash tool is actually registered; SDK defaults (~400 KB per output, 5 MB total) match the shell-safe budget. No new env var or yaml capability — piggybacks on the existing `execute_code` gate. - `tools.ts`: replace the module-level `BASH_TOOL_DEF` constant with a per-call `buildBashToolDef` that wraps `buildBashExecutionToolDescription`. Description now includes the `{{tool<idx>turn<turn>}}` reference syntax guide iff the new `enableToolOutputReferences` param is true. - `initialize.ts`: pass `enableToolOutputReferences: effectiveCodeEnvAvailable` into `registerCodeExecutionTools`. - `run.ts`: add `codeEnvAvailable?: boolean` to `RunAgent`, compute the flag from `agents[*].codeEnvAvailable`, and conditionally spread `toolOutputReferences: { enabled: true }` into `Run.create`. * 🧪 test: Cover tool-output references gating end-to-end - `tools.spec.ts`: 3 new cases asserting `bash_tool.description` contains `{{tool<idx>turn<turn>}}` iff `enableToolOutputReferences` is true (and unset → false). - `run-summarization.test.ts`: 4 new cases asserting `Run.create` is invoked with `toolOutputReferences: { enabled: true }` iff at least one `RunAgent.codeEnvAvailable === true`. Covers the present / absent / unset / multi-agent-OR cases. - `initialize.test.ts` + `skills.test.ts`: extend the existing `@librechat/agents` jest mocks with a `buildBashExecutionToolDescription` stub so suites stay green when the on-disk SDK lags the published 3.1.71-dev.0 export. * chore: Update `@librechat/agents` version to `3.1.71-dev.1` in package-lock and package.json files This commit updates the version of the `@librechat/agents` package from `3.1.71-dev.0` to `3.1.71-dev.1` across the relevant package files. This change ensures consistency and incorporates any updates or fixes from the new version. * 🪢 fix: Walk Subagents in toolOutputReferences run-level gate Codex P2 review on PR #12830: the run-level `enableToolOutputReferences` flag only inspected the top-level `agents` array. A parent agent without `execute_code` that spawns a subagent that *does* have it left the SDK's tool-output reference registry inactive for the run, so the subagent's `bash_tool` calls saw `{{tool<idx>turn<turn>}}` placeholders pass through to the shell unsubstituted. Replace `agents.some(a => a.codeEnvAvailable === true)` with a recursive `anyAgentHasCodeEnv` helper that walks `subagentAgentConfigs` transitively. Cycle-safe via a `visited` set, mirroring the existing `buildSubagentConfigs.ancestors` pattern in the same module. The bash tool *description* stays per-agent in `initializeAgent` (only agents with bash actually registered learn the `{{…}}` syntax), so broadening the run-level gate doesn't broaden the model-facing surface — it just lets the SDK's shared registry serve every `ToolNode` the run compiles, which is exactly the contract the SDK already implements. Tests cover three new cases: parent-off / subagent-on, parent-off / child-off / grandchild-on (transitive descent past one level), and a cyclic A↔B tree with neither codeenv-enabled (asserts both termination and absence of `toolOutputReferences`). Existing single-agent and multi-agent tests stay valid since the new helper returns `true` whenever the previous `.some(...)` did. * chore: Update `@librechat/agents` version to `3.1.71` in package-lock and package.json files This commit updates the version of the `@librechat/agents` package from `3.1.71-dev.1` to `3.1.71` across the relevant package files. This change ensures consistency and incorporates any updates or fixes from the stable release. * review: address audit findings on tool-output references PR Two findings from comprehensive PR review on #12830: #1 (MINOR) — `injectSkillCatalog` omitted `enableToolOutputReferences` when calling `registerCodeExecutionTools`, so its resulting `bash_tool` description always lacked the `{{tool<idx>turn<turn>}}` guide. Today this is a no-op because `initializeAgent` registers first and the registry `.has()` check makes the skills-path call a dedupe-only operation. But if call order ever flips (skills-first), the missing flag would silently ship a `bash_tool` without the syntax guide, and the `initializeAgent` pass would itself become the no-op — the feature would silently break with no visible error. Forward `enableToolOutputReferences: codeEnvAvailable === true` so both call sites produce identical tool definitions regardless of firing order. Defense-in-depth, not a current bug. Added a test in `skills.test.ts` that asserts the bash description contains the `{{tool<idx>turn<turn>}}` marker when `codeEnvAvailable` is on, exercising the skills caller end-to-end. #2 (NIT) — `buildBashToolDef` allocated + froze a fresh object on every agent init. Replaced with two module-level frozen singletons (`BASH_TOOL_DEF_WITH_OUTPUT_REFS`, `BASH_TOOL_DEF_WITHOUT_OUTPUT_REFS`) built once at module load via a `createBashToolDef` helper. The factory now picks the right cached reference instead of building. Restores the no-allocation intent of the original `BASH_TOOL_DEF` constant while keeping the per-agent gate behavior. Two new tests in `tools.spec.ts` pin the contract: identical-flag calls return reference-equal `bash_tool` defs across registries; opposite-flag calls return distinct frozen objects with the expected description content.	2026-04-26 02:06:23 -07:00
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	ac913aa886	🔐 chore: Skills Permissions Housekeeping, Reachable Admin Dialog + Defaults Tests (#12766) ... * 🔐 chore: Skills permissions housekeeping — reachable admin dialog + defaults tests Phase 9 housekeeping pass. Skills was already gated on `PermissionTypes.SKILLS` (seeded from `interface.skills`) and `AgentCapabilities.skills` everywhere it matters, but two smaller parity gaps with Prompts/Memory/MCP remained: - The skills admin settings dialog had no UI entry point. The only mount was inside an unused `FilterSkills` component, so admins had no way to reach the role-permissions editor for skills. Mounted it in `SkillsAccordion` gated on `SystemRoles.ADMIN`, matching the `PromptsAccordion` pattern. - No regression lock on skill permission defaults. `roles.spec.ts` asserted structural completeness but not the specific shape — a future refactor could silently flip ADMIN's `USE/CREATE/SHARE/SHARE_PUBLIC` to false or drop SKILLS from USER defaults without failing. Added explicit Skills assertions for both roles. - No lock on `AgentCapabilities.skills` being in `defaultAgentCapabilities`. Added an assertion in `endpoints.spec.ts`. * 🩹 fix: Remove duplicate `const appConfig` in Responses createResponse The Skills polish commit (#12760) added `const appConfig = req.config;` at line 381 inside the try block of `createResponse`, without noticing that the earlier drive-by fix (2463b6acd) already declared it at the function top (line 283). The second `const` creates a new block-scoped binding inside the try, so earlier references within the same block (e.g. line 348's `appConfig?.endpoints?.[EModelEndpoint.agents]?.allowedProviders`) now hit the TDZ instead of the outer binding and throw `ReferenceError: Cannot access 'appConfig' before initialization` — which the outer try/catch then swallows into a generic 500. This surfaced as all six token-usage tests in `api/server/controllers/agents/__tests__/responses.unit.spec.js` failing with `mockRecordCollectedUsage` never being called (because the throw skips past the `recordCollectedUsage(...)` call). Dropping the inner re-declaration restores the full control flow. All 11 tests in the file pass again. * 🧹 refactor: Address review nits on Phase 9 housekeeping - Move the `defaultAgentCapabilities` regression test out of the `createEndpointsConfigService` describe block and into its own top-level describe. It tests a module constant and has no relationship to the service factory; nesting was misleading and made it easier to accidentally drop if the service tests are later restructured. - Re-order local imports in `SkillsAccordion.tsx` longest-to-shortest per AGENTS.md convention (`SkillsSidePanel` 48 chars before `useAuthContext` 41 chars).	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	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	bb13d5b9ee	🪜 chore: Plumb allowedTools through resolveManualSkills (#12744) ... * 🪜 chore: Plumb `allowedTools` through `resolveManualSkills` Tiny shape-only precursor shared by Phase 5 (`always-apply`) and Phase 6 (frontmatter runtime enforcement). Adds `allowedTools?: string[]` to `ResolvedManualSkill` and widens the `getSkillByName` return type in `ResolveManualSkillsParams` and `InitializeAgentDbMethods` to carry the same field. The resolver forwards `skill.allowedTools` verbatim when present. No runtime behavior change — the field is populated but not yet consumed. Phase 6 will union the per-skill allowlist into the agent's effective tool set for the turn; Phase 5's `ResolvedAlwaysApplySkill` will mirror this shape. Landing this first eliminates the type-shape race between the two phases. * 🪜 style: Drop phase-name refs from `allowedTools` JSDoc for longevity JSDoc that cites "Phase N will X" goes stale the moment that phase ships. Swap for "future runtime enforcement" so the docs age with the code.	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
Marco Beretta	f6ee2ea0ee	📜 feat: Skills UI + Initial E2E CRUD / Sharing (#12580) ... * 🎨 feat: Skills UI — Create/Edit/Share/List with Conditional File Tree First-pass UI on top of the CRUD API scaffolding (#12613). Ships the full user-facing flow for inline, single-SKILL.md skills and leaves a clean drop-in for phase-2 multi-file support. - Create a skill from /skills/new with name (kebab-case, validated), description, and SKILL.md body — wired to the real `useCreateSkillMutation` and `TCreateSkill` payload. - List skills in a sidebar (SkillsSidePanel) via `useListSkillsQuery` with live search filtering. - Edit any skill the caller has EDIT permission on — `useUpdateSkillMutation` passes `expectedVersion` for optimistic concurrency and surfaces 409 conflicts as a warning toast + cache refetch. - Non-blocking `TSkillWarning[]` (e.g. "description too short") are shown inline above the form after a successful create/patch. - Read-only mode when the current user lacks EDIT — the form still renders but inputs are marked `readOnly` and the save/reset buttons are hidden. - Share via ACL using the existing `GenericGrantAccessDialog` — the `ShareSkill` button is gated on the SHARE permission. - Delete with confirmation, driven by `useDeleteSkillMutation({ id })`. - Conditional file tree: only rendered when `useListSkillFilesQuery` returns > 0 files. The tree groups flat `relativePath` strings into a nested view (no `react-arborist` dependency) and supports per-file deletion via `useDeleteSkillFileMutation`. Upload is intentionally deferred — the backend stubs it at 501 in phase 1. - New routes: `/skills`, `/skills/new`, `/skills/:skillId`. - Sidebar accordion (`SkillsAccordion` wrapping `SkillsSidePanel`) added to `useSideNavLinks` gated on `PermissionTypes.SKILLS` USE. The initial UI branch (#12580) shipped a lot of exploration code on top of a now-superseded placeholder backend. Kept as complementary: the `Skills/` component tree, translation keys, role descriptions, `PublicSharingToggle` SKILL mapping, `resources.ts` SKILL config, `useCanSharePublic` SKILL mapping, and `data-provider/roles.ts` `useUpdateSkillPermissionsMutation`. Deferred out of this first pass: - Skill favorites (`useSkillFavorites`, `getSkillFavorites` endpoint) — the backend route doesn't exist yet; saving for a follow-up. - AgentConfig `SkillSelectDialog` integration — the UI branch had this gated behind `false &&`; rolled back with the config. - `InvocationMode` / `CategorySelector` / `parseSkillMd` / tree-node mutations — not in the Anthropic skill spec and not in the CRUD API. - `react-arborist` dependency — replaced with a hand-rolled recursive tree built from flat `TSkillFile[]`. - 38 data-schemas skill model tests: pass - 25 api skill route tests: pass - 16 user-controller cleanup tests: pass * 🔐 feat: Default-On Skills in Interface Config and Role Seeder The skills accordion was registered in the side nav gated on `PermissionTypes.SKILLS` USE, but no one was actually seeding that permission on startup, so a fresh install had the USER role with zero skill permissions and the accordion never rendered. Fixes three gaps: 1. `interfaceSchema` in data-provider's `config.ts` had no `skills` field at all. Added it alongside the existing agents/prompts shape (boolean | { use, create, share, public }) and a default of `{ use: true, create: true, share: false, public: false }`. 2. `loadDefaultInterface` in data-schemas passed every interface key through to the loaded config EXCEPT `skills`. Added the one-line passthrough so `appConfig.interfaceConfig.skills` is actually populated on boot. 3. `updateInterfacePermissions` in packages/api/src/app/permissions.ts seeds role permissions from the interface config on every restart. Added: - `SKILLS` case to `hasExplicitConfig` - `skillsDefaultUse/Create/Share/Public` extraction (mirrors prompts/agents) - `PermissionTypes.SKILLS` block in `allPermissions` that falls through config → roleDefaults → schema default, same pattern as AGENTS and PROMPTS - `SKILLS` entry in the share-backfill array so that pre-existing SKILL role docs missing SHARE/SHARE_PUBLIC get them filled on the next restart Test expectations updated: seven `expectedPermissionsFor(User|Admin)` blocks in `permissions.spec.ts` now include SKILLS, matching the role-default values (USER: use+create true, share/public false; ADMIN: all true). Result: on a fresh install, a regular USER gets skill USE/CREATE and the "Skills" accordion shows up in the chat side panel without any yaml config. Admins can lock it down per role or per tenant via `interface.skills` in librechat.yaml. Tests: - 34 packages/api permissions.spec.ts: pass - 151 packages/api app tests: pass - 38 data-schemas skill.spec.ts: pass - 928 data-provider tests: pass - 25 api skills.test.js: pass * ♻️ fix: Resolve Skills UI Review Findings Addresses the 13 findings from the PR review against the prior commit. 1. **canEdit consistency** — extracted `useSkillPermissions(skill)` as the single source of truth for owner/admin/ACL gating. `SkillsView`, `SkillForm`, `ShareSkill` all consume it; `SkillFileTree`'s per-file delete button now honors admin + EDIT-bit permissions instead of just ownership. Unit tests cover owner, admin, editor-ACL, viewer-ACL, owner-ACL, loading, and undefined-skill cases. 2. **Disabled submit buttons** — create/edit form submit buttons now set native `disabled` (not just `aria-disabled`) during `isLoading`. `onSubmit` also guards with an early return when the mutation is still in-flight so a duplicate enter-key submit can't create two skills. 3. **Wrong maxLength error message** — description/name `maxLength` rules no longer re-use `com_ui_skill_*_required`. Added dedicated `com_ui_skill_name_too_long` and `com_ui_skill_description_too_long` keys with the literal limit interpolated (`{{0}}`). 4. **Search debouncing** — `SkillsSidePanel` now threads the filter input through the existing `useDebounce` hook (250ms) so typing "skills" no longer fires six separate list queries. 5. **Frontend test coverage** — added: - `tree.test.ts` (9 tests) covering `buildTree` / `nodeKey` edge cases: empty input, single root file, multiple roots, nested folders, deeply-nested trees, lexicographic sort, empty paths, stable keys - `useSkillPermissions.test.ts` (7 tests) covering every precedence branch (owner / admin / EDIT / VIEW / owner-ACL / loading / undef) Form integration tests proved flaky against react-hook-form's async `isValid` with our jest-dom mock setup; deferred to a follow-up PR with a proper `@librechat/client` test harness. 6. **Shared `SKILL_NAME_PATTERN`** — promoted the regex plus the four length constants (`SKILL_NAME_MAX_LENGTH`, `SKILL_DESCRIPTION_MAX_LENGTH`, `SKILL_DESCRIPTION_SHORT_THRESHOLD`, `SKILL_DISPLAY_TITLE_MAX_LENGTH`, `SKILL_BODY_MAX_LENGTH`) out of `packages/data-schemas/src/methods/skill.ts` and into `packages/data-provider/src/types/skills.ts`. The data-schemas module now aliases the shared exports so the backend validator and the frontend form share one source of truth. Also fixed a latent bug: the client regex was stricter than the backend (`^[a-z0-9]+(?:-[a-z0-9]+)*$` vs. the real `^[a-z0-9][a-z0-9-]*$`), which would have rejected valid names like `foo--bar` client-side. 7. **Removed hardcoded "Claude"** — replaced `com_ui_skill_description_help` ("Claude uses this to...") with a new `com_ui_skill_create_subtitle` for the form header and `com_ui_skill_description_field_hint` ("This is what the model reads to decide...") for the inline hint. LibreChat is LLM-agnostic; the old copy misled GPT/Gemini users. 8. **Lifted tree mutation hook** — `useDeleteSkillFileMutation` is now instantiated once in `SkillFileTree` (not per `TreeRow`). A `TreeContext` provides `onDeleteFile` + `isDeleting` + `canEdit` to rows. A 60-node tree used to instantiate 60 mutation hooks; it now instantiates one. 9. **List O(n) re-render** — `SkillListItem` no longer reads `useParams()` directly. `SkillList` reads the active id once and passes `isActive` as a prop, so navigation only re-renders the two items whose `isActive` flipped (memo'd), not all N items. 10. **Deduped help text** — the field-level hint and form-level subtitle now use different translation keys with distinct copy instead of showing the same sentence twice on the same page. 11. **Removed ineffective `useCallback`** — `DeleteSkill.handleDelete`, `CreateSkillForm.onSubmit` / `.handleCancel`, `SkillForm.onSubmit`, and `SkillFileTree.handleDeleteFile` all wrapped closures around React Query `mutation` refs, whose identities change every render. Their dep arrays invalidated every render, making the memo a no-op with extra overhead. `SkillFileTree` now destructures the stable `mutate` function and inlines the arrow inside the memoized `contextValue` — one stable reference per deps change. 12. **Import order** — fixed shortest→longest package ordering and longest→shortest local ordering across all touched skill files per AGENTS.md. `react` always first where imported. 13. **Memoization principle** — documented the rule with inline comments: `memo` on components that appear in repeated contexts (`TreeRow`, `SkillListItem`) or as children of frequently-re-rendering parents (`ShareSkill` / `DeleteSkill` under `SkillForm`'s per-keystroke form-state updates). Removed `memo` from `SkillFileTree` since its parent `SkillDetailPanel` only re-renders on query-data changes. - 38 data-schemas skill.spec.ts - 34 packages/api permissions.spec.ts - 25 api skills.test.js - 16 client unit tests (9 buildTree + 7 useSkillPermissions) - All type-checks + eslint clean on touched files * 🧹 fix: Skills Duplication, Input Styling, Remove LLM-specific Copy Three UI fixes from an in-chat review pass: 1. **Sidebar duplication** — `SkillsView` was rendering its own `SkillsSidePanel` aside alongside the chat side panel's `SkillsAccordion`, so on `/skills` the user saw the skill list twice. Fixed by mirroring the `InlinePromptsView` pattern: the route content is now just the detail / create panel and the chat side panel is the sole list. Added `/skills → /skills/new` redirect and a `/skills/new` literal route so `useParams().skillId` is `undefined` for "new" (matches prompts). 2. **Name Input styling** — the big floating-label pattern used by prompts/agents for the primary name field was replaced with a conventional `<Label>` + `<Input>` above it, diverging from the rest of the app. Restored the prompts-style `text-2xl` input with the peer-focus animated label on both `CreateSkillForm` and `SkillForm`. Kept the conventional pattern for description and body since they're textareas. 3. **Remove LLM-specific copy from skill translations** — dropped `com_ui_skill_description_help` ("Claude uses this to...") and the transitional "This is what the model reads..." phrasing. Field hint is now a neutral "Be specific about when this skill should apply." and the create-page subtitle is a neutral "Author a new skill your agents can invoke." LibreChat is LLM-agnostic; baking product names into user-facing copy is wrong outside the `com_endpoint_anthropic_*` keys where the setting actually only applies to Claude models. Side-effect: the `SkillDetailView` wrapper in `SkillsView` now only renders the file-tree aside when the skill has > 0 files — same conditional-tree behavior as before, just scoped to this route instead of also trying to also render a list sidebar. - 16 client skill tests still pass - Type-check + eslint clean on touched files * 🎁 feat: Restore Skills UI from PR #12580 Brings back everything the original UI PR (#12580, commit da039917c) shipped that my earlier rebase dropped. Verbatim restores where possible; adapts the new hooks/types where the backend contract has shifted. **Scoped-out / gated-off (now restored as inert UI scaffolding):** - `hooks/useSkillFavorites.ts` + `utils/favoritesError.ts` + the `useGetSkillFavoritesQuery` / `useUpdateSkillFavoritesMutation` additions in `data-provider/Favorites.ts`. The backend route doesn't exist yet — the data-service functions resolve with empty arrays so the Star UI is a visual-only no-op until phase 2. - `dialogs/SkillSelectDialog.tsx` + the "Add Skills" section in `SidePanel/Agents/AgentConfig.tsx` (still gated behind the original `false &&`) + `skills?: string[]` on `AgentForm` / `Agent` / `AgentCreateParams` / `AgentUpdateParams` + the `skills: []` entry in `defaultAgentFormValues`. - `TUserFavorite.skillId` reserved on the shared favorites type. **Concept-is-gone / deleted-types (restored as UI-only types + stubs):** - `InvocationMode` enum and `TSkillNode`, `TSkillTreeResponse`, `TCreateSkillNodeRequest`, `TUpdateSkillNodeRequest` types in `packages/data-provider/src/types.ts`. UI-facing only; the backend flat `TSkillFile[]` contract is unchanged. - `TSkill.invocationMode?: InvocationMode` as an optional field. Forms read/write it in local state and deliberately drop it from the PATCH payload until the backend column lands. - `tree/SkillFileTree.tsx` (`react-arborist`-based), `SkillTreeNode.tsx`, `TreeToolbar.tsx`, `SkillFileEditor.tsx`, `SkillFilePreview.tsx` — full filesystem-style browser UI restored verbatim. - `data-provider/Skills/tree-queries.ts` + `tree-mutations.ts` hooks (`useGetSkillTreeQuery`, `useCreateSkillNodeMutation`, etc.). The `data-service` stubs them: `getSkillTree` returns `{ nodes: [] }`, `createSkillNode` / `updateSkillNode` / `updateSkillNodeContent` return synthetic node shapes, `deleteSkillNode` resolves void. Hooks compile and run; tree is empty until phase 2 wires a real backend. - `MutationKeys.createSkillNode` / `updateSkillNode` / `deleteSkillNode` / `updateSkillNodeContent` + `CreateSkillNodeBody` / `UpdateSkillNodeVariables` / `DeleteSkillNodeBody` / `UpdateSkillNodeContentVariables` types. - `QueryKeys.skillTree` / `skillNodeContent` / `skillFavorites` / `favorites` and the `skillTree()` endpoint helper. **Scope-simplified (restored with minimal adaptation):** - `display/SkillDetailHeader.tsx` + `display/SkillDetail.tsx`. Header now falls back to `InvocationMode.auto` when `skill.invocationMode` is undefined. - `forms/SkillContentEditor.tsx` — click-to-edit markdown preview toggle for the SKILL.md body field. Wired into both `CreateSkillForm` and `SkillForm` replacing the plain `<TextareaAutosize>`. (Needed `@ts-ignore` on `remarkPlugins` / `rehypePlugins` for the same `PluggableList` vs `Pluggable[]` shape drift `MarkdownLite.tsx` already works around.) - `forms/InvocationModePicker.tsx` + `forms/CategorySelector.tsx` — the auto/manual/both dropdown and the skill category selector. Wired into both forms inside a `FormProvider` so the Controller-based widgets can read `useFormContext`. `category` flows to the PATCH / POST payload as before; `invocationMode` is UI-only per the type note above. - `buttons/CreateSkillMenu.tsx` + `utils/parseSkillMd.ts` — dropdown with AI / Manual / Upload SKILL.md entries + the YAML frontmatter parser for the upload path. `CreateSkillForm.defaultValues` now accepts the parsed shape, so the upload → redirect → pre-populated form flow works again. - `buttons/AdminSettings.tsx` — admin permissions dialog. Uses the existing `useUpdateSkillPermissionsMutation` which was already wired. - `sidebar/FilterSkills.tsx` — restored filter + AdminSettings + CreateSkillMenu wrapper. `SkillsSidePanel.tsx` is back to the original `FilterSkills`-based layout. - `lists/SkillList.tsx` + `lists/SkillListItem.tsx` — restored verbatim. - `layouts/SkillsView.tsx` — restored the full tree + file editor + file preview layout. The chat side panel keeps its own accordion list; this view is the inline detail experience. - `hooks/Generic/useUnsavedChangesPrompt.ts` — route-leave guard hook. - `useGetSkillByIdQuery` is aliased to `useGetSkillQuery` so restored components (`SkillsView`, `SkillForm`) that import the old name resolve to the new hook. - `SkillSelectDialog` + `AgentConfig` coerce `skillsData?.skills` instead of `.data` (list response shape drift from the CRUD PR). - `CreateSkillForm` / `SkillForm` wrap their JSX in `FormProvider` so the restored `CategorySelector` and `SkillContentEditor` components — which read `useFormContext` — work inside the existing forms without another refactor. - `CreateSkillForm.defaultValues` prop accepts `Partial<Values> & { invocationMode?: unknown }` so the upload flow's `{ name, description, invocationMode }` shape passes through cleanly. - `SkillsView` route map gains `/skills/:skillId/edit` and `/skills/:skillId/file/:nodeId` so the tree-navigation URLs the original view produces actually resolve. - `client/package.json` gains `react-arborist@^3.4.3`. - ~60 translation keys the restored files reference — invocation labels, edit/create page titles, file editor chrome, tree toolbar tooltips, favorites, admin allow-settings, unknown-file-type, sr_public_skill, delete/rename _var variants — all added to `en/translation.json`. - Prompts-style floating-label name input — kept from my earlier commit so it matches the rest of the app (user reviewed and approved that styling). Hidden skill-body textarea is replaced by `SkillContentEditor` in both forms. - 38 data-schemas skill.spec.ts - 34 packages/api permissions.spec.ts - 25 api skills.test.js - 7 client useSkillPermissions.test.ts - Type-check: pre-existing error count (188) dropped to 120 because my restorations fixed some previously-broken field types. * chore: Update package-lock.json to include react-arborist and memoize-one * feat: Add support for react-arborist in Vite configuration This update introduces a new condition in the Vite configuration to handle the 'react-arborist' package, ensuring it is properly recognized during the build process. This change enhances compatibility with the recently added 'react-arborist' dependency in the project. * 🩹 fix: Hide InvocationMode, Fix SkillContentEditor Click-to-Edit 1. Hide InvocationModePicker from both CreateSkillForm and SkillForm. Component stays on disk for when the backend lands the column. 2. Fix "Click to edit" doing nothing on SkillContentEditor. The `onBlur={() => setIsEditing(false)}` on the TextareaAutosize was racing with `autoFocus` — React renders the textarea, autoFocus fires, then a layout/reconciliation blur fires immediately, bouncing back to preview mode before the user can interact. Removed onBlur; users toggle via the header button or Escape key. * 🎨 feat: Reader-First Skills UI — Match Claude.ai Layout Reworks the Skills UI from form-first to reader-first, matching Claude.ai's skill detail pattern. **Default view is now read-only.** Clicking a skill in the sidebar navigates to `/skills/:id` which renders `SkillDetail` — a clean content view with: - Skill name as the primary heading - Metadata row: "Added by" + "Last updated" (formatted date) - Description block - Rendered SKILL.md body in a bordered card with a source/rendered toggle (eye + code icons, matching Claude.ai's segmented control) No form fields, no save/cancel buttons. The user reads the skill first and takes action deliberately. **Create is now a dialog.** The `/skills/new` route is gone. `CreateSkillMenu` (the + dropdown in the sidebar) now opens `CreateSkillDialog` — a minimal modal with name, description, and instructions fields. Upload-from-file still works: parse → populate dialog → create. Matches Claude.ai's "Write skill instructions" modal. **Edit is behind an action.** The detail view shows an "Edit" button (permission-gated) that navigates to `/skills/:id/edit`, rendering the existing `SkillForm`. The edit route is preserved for direct linking. **Navigation goes to detail, not edit.** `SkillListItem` now navigates to `/skills/:id` (detail) instead of `/skills/:id/edit`. - `display/SkillMarkdownRenderer.tsx` — shared ReactMarkdown component extracted from `SkillContentEditor`. Same remark/rehype plugins, no form dependency. - `display/SkillDetail.tsx` — the reader-first view (replaces the old thin wrapper). - `dialogs/CreateSkillDialog.tsx` — OGDialog modal for skill creation. - `layouts/SkillsView.tsx` — gutted and rebuilt. Three states: no-skill (empty state), skillId (SkillDetail), skillId+edit (SkillForm). Removed full-page CreateSkillForm, removed TreeView. - `buttons/CreateSkillMenu.tsx` — opens dialog instead of navigating to `/skills/new`. Upload flow: parse → set dialog defaults → open. - `lists/SkillListItem.tsx` — navigate to detail, not edit. - `routes/index.tsx` — removed `/skills/new` and file/nodeId routes; `/skills` renders SkillsView directly (empty state). - `display/index.ts`, `dialogs/index.ts` — added new exports. - `locales/en/translation.json` — added ~10 new keys for metadata, toggle labels, dialog title, empty state. * 🩹 fix: SkillContentEditor click-to-edit z-index — button was z-0 behind rendered content * 🩹 fix: Align Edit button size with Share/Delete (size-9) * 🎨 feat: Claude.ai-Style Skill List Panel Rewrites the skills sidebar to match Claude.ai's panel layout: - Header: "Skills" title + search icon (toggles input) + add icon (opens CreateSkillDialog directly, no dropdown menu) - Collapsible "Skills" section with chevron toggle - Skill items: 24px icon badge (rounded square with ScrollText icon) + name only. No description text in the list — that lives in the detail view. Active item gets highlighted bg + bold font. - Removed AdminSettings button from sidebar header — admin config is accessible via the admin dashboard, not cluttering every user's skill list. - Removed FilterSkills wrapper (was Filter + AdminSettings + CreateSkillMenu). The search + create are now inline in the panel header. Files changed: - sidebar/SkillsSidePanel.tsx — full rewrite - sidebar/SkillsAccordion.tsx — simplified wrapper - lists/SkillList.tsx — collapsible section, no description - lists/SkillListItem.tsx — icon badge + name, memo'd * 🎨 fix: Align Skills UI Styling with Prompts Patterns Style alignment pass based on direct comparison with claude.ai and the existing prompts preview dialog. SkillsSidePanel search now replaces the title in the header row when toggled (search icon + input + X close), matching Claude.ai's pattern. Previously it pushed a separate input below the header, wasting vertical space. Close button clears the search term. Replaced `text-text-tertiary` with `text-text-secondary` across SkillDetail, SkillList, SkillForm, CreateSkillForm, CreateSkillDialog, SkillContentEditor. Tertiary was too dark / low contrast. SkillList section chevron label now reads "Personal skills" (matching Claude.ai) via the existing `com_ui_my_skills` key, instead of the generic "Skills" which duplicated the header. Aligned with `PromptDetailHeader` styling: - 48px round icon (ScrollText in bg-surface-secondary circle) - Name + public badge in the icon row - Metadata below the icon: User icon + author, Calendar icon + date (text-xs text-text-secondary with gap-3, matching prompts exactly) - Description uses the same label-above-text pattern as prompts - Content card uses `bg-transparent` border (not bg-surface-primary-alt) - Toggle buttons use size-5 icons and text-text-secondary for inactive Changed from `max-w-lg p-0` to `max-w-5xl` with the same max-height and padding pattern as the prompts PreviewPrompt dialog: `max-h-[80vh] p-1 sm:p-2 gap-3 sm:gap-4`. Close button now renders via default OGDialogContent behavior (removed showCloseButton=false). * 🩹 fix: SkillDetail fills parent height, tighter spacing (px-6 pb-6 gap-2) * 🩹 fix: Align Skills panel header padding (px-4) with list content below * 🩹 fix: Reduce Skills header top padding (pt-2) to align with sidebar icon strip * 🩹 fix: Tighten Skills header (py-2) and detail top (py-2) to align with sidebar icons and match edit view * 🩹 fix: Offset SidePanel Nav pt-2 with -mt-2 on SkillsAccordion so Skills header aligns with icon strip * 🛠️ fix: Increase Node memory limit for production build in package.json * 🩹 fix: Remove top padding from SkillDetail header row (py-2 → pb-2) * 🏗️ refactor: Move pt-2 from SidePanel/Nav wrapper to each panel Removed the global `pt-2` from `SidePanel/Nav.tsx` and pushed it into each panel's own top-level wrapper. This lets each panel own its vertical alignment independently — Skills can sit flush at the top to align with the sidebar icon strip, while other panels keep their original spacing. Panels updated with `pt-2`: - PromptsAccordion (via className on PromptSidePanel) - BookmarkPanel - FilesPanel - MemoryPanel - MCPBuilderPanel - AgentPanel (form wrapper) - AssistantPanel (form wrapper) - ParametersPanel (already had pt-2) SkillsAccordion: removed the -mt-2 hack, now naturally flush. * 🧹 fix: Align CreateSkillDialog field styling + remove 19 unused i18n keys Dialog fields: all three inputs now use consistent `rounded-xl border-border-medium px-3 py-2 text-sm` styling. Replaced the `<Input>` component with a plain `<input>` to avoid the component's built-in `rounded-lg border-border-light` overriding the dialog's border style. Labels use `font-medium` for consistency. Removed 19 unused translation keys from translation.json: com_ui_skill_body, com_ui_skill_body_placeholder, com_ui_skill_create_subtitle, com_ui_skill_file_delete_confirm, com_ui_skill_file_delete_error, com_ui_skill_file_deleted, com_ui_skill_files_empty, com_ui_skill_files_multi_hint, com_ui_skill_list, com_ui_skill_load_error, com_ui_skill_resize_file_tree, com_ui_skill_select_file, com_ui_skill_select_file_desc, com_ui_skills_load_error, com_ui_add_first_skill, com_ui_create_skill_page, com_ui_edit_skill_page, com_ui_save_skill, com_ui_no_skills_title * 🎁 feat: Upload Skill Dialog + Simplified Create Menu New `UploadSkillDialog` matching Claude.ai's upload modal: - Dashed drop zone with drag-and-drop support - Accepts .md, .zip, .skill files - Phase 1: processes .md files (parses YAML frontmatter → creates skill with body as the full file content) - Shows file requirements below the drop zone - On success: navigates to the new skill's detail view `CreateSkillMenu` now has two flat options (no sub-menu): - "Write skill instructions" → opens `CreateSkillDialog` - "Upload a skill" → opens `UploadSkillDialog` Removed the disabled "Create with AI" option and the old file input hidden-element approach. The sidebar `+` button now renders `CreateSkillMenu` directly instead of a standalone create dialog. - Removed 5 unused i18n keys (com_ui_skill_added_by, com_ui_skill_last_updated, com_ui_skills_add_first, com_ui_skills_filter_placeholder, com_ui_skills_new) - Tightened metadata gap in SkillDetail (mt-1 → mt-0.5) - Added 7 new upload-related i18n keys * 🔒 feat: Zip/Skill File Upload Support with Safety Limits Rewrites UploadSkillDialog to properly handle all three accepted file types: - `.md` — reads as text, parses YAML frontmatter, creates skill - `.zip` / `.skill` — reads as ArrayBuffer, extracts with JSZip, finds SKILL.md (at root or one level deep), parses its content, creates skill. Shows spinner during processing. Security guards against zip bombs: - MAX_ZIP_SIZE: 50MB compressed file limit - MAX_ENTRIES: 500 file limit inside the archive - Path traversal rejection: skips entries with `..` or leading `/` - SKILL.md search limited to depth ≤ 2 segments Added `jszip@^3.10.1` to client dependencies (already in the monorepo's node_modules from backend usage). The name is inferred from the zip filename if SKILL.md frontmatter doesn't have one (e.g. `skills-autofix.zip` → `skills-autofix`). * 🚀 feat: Backend Skill Import + Live File Upload Endpoints New endpoint that accepts a single multipart file (.md, .zip, .skill) and creates a skill with all its files in one request: - **.md**: parse YAML frontmatter → create skill with body - **.zip / .skill**: extract with JSZip, find SKILL.md (root or one level deep), create skill from its content, then persist every additional file via `upsertSkillFile` + local file storage strategy. Returns the created skill + an `_importSummary` with per-file results. Security: - 50MB compressed file size limit (multer) - 500 max entries in archive - 10MB per individual file - Path traversal rejection (no `..`, no absolute, validated charset) - File type filter: only .md/.zip/.skill accepted - Rate limited via existing `fileUploadIpLimiter` + `fileUploadUserLimiter` Handler lives in `packages/api/src/skills/import.ts` with injectable deps (`createSkill`, `upsertSkillFile`, `saveBuffer`) for testability. Replaced the 501 stub with a real handler: - Accepts multipart FormData with `file` + `relativePath` - Saves file via local storage strategy - Calls `upsertSkillFile` to persist the SkillFile record - Returns the upserted document - Rate limited, ACL-gated (EDIT permission required) - 10MB per file limit `UploadSkillDialog` now sends the file to `/api/skills/import` via `dataService.importSkill(formData)` — no more client-side JSZip. Removed `jszip` from client dependencies (only backend needs it). Added `importSkill()` in data-service + `importSkill()` endpoint builder in api-endpoints. Updated the file upload test from expecting 501 stub to expecting 400 "no file provided" (live validation). All 25 skill route tests pass. * 🔒 fix: Complete Import Handler — Validation, Ownership, Error Surfacing Fixes several gaps in the skill import flow: 1. **Skill validation now runs and surfaces properly.** The import handler calls the real `createSkill(CreateSkillInput)` which runs `validateSkillName`, `validateSkillDescription`, `validateSkillBody`. Validation errors (SKILL_VALIDATION_FAILED) are caught and returned as 400 with the issue messages. Duplicate-key errors return 409. Previously all errors were swallowed into a generic 500. 2. **`authorName` is now populated.** The `CreateSkillInput` requires `authorName` which was missing — resolved from `req.user.name ?? req.user.username ?? 'Unknown'`, matching the existing create handler. 3. **SKILL_OWNER permission is granted after import.** Calls `grantPermission` with `AccessRoleIds.SKILL_OWNER` so the uploader can edit/delete/share the imported skill. This was entirely missing — imported skills would have been ownerless. 4. **`tenantId` propagated.** Both the skill and each SkillFile record receive `req.user.tenantId` for multi-tenant deployments. 5. **SkillFile records are created in the DB.** Each non-SKILL.md file in the zip is saved to file storage via `saveBuffer` and recorded via `upsertSkillFile`, which validates the relativePath, infers the category from the path prefix, and atomically bumps the skill's `fileCount` and `version`. Import deps now include `grantPermission` from PermissionService, injected in `api/server/routes/skills.js`. * 🐛 fix: Import grant uses accessRoleId (not roleId) — fixes skill not appearing in list * 🎨 fix: Cache invalidation, file tree, frontmatter rendering Three fixes for the skill detail view: 1. **Cache invalidation after import.** UploadSkillDialog now calls `queryClient.invalidateQueries([QueryKeys.skills])` after a successful import so the sidebar list picks up the new skill without requiring a page refresh. 2. **File tree in detail view.** When a skill has `fileCount > 0`, the detail view now queries `useListSkillFilesQuery` and renders a file list below the body card — SKILL.md first, then folders and root files. Icons: Folder for directories, FileText for files. 3. **Frontmatter stripped and rendered as metadata.** YAML frontmatter (`---\nversion: 0.1.0\ntriggers: ...\n---`) is now parsed out of the body before markdown rendering. The `name` and `description` fields are skipped (already shown in the header). Remaining fields (version, triggers, dependencies, etc.) are displayed in a Claude.ai–style grid: label on the left, value on the right, above the rendered markdown content. Source view still shows the full raw body including frontmatter. * 🩹 fix: Always fetch skill files — fileCount may be stale in cached skill object * 🌳 feat: Inline File Tree in Sidebar Skill List Moves the file tree from the bottom of SkillDetail into the sidebar list, matching Claude.ai's pattern: - Multi-file skills show a chevron toggle on the right side of the skill list item - Clicking the chevron expands an inline file tree below the skill name: SKILL.md first, then folders (with folder icon + right chevron) and root files - File list is fetched lazily (only when expanded) via useListSkillFilesQuery - Clicking a file navigates to the skill detail view - Files section removed from SkillDetail — the sidebar is now the sole file tree location, keeping the detail panel clean SkillDetail cleaned up: removed groupFiles helper, file-related state, useListSkillFilesQuery import, FileText/Folder icon imports. * 🌲 feat: Virtualized inline file tree with react-vtree Replace hand-rolled recursive FolderRow/FileRow buttons with a proper virtualized FixedSizeTree from react-vtree for the sidebar skill list. Dynamic height tracks open folders; capped at 350px with smooth expand/collapse transitions. * chore: Remove no longer used SkillFileTree and SkillTreeNode components * chore: Update Vite config to replace 'react-arborist' with 'react-vtree' for module resolution * feat: Skill file content viewing with lazy DB caching - Add `skills` field to `fileStrategiesSchema` so operators can configure a dedicated storage backend for skill files. Falls back by type (image/document) when unset. - Fix hardcoded `FileSources.local` in skill save/import — now uses the resolved strategy via `getFileStrategy(req.config, { context })`. - Replace 501 download stub with real handler that streams from any storage backend and returns JSON `{ content, mimeType, isBinary }`. - Binary detection (null-byte + non-printable ratio on first 8 KB) flags files on first read so they're never re-fetched. - Text content ≤ 512 KB is cached in the SkillFile MongoDB document; subsequent reads skip storage entirely. - Clicking a skill row now expands inline files (not just chevron). - Clicking a file navigates to `?file=<path>` and renders content in a new SkillFileViewer (markdown, code, images, binary placeholder). * chore: Remove react-window and its type definitions from package.json and package-lock.json - Deleted `react-window` and `@types/react-window` dependencies from both `package.json` and `package-lock.json` to streamline the project and reduce unnecessary bloat. * fix: Build errors — remove endpoints import, fix Uint8Array cast - Replace `import { endpoints }` (not public) with inline URL in SkillFileViewer - Remove `as Uint8Array` cast in stream chunk handling - Extend getSkillFileByPath return type with content/isBinary to decouple from data-schemas build artifact resolution * chore: Remove 8 unused i18next keys com_ui_create_skill_ai, com_ui_create_skill_manual, com_ui_delete_folder_confirm_var, com_ui_delete_skill, com_ui_delete_skill_confirm_var, com_ui_delete_var, com_ui_rename_var, com_ui_skill_files * fix: Add configMiddleware to skills router, handle SKILL.md in viewer - Add configMiddleware to skills router so req.config is populated when getLocalFileStream (or any strategy) reads file paths. - Handle SKILL.md in download handler — serves skill.body directly from the Skill document instead of looking for a SkillFile record. - Clicking SKILL.md in sidebar tree now opens the file viewer (matching Claude.ai behavior: file view vs default detail view). * ci: Run unit tests on PRs to any branch Remove the branches filter from both test workflows so contributor PRs targeting feature branches (not just main/dev) get CI coverage. Path filters are kept so tests only run when relevant files change. * fix: Update skills route tests for download handler changes - Mock configMiddleware (sets req.config for file storage access) - Mock getStrategyFunctions and getFileStrategy (storage strategy deps) - Replace 501 stub test with SKILL.md content test + 404 test * fix: Auto-expand files, frontmatter parsing, select-none, prefetch - Auto-expand file tree when navigating directly to a skill URL - Prefetch files for the active skill (eliminates first-expand lag) - Fix frontmatter parser to handle multi-line YAML list values (triggers field was missing because it uses list syntax) - SkillFileViewer now parses frontmatter for .md files — shows structured grid + rendered body (matching SkillDetail's display) with source/rendered toggle - Add select-none to all sidebar skill and file tree buttons * refactor: Derive expanded state from isActive instead of useEffect Replace useEffect sync with deterministic derivation: expanded = hasFiles && (isActive || !collapsed) Active skill is always open. collapsed is a manual toggle that only takes effect on non-active items. * fix: Remove empty space above body card — overlay view toggle Move the rendered/source toggle from a dedicated row (40px of empty space) to an absolute-positioned overlay in the card's top-right corner, matching Claude.ai's layout. * fix: Remove header bars from content editors — overlay action buttons Collapse the full-width header bars ("Skill Content", "Text") in SkillContentEditor, PromptTextCard, and PromptEditor. Action buttons (edit/save toggle, copy, variables) are now absolute-positioned in the card's top-right corner, reclaiming ~46px of vertical space. * fix: Spinner visibility in file viewer — use text-text-secondary * fix: Address review findings — security, correctness, code quality Codex P1: Use $unset instead of undefined to clear cached content and isBinary fields on file re-upload (Mongoose strips undefined). Codex P2: Match skill-file validation errors by error.code instead of error.message substring. F1: Zip bomb defense — track cumulative decompressed bytes (500 MB cap), check declared uncompressed size before buffering each entry. F2: Remove misleading "atomically" from import handler JSDoc. F3: Static import for isBinaryBuffer instead of dynamic import(). F4: Replace console.error with logger in upload handler. F6: Add multer error handler middleware to skills router. F7: Move React import to top of SkillDetail.tsx. F9: Fix variable shadowing (trimmed → item) in parseFrontmatter. F11: Replace JSON.parse(JSON.stringify()) with toJSON() for Mongoose document serialization. F12: Remove dead dynamic import('fs') fallback (memoryStorage always provides file.buffer). F13: Hoist MIME_MAP to module scope to avoid per-call allocation. F16: Share single multer.memoryStorage() instance. * fix: Follow-up review — close zip bomb gap, fix error handler F1: Add post-decompression cumulative byte check with break (the pre-decompression check relies on undocumented JSZip internals that may be absent; this closes the gap unconditionally). F2+F3: Multer error handler now forwards non-multer errors via next(err) instead of swallowing them. Also catches file filter rejections (plain Error, not MulterError) by message prefix. F4: Move isBinaryBuffer import to local imports section per CLAUDE.md import order rules. F5: Simplify dead toJSON branch — createSkill returns a POJO. * nit: Link filter error message to handler prefix check * feat: Accordion expansion + active file highlight in sidebar - Only one skill's file tree can be expanded at a time (accordion). Expansion state lifted from SkillListItem to SkillList. - Selected file gets bg-surface-active highlight in the tree. Skill row uses subtle style (no background) when a file is active, matching Claude.ai's pattern where the file — not the skill — carries the selection state. * style: Adjust margin for file tree in SkillListItem component - Reduced left margin from 10 to 5 for improved layout consistency in the file tree display. * fix: TS error on FileTreeNode, nested ternary, chevron collapse - Make style prop optional to match react-vtree's NodeComponentProps - Flatten nested ternary for skill row active styles - Skill row click expands (but doesn't collapse) files + navigates - Chevron click explicitly toggles collapse (matching Claude.ai where clicking the chevron is how you collapse files) * fix: Upload basePath, reject SKILL.md uploads, add skills permission route - Pass basePath: 'uploads' in per-file upload handler (was defaulting to 'images' path, inconsistent with the import flow). - Reject uploads targeting SKILL.md (reserved path — download handler special-cases it to return skill.body, making an uploaded file unreachable via the API). - Add skills entry to roles router permissionConfigs so PUT /api/roles/:roleName/skills actually reaches a handler instead of returning 404. * feat: Expand content area, move controls to header, reduce padding Default detail view: - Remove rounded-xl bordered card wrapper — content flows directly into the article, capitalizing on full screen width - Move eye/code toggle inline with the divider row - Reduce px-6/pb-6 to px-4/pb-4 File viewer: - Move eye/code toggle from card overlay to the header bar - Add copy-to-clipboard button for text files in the header bar - Remove rounded-xl bordered card wrapper for markdown content - Remove bordered pre wrapper for non-markdown text - Reduce px-6/py-4 to px-4/py-3 Both views maximize content space over decorative chrome. * fix: Stable header height, restore some padding - Fix layout shift in file viewer header: use fixed h-10 so the bar height stays constant whether the eye/code toggle renders (markdown) or not (plain text). - Bump content padding from px-4/py-3 back to px-5/py-4 in both views — the previous reduction was too aggressive. * fix: Grant rollback, path validation, error format, dead code cleanup F2: grantOwnership now rolls back (compensating delete) on failure, matching the create handler. Both markdown and zip import paths check the result and return 500 on grant failure. F4: Upload handler validates relativePath with regex + traversal check before calling downstream upsertSkillFile. F5: Document JSZip _data.uncompressedSize as best-effort; the post-decompression cumulative check is the real safety net. F10: Standardize all upload handler error responses to { error } (was { message }, inconsistent with handlers.ts). F13: Single-pass fileResults accumulation in import handler. F1-5: Remove dead uploadFileStubHandler (no route references it). Codex P2: Fix delete nav from /skills/new to /skills. F12: Use cn() in UploadSkillDialog instead of template literals. * perf: Stream-first binary detection + O(1) public skill check F1: Download handler now reads only the first 8 KB for binary detection. If binary, the stream is destroyed immediately without buffering the remaining file. Text files continue reading for caching. Eliminates buffering up to 10 MB per request for binary files under concurrent load. F7: Single-skill GET and PATCH now use hasPublicPermission (O(1) ACL lookup) instead of getPublicSkillIdSet (queries ALL public skill IDs). The list handler still uses the Set approach since it serializes multiple skills. serializeSkill/serializeSkillSummary now accept boolean | Set for flexibility. * fix: Update test to match { error } response format * fix: Critical stream truncation bug, grantedBy, error format NF-1 (CRITICAL): Rewrite binary detection to single for-await loop. Breaking out of for-await-of destroys the stream via iterator.return(), so the previous two-loop approach silently truncated text files > 8KB. Now: one loop collects chunks, checks binary after 8KB accumulated, and either destroys+returns (binary) or continues reading (text). NF-2: Add grantedBy to import handler's grantPermission call and interface (was missing, inconsistent with create handler). NF-3: Standardize all import handler error responses from { message } to { error }, matching handlers.ts convention. Update client's UploadSkillDialog to read response.data.error accordingly. * fix: Prefer specific validation message over generic error field * fix: YAML quote stripping, saveBuffer null guard, dot segment rejection - Strip surrounding YAML quotes from frontmatter values so name: "my-skill" parses as my-skill (not "my-skill" with quotes that fails the name validator). - Guard resolveSkillStorage against backends with saveBuffer: null (e.g. OpenAI/vector strategies) — throws a descriptive error caught by the handler's try/catch instead of a TypeError. - Tighten upload path validation to reject . segments (e.g. docs/./a.md) matching the model-layer validator, preventing storage writes for paths the DB will reject. * fix: Orphan cleanup, stream errors, malformed zip, cache latency F1: Upload handler now deletes the stored blob if the subsequent DB upsert fails, preventing orphaned files on disk/cloud. F2: Multer error handler returns { error } (was { message }). F3: Wrap JSZip.loadAsync in try/catch — malformed zip returns 400 instead of falling through to 500. F4: Raw download stream gets an error handler — logs the error and destroys the response if headers were already sent. F8: Strip leading hyphens from inferred skill name so filenames like _my-skill.zip don't produce -my-skill (invalid name pattern). F9: Fire-and-forget all updateSkillFileContent cache writes so the response is sent immediately. Cache failures are logged but don't block or fail the read. * fix: Import orphan cleanup + Content-Disposition sanitization Finding A: Add deleteFile dep to ImportSkillDeps. The per-file loop in handleZip now cleans up stored blobs when upsertSkillFile fails, closing the second half of the F1 orphan fix (upload handler was already fixed). Finding B: Sanitize filename in Content-Disposition header for raw downloads — strip quotes, backslashes, and newlines to prevent header injection from user-uploaded filenames. * security: Prevent stored XSS via raw file downloads Non-image files served via ?raw=true now use Content-Disposition: attachment (force download) instead of inline. An uploaded .html or .svg file served inline from the LibreChat origin could execute scripts with access to the user's session — this closes that vector. Images stay inline (needed for <img> rendering in SkillFileViewer). X-Content-Type-Options: nosniff added to prevent MIME sniffing. * security: Block SVG XSS — allowlist safe raster MIME types for inline SVG (image/svg+xml) passed the startsWith('image/') check and was served inline, but SVG is a scriptable format — embedded <script> tags execute in the LibreChat origin. Replace the prefix match with a Set of safe raster-only MIME types (png, jpeg, gif, webp, avif, bmp). SVGs and any future scriptable image/* subtypes now get Content-Disposition: attachment (forced download). * fix: Cap JSON text response at 1MB, consistent md name inference F3: Text files > 1MB now return { isBinary: false } with no content field, forcing the client to use ?raw=true for download. Prevents buffering 10MB files into heap for JSON serialization. Frontend shows a download fallback when content is absent. F4: handleMarkdown now infers skill name from filename (same as handleZip) when frontmatter has no name, instead of rejecting with 400. Consistent behavior across import paths. F1 (reviewer concern): upsertSkillFile is NOT affected — it uses { new: false } for insert-vs-replace detection but does a follow-up findOne (lines 855-859) to return the post-upsert document. * fix: deleteFile arg shape, raw URL base path, hoist SAFE_INLINE_MIMES Codex P2: deleteFile expects { filepath } object, not a raw string. Both upload handler cleanup and import handler cleanup now pass { filepath } to match the strategy contract (deleteLocalFile, deleteFileFromS3 all expect a file object). Codex P2: Raw download URL in SkillFileViewer now uses apiBaseUrl prefix so subpath deployments (/chat, etc.) resolve correctly. NIT: Hoist SAFE_INLINE_MIMES Set to factory scope — was re-allocated per raw download request inside the if block. * fix: Remove inert cache write for large text files, localize aria-label N2: The { isBinary: false } cache write for text files > 1MB had no effect — subsequent requests still fell through to stream read since neither isBinary nor content provided a fast-path short-circuit. Removed the pointless DB updateOne per request. N4: Replace hardcoded "Back to skill" aria-label with localize(). * refactor: Extract shared parseFrontmatter, widen deleteFile type N3: Extract parseFrontmatter into Skills/utils/frontmatter.ts — single implementation shared by SkillDetail and SkillFileViewer. Accepts optional skipKeys set so callers control which frontmatter fields are excluded (SkillDetail skips name/description since they're shown in the header; other .md files show all fields). N5: Widen ImportSkillDeps.deleteFile file param from { filepath } to { filepath; [key: string]: unknown } to signal extensibility if strategies start accessing additional file properties. * fix: Advance i past list items for skipped keys, DRY parseSkillMd Finding A: parseFrontmatter now consumes multi-line YAML list items before checking skipKeys — prevents list lines from leaking into subsequent key parsing as spurious fields. Finding B: parseSkillMd now delegates to the shared parseFrontmatter instead of re-implementing the same frontmatter scanning loop. Reduces client-side parseFrontmatter implementations from 3 to 1. * fix: Call apiBaseUrl(), delete storage blob on file removal - apiBaseUrl is a function, not a string — call it in the template literal so raw download URLs resolve correctly. - deleteFileHandler now looks up the file record before deleting, then fire-and-forget deletes the storage blob via the strategy's deleteFile. Previously only the DB record was removed, leaving orphaned blobs in local/S3/Firebase/Azure storage. * fix: Clean up storage blobs when deleting an entire skill deleteHandler now lists all files for the skill before calling deleteSkill, then fire-and-forget deletes each blob via the storage strategy. Previously only per-file deletion cleaned up blobs — deleting a whole skill left all associated files orphaned in local/S3/Firebase/Azure storage. * refactor: useImportSkillMutation hook, fix TSkill[] unsafe cast - Create useImportSkillMutation in mutations.ts + ImportSkillOptions type. UploadSkillDialog now uses the mutation hook instead of calling dataService.importSkill directly with manual useState loading management. Eliminates unmounted-component state update risk and aligns with the React Query mutation pattern used by every other mutation in the codebase. - SkillSelectDialog: replace as unknown as TSkill[] with proper TSkillSummary typing. SkillCard props updated to TSkillSummary. The dialog only uses summary-level fields (name, description, category, author) — the cast was hiding a type mismatch. * fix: Use saved source for import cleanup, delete old blob on replace Codex P2: Import cleanup now uses file.source (the backend the file was actually saved to) instead of re-resolving from config. In mixed strategy setups, the previous approach could target the wrong backend. Codex P2: When re-uploading a file to an existing relativePath, the old blob is now deleted after successful upsert. Previously only the DB record was replaced, leaving the old storage object orphaned. * fix: Register PUT /:roleName/skills route in roles router * fix: Re-read skill after zip file processing for fresh metadata The import response was built from the skill object created before the file loop, but each upsertSkillFile bumps version and fileCount. Clients caching the stale response would get 409 conflicts on first edit and see incorrect file counts. Now re-reads the skill via getSkillById after the loop so the response reflects the current version, fileCount, and updatedAt. * fix: Size-check SKILL.md before decompression, don't gate on fileCount P1: SKILL.md was decompressed before any size accounting. A crafted archive could expand SKILL.md past 10MB before validation ran. Now checks declared size pre-decompression and actual size post, both against MAX_SINGLE_FILE_BYTES. P2: File list query was gated on cached fileCount which can be stale after mutations. Now fetches files for the active skill regardless of fileCount. hasFiles derived from fetched data with fileCount as fallback, so newly uploaded files appear without hard refresh. * fix: Move files declaration before hasFiles to avoid TDZ error * security: Stream-decompress zip entries with enforced byte cap Replace zipEntry.async('nodebuffer') (buffers entire entry before checking limits) with zipEntry.nodeStream('nodebuffer') piped through a byte counter that destroys the stream when the per-file or cumulative limit is exceeded. Previously, when JSZip's _data.uncompressedSize was absent (the common case), a high-ratio entry could allocate hundreds of MB before the post-decompression check caught it. Now decompression is aborted mid-stream at the exact byte threshold — no entry can exceed its limit regardless of compression ratio. * refactor: Reorganize access check for prompts in useSideNavLinks hook Moved the prompts access check to a new position in the code to improve readability and maintainability. This change ensures that the prompts link is added to the navigation only if the user has the appropriate access, without altering the existing functionality. --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2026-04-25 04:02:00 -04:00
Danny Avila	963068b112	🧬 feat: Scaffold Skills CRUD with ACL Sharing and File Schema (#12613) ... * 🧬 feat: Scaffold Skills CRUD with ACL Sharing and File Schema Adds Skills as a new first-class resource modeled on Anthropic's Agent Skills, reusing the existing Prompt ACL stack for sharing. Lays the groundwork for multi-file skills (SkillFile schema + metadata routes) without wiring upload processing — single-file skills (inline SKILL.md body) work end-to-end, multi-file uploads are stubbed for phase 2. * 🔬 fix: Wire Skill Cleanup, AccessRole Enum, and Express 5 Path Params CI surfaced four follow-ups from the initial Skills scaffolding commit that local builds missed: - AccessRole's resourceType field had a hardcoded enum that didn't include `'skill'`, blocking SKILL_OWNER/EDITOR/VIEWER role creation in every test that hit the AccessRole model. - The seedDefaultRoles assertion in accessRole.spec.ts hard-listed the expected role IDs and needed the new SKILL_* entries. - deleteUserController had no cleanup for skills, and the deleteUserResourceCoverage guard test enforces every ResourceType has a documented handler — wired in db.deleteUserSkills(user._id) and added the entry to HANDLED_RESOURCE_TYPES. - Express 5's path-to-regexp v6 rejects the legacy `(*)` named-group glob syntax. The two skill file routes now use a plain `:relativePath` param; the client already encodeURIComponents the path, so a single param is sufficient and decoded server-side. * 🪡 fix: Make Skill Name Uniqueness Application-Level Resolve three more CI failures from the Skills scaffolding PR: - Mongoose creates indexes asynchronously and mongodb-memory-server tests can race ahead of the unique (name, author, tenantId) index being built, so the duplicate-name uniqueness test was flaky. Added an explicit findOne pre-check inside createSkill that throws with code 11000 (mimicking the index violation), giving deterministic behavior. The unique index stays as the persistent guarantee. - The deleteUser.spec.js and UserController.spec.js suites mock the ~/models module directly and were missing deleteUserSkills, causing deleteUserController to throw and return 500 instead of 200. - Removed two doc-comment claims that the SKILL_NAME_MAX_LENGTH and SKILL_DESCRIPTION_MAX_LENGTH constants "match Anthropic's API". The values themselves are reasonable but the comments were misleading about who enforces them. * 🪢 fix: Address Code Review Findings on Skills Scaffolding Resolve all 15 findings from the comprehensive PR review: Critical: - Rollback the created skill when grantPermission throws so a transient ACL failure cannot leave an orphaned, inaccessible skill in the DB. - Fix infinite query cache corruption in useUpdateSkillMutation helpers. setQueriesData([QueryKeys.skills]) matches useSkillsInfiniteQuery's InfiniteData cache entries, which have { pages, pageParams } shape — spreading data.skills on those would throw. Added an isInfiniteSkillData guard and per-page transform so both flat and infinite caches update correctly. Major: - Fix TUpdateSkillContext type: the public type declared previousListData but onMutate actually returns previousListSnapshots (a [key, value] tuple array). Updated the type + added TSkillCacheEntry as a shared export from data-provider. - Add cancelQueries calls before optimistic update in onMutate so in-flight refetches cannot clobber the optimistic state. - Parallelize deleteUserSkills ACL removal via Promise.allSettled instead of a sequential await loop — O(1) round-trip vs O(n). - Stub mockDeleteUserSkills in stubDeletionMocks() and assert it's called with user.id in the deleteUser.spec.js happy-path test. - Add idResolver: getSkillById to the SKILL branch in accessPermissions.js so GET /api/permissions/skill/<missing-id> returns 404 instead of 403. Minor: - Reuse resolved skill from req.resourceAccess.resourceInfo in getHandler to eliminate a redundant getSkillById call per GET /api/skills/:id. - Reject PATCH /api/skills/:id requests whose body contains only expectedVersion — previously they silently bumped version with no changes, triggering spurious 409s for collaborators. - Make TSkill.frontmatter optional (wire type) and add serializeFrontmatter / serializeSourceMetadata helpers that return undefined for empty objects instead of casting incomplete data to SkillFrontmatter. - Standardize deleteUserSkills to accept string | ObjectId and convert internally, matching deleteUserPrompts's signature; UserController now passes user.id consistently. - Replace bumpSkillVersionAndRecount (read-then-write, racy) with bumpSkillVersionAndAdjustFileCount using atomic $inc. upsertSkillFile pre-checks existence to distinguish insert (+1) from replace (0). - Add DELETE /api/skills/:id/files/:relativePath integration tests covering success, 404, and 403 paths. Nits: - Drop trivial resolveSkillId wrapper — pass getSkillById directly. - Remove dead staleTime: 1000 * 10 from useListSkillsQuery since all refetch triggers are already disabled. * 🧭 fix: Resolve Second Skills Review Pass — Cache, Gate, TOCTOU Address 13 of 14 findings from the second code review; reject #13 as misread of the AGENTS.md import-order rule (package types correctly precede local types regardless of length). Major: - Fix addSkillToCachedLists closure bug: a hoisted `prepended` flag was shared across every cache entry matched by setQueriesData, so concurrent flat + infinite caches would silently drop the prepend on whichever was processed second. Replaced the shared helper with three per-entry inline updaters that handle InfiniteData at the page level (page 0 only for prepend, all pages for replace/remove). - Tighten patchHandler's expectedVersion validation: NaN passes `typeof === 'number'` and would previously leak current skill state via a misleading 409. Now requires finite positive integer and returns 400 otherwise. - Guard decodeURIComponent in deleteFileHandler with try/catch — malformed percent encoding now returns 400 instead of 500. - Add PermissionTypes.SKILLS + skillPermissionsSchema + TSkillPermissions in data-provider; seed default SKILLS permissions for ADMIN (all true) and USER (use + create only); wire checkSkillAccess / checkSkillCreate via generateCheckAccess onto the skills router mirroring the prompts pattern. Skills route now enforces role-based capability gates alongside per-resource ACLs. Test suite adds a mocked getRoleByName returning permissive SKILLS. - Fix upsertSkillFile TOCTOU: replaced the pre-check + upsert pair with a single `findOneAndUpdate({ new: false, upsert: true })` call that atomically returns the pre-update doc (null ⇒ insert) so fileCount delta can't double-count on concurrent same-path uploads. Minor: - Add `sourceMetadata` to listSkillsByAccess .select() so summaries no longer silently drop the field for GitHub/Notion-synced skills. - Include `cursor` in useListSkillsQuery's query key so manual pagination doesn't alias across pages. - Clean up TSkillSummary to `Omit<TSkill, 'body' | 'frontmatter'>` matching what serializeSkillSummary actually emits; drop the Omit-then-re-add noise. - Skip getPublicSkillIdSet in createHandler; a newly-created skill cannot have a PUBLIC ACL entry, so pass an empty set directly instead of paying a DB round-trip. - Trim SkillMethods public surface: drop internal helpers countSkillFiles / deleteSkillFilesBySkillId / getSkillFile from the return object; inline the file cascade into deleteSkill. - Use TSkillConflictResponse at the PATCH 409 call site instead of an inline ad-hoc object literal. - Drop the now-unused EXPECTED_VERSION_ERROR module constant. * 🧩 fix: Extend Role Schema + Types with SKILLS PermissionType CI type-check and unit test failures from the PermissionTypes.SKILLS addition surfaced three unrelated places that all hardcode the permission-type set: - IRole.permissions in data-schemas/types/role.ts enumerates every PermissionTypes key as an optional field. Adding SKILLS to the enum without updating the interface caused TS7053 'expression of type PermissionTypes can't be used to index type' errors in role.methods.spec.ts (lines 407-408, 477-478) because Object.values(PermissionTypes) now yielded a value the interface didn't cover. - schema/role.ts rolePermissionsSchema mirrors the interface at the Mongoose layer; also needed SKILLS added so the persisted role document can actually store skill permissions. - data-provider/roles.spec.ts has a guard test that every permission type carrying CREATE/SHARE/SHARE_PUBLIC must be explicitly "tracked" either in RESOURCE_PERMISSION_TYPES or in the PROMPTS/AGENTS/MEMORIES exemption list. Added SKILLS to the exemption list since skills follow the same default model as prompts/agents (USE + CREATE on for USER, SHARE / SHARE_PUBLIC off). All three are additive pass-throughs with no behavior change. * 🏷️ refactor: Introduce ISkillSummary for Narrow List Projection Follow-up NITs from the second review pass on the Skills PR: - Define ISkillSummary = Omit<ISkill, 'body' | 'frontmatter'> and use it as the element type in ListSkillsByAccessResult. The list query's .select() intentionally omits body and frontmatter for payload size, but the previous type claimed both fields were present — a type lie that would mislead future readers even though serializeSkillSummary never touches those fields at runtime. handlers.ts's signature for serializeSkillSummary now accepts ISkillSummary too. - Document the intentional second-round-trip `findOne` in upsertSkillFile. Switching to `findOneAndUpdate({ new: false })` was required for TOCTOU-safe insert-vs-replace detection, which means the handler needs a follow-up query to return the post-upsert document. A comment now explains the tradeoff so future readers don't silently "optimize" it away. No behavior change. * 🌐 fix: Wire SKILL into SHARE_PUBLIC Resource Maps Address codex comment #1 — making a skill public was blocked on two hardcoded resource→permission-type maps that didn't know about SKILL: - api/server/middleware/checkSharePublicAccess.js's resourceToPermissionType map was missing ResourceType.SKILL, so PUT /api/permissions/skill/:id with { public: true } would fall through to the 400 "Unsupported resource type for public sharing" path even though PermissionTypes.SKILLS exists and ADMIN has SHARE_PUBLIC configured. Added the mapping. - client/src/hooks/Sharing/useCanSharePublic.ts has an identical client-side map used to gate the "Make Public" UI toggle. Without the SKILL mapping the hook returned false for everyone, so the toggle wouldn't render for skills once the sharing UI lands in phase 2. Added the mapping. Codex comment #2 (create/update cache writes inject skills into unrelated filtered lists) is invalid — it flags a pattern that mirrors useUpdatePromptGroup (which the PR description explicitly cites as the model) and is a deliberate optimistic-update tradeoff. Trying to match each cache key's embedded filter would couple the mutation callback to query-key internals, which is exactly what setQueriesData is designed to avoid. No change there. * 🧪 feat: Frontmatter Validation, Reserved-Name Fixes, Coaching Warnings Address the follow-up review notes on the Skills PR. This commit closes the gap between the wire-type promise and what the backend actually enforces, tightens the reserved-name rules, and adds a non-blocking coaching tier for validators. Frontmatter validation (new): - Add `validateSkillFrontmatter` in data-schemas/methods/skill.ts with strict mode — unknown keys are rejected so expanding the allowed set is an intentional code change. Known keys are type-checked against a `FrontmatterKind` table derived from Anthropic's Agent Skills spec (name, description, when-to-use, allowed-tools, arguments, argument-hint, user-invocable, disable-model-invocation, model, effort, context, agent, paths, shell, hooks, version, metadata). - `hooks` and `metadata` get a shallow JSON-safety check (max depth 4, max string 2000, max array 100) instead of a full schema, since their full shapes live outside this module. - Wired into BOTH createSkill AND updateSkill so the PATCH path can't smuggle invalid frontmatter past the validator. Validation warning tier (new): - Add optional `severity: 'error' | 'warning'` to `ValidationIssue` (defaults to error). `partitionIssues` splits an issue list into blocking errors and non-blocking warnings. - `createSkill` / `updateSkill` filter on errors for the throw check and return warnings in a new `warnings: ValidationIssue[]` field on their result objects (`CreateSkillResult` / `UpdateSkillResult`). - `validateSkillDescription` now emits a `TOO_SHORT` warning for descriptions under 20 chars — the primary triggering field, so a little coaching goes a long way. - `createHandler` / `patchHandler` in packages/api surface the warnings via a new `attachWarnings` helper that decorates the serialized response with a `warnings?: TSkillWarning[]` field. - `TSkill` gains an optional `warnings?: TSkillWarning[]` field documented as "present on POST/PATCH, never on GET". Reserved-name filter (tightened): - Replace the substring match (`.includes('anthropic')`) with prefix matching on `anthropic-` and `claude-` plus exact-match rejection of CLI slash-command collisions (help, clear, compact, model, exit, quit, settings, plus the bare `anthropic` / `claude` words). Both the pure validator (`methods/skill.ts`) and the Mongoose schema validator (`schema/skill.ts`) updated in lockstep; comments on each reference the other to prevent drift. - `research-anthropic-helper` and `about-claude` are now allowed; `anthropic-helper`, `claude-bot`, and `settings` are still rejected. Documentation: - Add docstrings on `ISkill`, `schema/skill.ts`, and `TSkill` explaining the semantics of `name` (Claude-visible identifier, kebab-case, stable), `displayTitle` (UI-only cosmetic label, NOT sent to Claude), `description` (highest-leverage trigger field), and `source` / `sourceMetadata` (reserved for phase 2+ external sync). - Add a detailed consistency comment on `bumpSkillVersionAndAdjustFileCount` explaining that it runs as a separate MongoDB operation from upsertSkillFile/deleteSkillFile, so `fileCount` can drift if the second op fails — options listed, tradeoff documented, phase 1 risk window noted as closed because upload is still stubbed. Tests: - data-schemas skill.spec.ts: destructure `{ skill, warnings }` from createSkill at every call site; add a TOO_SHORT warning test, a frontmatter strict-mode test, reserved-prefix tests (including positive cases for substring names that should pass), CLI reserved word tests, and a full `validateSkillFrontmatter` describe block covering unknown keys, type mismatches, and deep-nesting rejection. - api/server/routes/skills.test.js: bump default test description above the 20-char threshold, add a warning-emission test, add reserved-prefix + reserved-CLI-word tests, add an unknown-frontmatter- key test asserting the 400 response carries `issues` with `UNKNOWN_KEY`. * 📦 fix: Export CreateSkillResult from data-schemas Methods Index `CreateSkillResult` was defined in `methods/skill.ts` and consumed by `packages/api/src/skills/handlers.ts` but never re-exported from the methods barrel, so the type-check job failed with TS2724 "'@librechat/data-schemas' has no exported member named 'CreateSkillResult'". Rollup's bundle-mode build picked up the type via its internal resolver, but the standalone `tsc --noEmit` type-check ran against the package's public entrypoint and couldn't see it. Added the type import + export alongside the existing `UpdateSkillResult` export, which fixes the CI type-check without any runtime change.	2026-04-25 04:01:59 -04:00
Danny Avila	738003b220	🛡️ fix: Prevent silent crash from unhandled MCP OAuth reconnect rejections (#12812) ... * 🛡️ fix: Install global `unhandledRejection` handler Node 15+ terminates the process by default when a promise rejection goes unhandled. Under MCP OAuth reconnect storms and streamable-HTTP transport resets, fire-and-forget async paths can emit transient rejections (ECONNRESET, token refresh races) that would otherwise silently kill the server — no uncaught exception log, no OOM signal. Register a listener so these paths log and the process keeps serving other requests. Refs: #12078 * 🔧 fix: Guard MCP OAuth reconnect fire-and-forget calls `OAuthReconnectionManager.tryReconnect` awaits `getServerConfig` outside its inner try/catch, so a rejection from the registry (or any throw before the guarded block) would escape the fire-and-forget `void` call sites and propagate as an unhandled rejection — the failure mode behind the silent crashes reported in #12078. Route both call sites through a `safeTryReconnect` wrapper that attaches a terminal `.catch` so unexpected rejections are surfaced via the logger instead. Refs: #12078 * 🧹 fix: Address review findings on MCP OAuth reconnect crash fix - Move `getServerConfig` inside `tryReconnect`'s try/catch so the registry rejection path is handled by the inner cleanup (the structural root cause behind the silent crash). The outer `safeTryReconnect` wrapper remains as defense-in-depth. - Extract the failed-reconnect cleanup as a private `cleanupOnFailedReconnect` method and invoke it from `safeTryReconnect`'s catch as well, so any rejection that does escape the inner try (e.g. a future regression) still resets tracker state instead of leaving the server stuck in `active` for the full `RECONNECTION_TIMEOUT_MS` window. - Update the regression test to assert tracker state is cleaned up (`isActive` cleared, `isFailed` set, `disconnectUserConnection` called) so it can detect the stale-state failure mode it was meant to guard against. - Forward non-Error rejection reasons as-is in the global handler so structured payloads like `{ code: "ECONNRESET", errno: -104 }` survive instead of being collapsed to "[object Object]" by `String()`. Refs: #12078, review of #12812 * 🚑 fix: Restore fail-fast on boot rejection in primary server entry `startServer()` was invoked bare in `api/server/index.js`. Before installing the global `unhandledRejection` handler, a startup rejection (`connectDb`, `getAppConfig`, `performStartupChecks`) terminated the process via Node's default — Kubernetes / the orchestrator restarted the pod immediately. After the handler was added, the same rejection was caught and logged, then the process kept running half-initialized (no HTTP listener) until the liveness probe eventually timed out — slow, indirect recovery instead of a fast restart. Wrap `startServer()` with the same `.catch(() => process.exit(1))` pattern already used in `experimental.js` so boot failures fail-fast. Refs: #12078, codex review of #12812 * 🚑 fix: Fail-fast on post-listen init failure in both server entries The `app.listen` callback in `index.js` and `experimental.js` is async and awaits `initializeMCPs`, `initializeOAuthReconnectManager`, and `checkMigrations`. The callback's promise is detached from `startServer().catch(...)` (the outer catch only sees errors that occurred before `app.listen` was called), so without explicit handling those init rejections used to terminate the process via Node's default and now would be swallowed by the new `unhandledRejection` handler — leaving the HTTP server listening (and passing liveness probes) while MCP / OAuth / migration state is broken. Wrap the post-listen init block in a try/catch that logs and calls `process.exit(1)` so initialization failures stay fail-fast. Refs: #12078, codex review of #12812	2026-04-24 23:18:49 -07:00
Dustin Healy	fc3189b718	🔐 fix: Restore Tenant Context in MCP OAuth Callback (#12782) ... * fix: restore tenant context in MCP OAuth callback for multi-tenant deployments The MCP OAuth callback is a cross-origin redirect from the OAuth provider. SameSite=Strict cookies (including the JWT) are not sent, leaving the callback with no tenant context. With TENANT_ISOLATION_STRICT=true, all DB writes fail. Stores tenantId in flow metadata at OAuth initiation time (when the user is authenticated), then restores it via tenantStorage.run in the callback, wrapping the entire post-validation body. * test: address review findings for tenant context tests - Assert tenantId flows through to initFlow in MCPConnectionFactory test - Add beforeEach to tenant context tests to reset mocks independently	2026-04-22 14:05:51 -07:00
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	f5c4deac28	🔐 fix: Prefer WWW-Authenticate resource_metadata Hint for MCP OAuth (#12763) ... * 📦 chore: Bump @modelcontextprotocol/sdk to v1.29.0 * ♻️ refactor: Extract WWW-Authenticate Probe Helper for MCP OAuth * 🔐 fix: Prefer WWW-Authenticate resource_metadata Hint for MCP OAuth Per RFC 9728 §5.1, the `resource_metadata=<url>` parameter in a 401 `WWW-Authenticate: Bearer` challenge is the authoritative protected-resource metadata source. Path-aware `.well-known` discovery was winning over the hint, so split deployments that serve valid-but-wrong metadata at the path-aware endpoint stranded OAuth at defunct authorization servers. Threads the hint through `discoverOAuthProtectedResourceMetadata` via `opts.resourceMetadataUrl` in both startup detection and the OAuth handler, matching the behavior of Claude Desktop, the MCP Inspector, OpenAI tooling, and Microsoft Copilot Studio. Fixes #12761. * 🧵 fix: Thread OAuth-Aware fetchFn Through Resource-Metadata Probe Without this, admin-configured `oauthHeaders` (e.g. a gateway API key that fronts the MCP endpoint) were stripped from the probe, causing the gateway to 401 for the wrong reason and masking the real `WWW-Authenticate` hint. The helper now accepts a FetchLike and defaults to global fetch, so the startup detection path is unchanged while the handler passes its OAuth- aware wrapper through. * 🧹 refactor: Address MCP OAuth Probe Review Findings - Thread `fetchFn` through `probeResourceMetadataHint` so admin-configured `oauthHeaders` reach the probe (a gateway API key that fronts the MCP endpoint would otherwise 401 us for the wrong reason and hide the real Bearer challenge). - Skip the redundant HEAD request in `checkAuthErrorFallback` when the probe already observed a 401/403; fall back to a fresh HEAD only when every probe attempt threw (transient network error). - Narrow the oauth barrel: drop `export * from './resourceHint'` so the helper stays an internal module. - Add `scope` extraction coverage (`Bearer scope="read write"`) and a 403-only observation path; isolate `MCP_OAUTH_ON_AUTH_ERROR=true` in a dedicated suite so precise-outcome tests aren't muddied by the safety net. * ✅ fix: Use Zod Schema in MCP Reconnection-Storm Test Tool MCP SDK 1.28 tightened `McpServer.tool()` to require Zod schemas instead of plain JSON-Schema objects. Swap the `{ message: { type: 'string' } }` shape for `z.string()` so the fixture server spins up under SDK 1.29. * 🛡️ fix: Harden MCP OAuth resource_metadata Hint Against SSRF The `resource_metadata` URL is echoed from an untrusted MCP server, so handing it straight to the SDK lets a malicious server redirect discovery at private IPs, the cloud metadata service, or any host the admin did not intend to reach. Caught by the Copilot review on #12763. - `handler.ts`: run the hint through the same `validateOAuthUrl` / `allowedDomains` gate that already guards the authorization-server URL; drop it and fall back to path-aware discovery on rejection. - `detectOAuth.ts`: no admin-scoped allowedDomains here, so apply a strict `isSSRFTarget` + DNS resolution check and silently discard any hint pointing at a private/loopback/metadata address. - Tests cover both the hostname-list and DNS-resolution rejection paths and assert the SDK falls back to path-aware discovery unharmed. * 🧪 test: Mock ~/auth in fallback Suite for Consistency Matches the main `detectOAuth.test.ts` mock so the SSRF guards added in the previous commit don't touch the real `~/auth` module at test time. * 🔍 fix: Scope OAuth Fallback to HEAD + Parse Multi-Scheme WWW-Authenticate Two codex findings on #12763: - **P1**: the merged `authChallenge` flag was letting POST-only 401/403 flip the `MCP_OAUTH_ON_AUTH_ERROR` fallback, misclassifying WAF/CSRF-hardened endpoints (HEAD 200 + POST 403) as OAuth-required. Rename to `headAuthChallenge` and derive it only from the HEAD probe, matching the legacy fallback's HEAD-only semantics. Add a regression test. - **P2**: the SDK's `extractWWWAuthenticateParams` only inspects the first scheme token, so multi-scheme headers like `Basic realm="api", Bearer resource_metadata="..."` silently dropped the authoritative Bearer hint. Fall back to a regex across the full header when the SDK returns nothing but Bearer is present. Add a regression test covering the multi-scheme case. * 🧽 refactor: Tighten MCP OAuth Probe Semantics Addresses the second external review pass plus codex P2: - Merge the two stacked JSDoc blocks on `probeResourceMetadataHint` into one with a proper `@returns` section. - Only short-circuit HEAD when it delivered the `resource_metadata` hint itself — a Bearer-without-params HEAD now lets POST run, since some servers surface their hint only on POST and we were missing it. - Drop the unused `scope` field from `ResourceHintProbeResult`; no caller read it, and YAGNI beats a reserved field. - Remove the redundant `OAUTH_ON_AUTH_ERROR` guard inside `checkAuthErrorFallback` — the only call site already gates on it. - Codex P2: signal "HEAD status unknown" via `null` when the HEAD probe threw and POST returned non-auth. Previously that combination leaked a `{headAuthChallenge: false}` result and silently skipped the fallback's retry HEAD, which could misclassify OAuth-required servers after a transient HEAD failure. Regression tests cover every path: Bearer-no-hint-on-HEAD + hint-on-POST, multi-scheme `Basic + Bearer` headers, HEAD-threw + POST-200 retry, and the WAF/CSRF-only POST 403 case. * 🪥 polish: Tighten Probe Null-Guard Ordering + Add Malformed-Hint Test Two NITs from the follow-up review: - Move `bearerChallenge` computation after the `!wwwAuth` guard so the variable is only derived when it can be meaningfully `true`. The early-return path is now a clean unconditional exit. - Add a regression test that asserts `Bearer resource_metadata="not-a-url"` yields `resourceMetadataUrl: undefined` without throwing, locking in the try/catch safety net in `extractHintFromHeader` and the SDK parser alike.	2026-04-21 16:26:20 -07:00
Danny Avila	d1573a8493	🔒 fix: Validate MCP OAuth Protected Resource Metadata binding (#12755) ... * 🔒 fix: Validate MCP OAuth Protected Resource Metadata binding (GHSA-gvpj-vm2f-2m23) RFC 9728 §3.3/§7.3 requires clients to verify that the `resource` identifier advertised by an OAuth Protected Resource Metadata document matches the URL used to fetch it. Without this check, a malicious MCP server can serve metadata pointing at a legitimate server's `authorization_servers`, causing LibreChat to obtain an access token for the real server and send it to the attacker in subsequent API calls. Validation happens at discovery time so the entire metadata document is discarded on mismatch — `authorization_servers` on a spoofed document is equally untrustworthy and is the primary theft vector in the PoC. Uses the MCP SDK's own `checkResourceAllowed` (origin + path-prefix) for semantic parity with `selectResourceURL`, a SDK code path LibreChat bypasses. This is looser than RFC-strict equality (handles common cases like `/mcp/sse` server vs `/mcp` advertised resource, or trailing-slash normalization) while still rejecting cross-origin spoofs and same-origin sibling-path confusion. * 🛡️ fix: Re-validate Resource Binding at MCP OAuth Token Exchange Adds a defense-in-depth re-assertion of the RFC 9728 §3.3 resource/server binding inside `completeOAuthFlow`. Flows have a 10-minute TTL, so a flow initiated under pre-fix (vulnerable) code could still be in-flight at upgrade time carrying unvalidated resource metadata. Re-checking here closes that window without requiring operators to flush flow state on deploy. Also guards against future regressions that might re-introduce unvalidated paths into the flow-metadata pipeline (GHSA-gvpj-vm2f-2m23). * ✅ test: Address Review Findings on MCP OAuth Resource Validation Follow-up to GHSA-gvpj-vm2f-2m23 fix. Resolves three reviewer findings: - Assert `failFlow` is called when `completeOAuthFlow` rejects at re-validation — locks in the "no stuck PENDING entry" guarantee that the catch block already provides in production code. - Update the "no resource metadata" warning in `initiateOAuthFlow`: post-fix, that branch is only reachable when PRM discovery returned nothing (404, network error, server without RFC 9728). A document with a missing `resource` field now throws earlier in `assertResourceBoundToServer`, so the old "missing 'resource' property" phrasing described a case that can no longer reach this branch. - Add a test for an unparseable `resource` string triggering the error-wrapping path in `assertResourceBoundToServer` (verifies the wrapper surfaces a descriptive message instead of leaking a raw `TypeError: Invalid URL` from the SDK's `new URL()` call).	2026-04-21 05:44:09 -07:00
Danny Avila	8e866e6010	🗺️ fix: Resolve Custom-Endpoint Providers for Summarization (#12739) ... * 🔧 fix: resolve custom-endpoint providers for summarization When `summarization.provider` in `librechat.yaml` is set to a custom-endpoint name (e.g. `Ollama`), the string was passed verbatim to the agents SDK, which only knows a fixed set of provider names and threw `Unsupported LLM provider: Ollama`. Before shaping the summarization config for the SDK, resolve the provider through `getProviderConfig`: custom-endpoint labels are remapped to the underlying SDK provider (e.g. `openAI`) and the endpoint's baseURL/apiKey are injected into `parameters` so the summarization model reaches the right backend, even when summarization targets a different custom endpoint than the main agent. Unknown names and names that appear with no matching endpoint flow through unchanged so the SDK can surface a clear error. User-provided credentials and unresolved env-var references are skipped rather than forwarded, letting the SDK's self-summarize path reuse the agent's own clientOptions. Ref: LibreChat Discussion #12614 * address: widen unresolved-env-var guard, fix test naming - Reject summarization overrides when the extracted baseURL/apiKey still contains any `${...}` placeholder, including prefix/suffix patterns like `https://${UNSET}.example.com` that `envVarRegex` (exact-match) missed. - Rename the "case-insensitive" test to reflect that only `Ollama` is normalized via `normalizeEndpointName`; add coverage proving other custom-endpoint names match case-sensitively. * address: use req.config in responses.js; forward full endpoint options - `responses.js` relied on a module-level `appConfig` set via `setAppConfig`, which is never called anywhere. Use `req.config` directly so the summarization provider resolver actually runs on the responses route. - Route the custom endpoint config through `getOpenAIConfig` so summarization inherits the same `headers`, `defaultQuery`, `addParams`/`dropParams`, and `customParams` transforms (Anthropic/Google/etc.) that `initializeCustom` applies for the main agent flow. Strip the stale `model`/`modelName` defaults so `summarization.model` still wins. * address: skip overrides when summarization matches agent endpoint When `summarization.provider` resolves to the same custom endpoint as the main agent, rely on the SDK's self-summarize path (which reuses `agentContext.clientOptions` unchanged) rather than injecting overrides. Otherwise the shallow spread of `clientOverrides.configuration` would replace the agent's request-resolved state (dynamic headers, proxy/fetch options) with yaml-only config. Only applies when summarization targets a *different* endpoint from the agent; the yaml config is all we have in that case, so overrides still flow through. * address: preserve raw provider when overrides cannot be built When summarization points at a different custom endpoint than the agent and we can't resolve the endpoint's credentials (user_provided, or a still-unresolved `${VAR}` after env extraction), remapping to `openAI` without overrides would silently route summaries to the default OpenAI client. Preserve the raw provider name so the SDK raises a clear "Unsupported LLM provider" error (now also logged, via the agents SDK defense-in-depth fix) instead of sending traffic to the wrong backend. * address: resolve endpoint headers and forward PROXY to summarization - Custom-endpoint `headers` now flow through `resolveHeaders` before reaching `getOpenAIConfig`, matching the main agent path. This ensures templated values like `\${PORTKEY_API_KEY}` or `{{LIBRECHAT_BODY_...}}` are substituted for summarization requests instead of being forwarded literally. - `PROXY` env var is now passed into `getOpenAIConfig` so cross-endpoint summarization honors outbound proxy dispatchers configured for the rest of the deployment. * address: user summarization parameters win over endpoint defaults Flip the merge order so `summarization.parameters` from yaml override `clientOverrides` defaults (which come from `getOpenAIConfig` and always include `streaming: true` etc.). A user who sets `parameters.streaming: false` in their config should still see non-streaming summarization for providers that require it. * address: review feedback (logging, dead code, DRY, types, deep-merge) - Log error in the resolveSummarizationProvider catch-all so programming bugs in getProviderConfig/getOpenAIConfig/resolveHeaders surface in operator logs instead of falling through silently. - Drop dead `setAppConfig`/`appConfig` infrastructure in responses.js and fix adjacent `allowedProviders` reference that also relied on the never-initialized module-level appConfig. Uses `req.config` directly. - Import canonical `normalizeEndpointName` from librechat-data-provider instead of duplicating it locally. - Replace `SummarizationClientOverrides = Record<string, unknown>` with an explicit interface covering the known fields. - Deep-merge `configuration` when user-supplied `summarization.parameters. configuration` overlaps the resolved endpoint configuration, so user additions (e.g. `defaultQuery`) don't wipe out `baseURL`/`defaultHeaders`. - Wrap `process.env` mutations in test in `try/finally` so a failed assertion doesn't leak env state into subsequent tests. - Drop `as unknown as AppConfig` in test helper; fixture now matches the `AppConfig` shape directly using a `Partial<TEndpoint>` union. - Trim JSDoc that restated the name it was attached to. * address: review nits — import order, local test type, conflict test - Move `import { logger }` up into the package value-imports section so it no longer sits between `import type` blocks. - Replace `as unknown as SummarizationConfig['parameters']` in the deep-merge test with a named `TestSummarizationParameters` type and a single narrowing cast at the call site, making intent explicit. - Add a test proving that user-supplied `configuration.baseURL` wins over the resolved endpoint baseURL, locking in the deep-merge's user-wins-on-conflict semantics that the previous suite only exercised additively.	2026-04-20 12:00:46 -04:00
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	ccf3a6c670	📐 fix: Align Summarization Trigger Schema with Documented and Runtime-Supported Types (#12735) ... * 🐛 fix: accept documented `summarization.trigger.type` values The Zod schema for `summarization.trigger.type` only accepted `'token_count'`, but: - the documentation lists `token_ratio`, `remaining_tokens`, and `messages_to_refine` as valid - the `@librechat/agents` runtime only evaluates those three types and silently no-ops on anything else The result was a double failure: any user following the docs hit a startup Zod error, and anyone who matched the schema by using `token_count` got a silent no-op at runtime where summarization never fired. Align the schema with the documented, runtime-supported trigger types. Closes #12721 * 🧹 fix: bound `token_ratio` trigger value to (0, 1] Per Codex review: the previous schema accepted `value: z.number().positive()` for every trigger type. That meant `trigger: { type: 'token_ratio', value: 80 }` (presumably meant as "80%") passed validation and then silently never fired — because `usedRatio = 1 - remaining/max` is bounded at 1, so `>= 80` is always false. That is exactly the silent-no-op pattern this PR is trying to eliminate. Switch to a discriminated union so each trigger type has its own value constraint: - `token_ratio`: `(0, 1]` — documented as a fraction, so 80 is nonsense - `remaining_tokens`: positive — token counts can be large - `messages_to_refine`: positive — message counts can be > 1 Added tests for the upper-bound rejection and the inclusive upper bound (`value: 1` still accepted as a valid "fire at 100%" extreme). * 🧹 fix: accept `token_ratio: 0` per documented 0.0–1.0 inclusive range Per Codex review: `.positive()` rejected `value: 0`, but the docs describe the `token_ratio` range as `0.0–1.0` (both inclusive). Admins who copy the documented lower bound into their YAML would fail schema validation at startup. Switch `token_ratio` to `.min(0).max(1)`. `0` is a valid (if extreme) setting — the agents SDK's `usedRatio >= 0` check will fire as soon as there is anything to refine, which is a legitimate "always summarize when pruning happens" configuration. `remaining_tokens` and `messages_to_refine` keep `.positive()`: both are counts, and `0` there produces no meaningful behavior (the SDK has an early return for `messagesToRefineCount <= 0`). * 🐛 fix: preserve `token_ratio` trigger when `value: 0` Per Codex review: now that the schema accepts `token_ratio: 0`, `shapeSummarizationConfig` would silently drop it because of a truthy check on `config?.trigger?.value`. The trigger would disappear and the runtime would fall back to "no trigger configured" — which fires on any pruning rather than honoring the explicit ratio. Switch to `typeof value === 'number'`, which preserves `0` while still rejecting `undefined`/`null`. Added a regression test that asserts `{ type: 'token_ratio', value: 0 }` survives the shaping function untouched. * 🧹 fix: reject non-finite trigger values at schema level Per Codex review: `z.number().positive()` still accepts `Infinity` and `NaN` (via YAML `.inf`, `.nan`). Config validation would succeed, but the agents SDK guards every trigger path with `Number.isFinite(...)` and silently returns `false` — summarization never fires while the server starts cleanly. That is the exact schema/runtime split this PR is trying to eliminate. Add `.finite()` to every trigger value. `token_ratio` already had an implicit guard via `.max(1)`, but applying `.finite()` uniformly keeps the intent obvious and catches `NaN` (which `.max(1)` does not). * 🧹 fix: integer counts + targeted token_count migration warning Two findings from the comprehensive review: 1. `remaining_tokens` and `messages_to_refine` are token/message counts and are always integers in the runtime (`Number.isFinite(...)` guards already assume integer semantics). `z.number().positive()` accepted fractional values like `2.5`, which was semantically confusing and would round oddly against the runtime's `>=` / `<=` comparisons. Add `.int()` to both count-based branches; `token_ratio` stays fractional. 2. Anyone upgrading with `trigger.type: 'token_count'` in their YAML got the generic "Invalid summarization config" warning plus a flattened Zod error. Detect that specific case in `loadSummarizationConfig` and emit a migration-friendly message that names the three valid replacements. Export the function so the behavior is unit-testable. Also added a parameterized passthrough test covering `remaining_tokens` and `messages_to_refine` shaping, complementing the existing `token_ratio` coverage. * 🧹 fix: accurate fallback wording + bare-string trigger test Two nits from the follow-up audit: 1. The legacy-`token_count` warning claimed "Summarization will be disabled," but `shapeSummarizationConfig` treats a missing summarization config as self-summarize mode (fires on every pruning event using the agent's own provider/model). "Disabled" would mislead an admin into stopping investigation. Reword to describe the actual fallback and assert the new wording in the spec. 2. Add a regression test for the `trigger: 'bare-string'` YAML case, so the `typeof raw.trigger === 'object'` guard is exercised rather than implied. 3. Swap the en-dash in `(0–1)` for an ASCII hyphen so the log message is safe in every terminal/aggregator regardless of UTF-8 handling. * 🔇 fix: cast `raw.trigger.type` to inspect legacy value past narrowed union CI TS check failed: after the schema tightening, `raw.trigger.type` is narrowed to `"token_ratio" | "remaining_tokens" | "messages_to_refine" | undefined`, so the runtime comparison to `"token_count"` is a TS2367 ("no overlap") error even though that's exactly the comparison we want for the migration guard. Widen just that one access via `as { type?: unknown }` so the migration check reads runtime-shaped YAML input without the type system folding it back into the narrowed union.	2026-04-19 19:33:52 -07:00
Danny Avila	2358d07b64	📝 fix: Preserve Raw Markdown Formatting on Upload as Text (#12734) ... * 🐛 fix: Preserve Raw Markdown on `Upload as Text` When `RAG_API_URL` is configured, `.md` uploads were sent to the RAG API `/text` endpoint, which routes Markdown through `UnstructuredMarkdownLoader` and strips formatting (`#`, `**`, lists, blockquotes). Users expect `Upload as Text` to preserve raw content - identical bytes in a `.txt` file round-trip verbatim, while the `.md` came back stripped. Short-circuit the RAG API call for Markdown files (by MIME type or `.md` / `.markdown` extension) and read the file verbatim via `parseTextNative`. Non-Markdown paths are unaffected, and the embedding path (`/embed`) keeps its existing loader so vector search quality is unchanged. * 🐛 fix: normalize markdown MIME and accept `text/md` Addressing review feedback on the `Upload as Text` short-circuit: - Accept `text/md` in the markdown MIME set (LibreChat treats it as a valid markdown type elsewhere, e.g. the artifact-rendering prompt). - Normalize the incoming MIME type (lowercase + strip parameters) before the set lookup so parameterized values like `text/markdown; charset=utf-8` and uppercase `TEXT/MARKDOWN` still short-circuit. Extensionless uploads relying only on the `Content-Type` header would otherwise fall through to the RAG `/text` endpoint and lose their markdown formatting. Extend `text.spec.ts` parametrized cases with `text/md`, parameterized MIME, uppercase, and whitespace-padded variants. * 🧹 chore: Address Code Review Follow-ups on `Upload as Text` fix Addressing comprehensive review feedback: - Debug log now includes filename and MIME type so operators can identify which upload triggered the short-circuit without having to correlate other logs. - Expand markdown extension detection beyond `.md` / `.markdown` to cover `.mdown`, `.mkdn`, `.mkd`, `.mdwn` (case-insensitive regex). - Tighten `normalizeMimeType` parameter type from `string | undefined` to `string` to match the actual Express.Multer.File type. The falsy-check still protects against empty strings at runtime. - Extend parametrized tests with the most common real-world shapes: `text/plain` + `.md` (the MIME most browsers/servers assign), the new rare extensions, and empty MIME + `.md` (pure extension fallback path). - Add a positive assertion that `readFileAsString` was called with the expected arguments on every short-circuit case, so tests fail loudly if the native-parse path ever regresses. * 🧪 test: Cover `.mdwn` regex branch in Markdown short-circuit Every other alternation in `MARKDOWN_EXTENSIONS_RE` has at least one test case (`md`, `markdown`, `mdown`, `mkdn`, `mkd`) but `mdwn` did not, leaving a typo in that branch undetectable.	2026-04-19 19:31:39 -07:00
Danny Avila	3bd2681272	🪐 fix: Replace $bitsAllSet ACL Queries for Azure Cosmos DB Compatibility (#12736) ... * 🐛 fix: replace `$bitsAllSet` ACL queries for Cosmos DB compatibility Azure Cosmos DB for MongoDB API does not implement the `$bitsAllSet` query operator, so every permission check against Cosmos DB threw. The five read paths in `aclEntry.ts` (`hasPermission`, `findAccessibleResources`, `findPublicResourceIds`, and two sites in `getSoleOwnedResourceIds`) now fetch candidate entries and apply the bitwise mask in application code. This matches the existing FerretDB-compatible pattern. Fixes #12729. * 🐛 fix: delegate `findPubliclyAccessibleResources` to fixed DB method `AccessControlService.findPubliclyAccessibleResources` inlined the same `$bitsAllSet` query as the data-schemas layer, which fails on Azure Cosmos DB for MongoDB. Delegate to `_dbMethods.findPublicResourceIds` so a single implementation carries the Cosmos-compatible bitwise logic. Refs #12729. * 🐛 fix: move `$bitsAllSet` filter out of remote-agent aggregation `enrichRemoteAgentPrincipals` used `$bitsAllSet` inside an aggregation `$match`, which Azure Cosmos DB for MongoDB does not implement. Project `permBits` through the pipeline and filter for `PermissionBits.SHARE` in application code. The extra documents fetched are bounded by ACL entries on a single agent resource, so the cost is negligible. Refs #12729. * 🧪 test: rename misleading public-dedup test and add real dedup coverage The test previously named "returns deduplicated IDs even if the public principal has multiple entries" only set up a single ACL entry, so it did not actually exercise deduplication. Split into two tests: one for the happy path (single entry with required bits), and one that bypasses `grantPermission`'s upsert via `AclEntry.create` to confirm the application-layer dedup Map handles genuine duplicates. Refs #12729. * 🧪 test: cover SHARE-bit filter in `enrichRemoteAgentPrincipals` The `$bitsAllSet` match stage in `enrichRemoteAgentPrincipals` previously guaranteed every aggregation row had SHARE; the Cosmos DB fix moved that check into a JS `continue` branch with no direct coverage. Add a dependency-injected unit test that stubs the aggregation with mixed SHARE / non-SHARE / zero-bit rows and asserts only SHARE holders are enriched and queued for backfill. Also includes a regression guard that the `$match` pipeline stage no longer contains a `permBits` filter. Refs #12729. * ♻️ refactor: extract `filterByBitsAndDedup` helper for ACL reads `findAccessibleResources` and `findPublicResourceIds` each inlined the same bitmask-filter + `Map`-based dedup loop. Lift it into a private `filterByBitsAndDedup(entries, requiredBits)` helper so the Cosmos-DB compatible pattern lives in one place. Pure rename/extract — no behavior change. Refs #12729. * 📝 docs: fix stale `\$bitsAllSet` references in FerretDB spec The describe block and header comment in the FerretDB parity spec still referenced `\$bitsAllSet queries` after the Cosmos DB compatibility fix moved the bit mask into application code. Update the title to \"Bitwise permission queries\" and rewrite the header comment to describe the application-layer behavior being validated. Refs #12729. * ⚡ perf: push permission-mask filter back to the database via `$in` The original fix for #12729 moved `$bitsAllSet` filtering into application code, which meant every ACL read fetched the full set of rows for a principal/resource and filtered in JS. For tenants with large ACL collections this inflates wire transfer and heap. Replace the JS filter with `permBits: { $in: permissionBitSupersets(X) }`. For the 4-bit `PermissionBits` enum the `$in` list is at most 16 values (8 for a single-bit mask like SHARE). `$in` is indexable and supported by Azure Cosmos DB for MongoDB, so the filter runs on the server again — restoring `.distinct('resourceId')` and `findOne()` semantics. `permissionBitSupersets(requiredBits)` is memoized and exported from `@librechat/data-schemas`. Callers restored: - `hasPermission`: back to `findOne` short-circuit - `findAccessibleResources` / `findPublicResourceIds`: back to `.distinct()` - `getSoleOwnedResourceIds`: back to the `$match` + `$group` aggregation - `enrichRemoteAgentPrincipals`: bit filter back in `$match`, JS `continue` removed Refs #12729. * 🧪 test: add `\$bitsAllSet` vs `\$in` parity + perf spec Introduces `aclEntry.parity.spec.ts` — a side-by-side spec that runs the legacy `\$bitsAllSet` query and the current `\$in`-based query against the same `mongodb-memory-server` fixture and asserts identical output sets for every affected method (`hasPermission`, `findAccessibleResources`, `findPublicResourceIds`, `getSoleOwnedResourceIds`) across all 7 meaningful permBits combinations. Also logs median wall-clock time for the two query paths over 20 runs on an 800-entry fixture, with a loose 3x guard against catastrophic regressions. Initial local numbers: 1.05 ms vs 1.07 ms (findAccessibleResources), 1.10 ms vs 1.05 ms (findPublicResourceIds). Refs #12729. * 🔒 hardening: freeze `permissionBitSupersets` cache + enum-shape guard Two defensive changes from the comprehensive audit: * Cached superset arrays are now `Object.freeze`d and the return type is `readonly number[]`. Previously the cached arrays were returned by mutable reference, so a caller that mutated the result would silently corrupt the process-wide cache for every subsequent permission check. `Object.freeze` turns that into a loud `TypeError` at the mutation site. All existing call sites pass the result directly to Mongoose's `$in`, which does not mutate. * Added a module-load guard `if (MAX_PERM_BITS === 0) throw`. If `PermissionBits` is ever refactored to a `const` object or string enum, `Object.values(...).filter(isNumber)` would return `[]` and `MAX_PERM_BITS` would silently become 0, making every query match no rows and breaking every permission check. The guard fails loudly instead. Also collapsed four identical JSDoc lines across `hasPermission`, `findAccessibleResources`, `findPublicResourceIds`, and `getSoleOwnedResourceIds` into a single `{@link permissionBitSupersets}` reference. Refs #12729. * 🧪 test: add focused unit tests for `permissionBitSupersets` The helper is the single point of correctness for every ACL read path (every query uses `permBits: { $in: permissionBitSupersets(X) }`), so it warrants direct coverage independent of the higher-level parity and behavior specs. Six cases added: * `requiredBits=0` returns all 16 values * `requiredBits=15` returns `[15]` only * every returned value is a bitwise superset of `requiredBits` * full parity against the `$bitsAllSet` definition for every `required` in 0..15 * memoization: repeat calls return the same frozen reference * frozen result throws `TypeError` on mutation attempts Refs #12729. * 🧪 test: tighten parity perf guard and document fixture constants The `expect(currentMs).toBeLessThan(legacyMs * 3 + 50)` form was dominated by the `+ 50` additive term at typical sub-ms query latencies — at legacy=1ms, a 50x regression would still pass. Replace with `Math.max(legacyMs * 5, 50)` so the multiplicative ceiling is intact once the new path climbs out of the fixed noise floor. Also added inline rationale for the `FIXTURE_SIZE = 800` and `PERF_ITERATIONS = 20` constants. Refs #12729. * 🧹 chore: remove stale perf-guard comment, hoist rationale to describe Commit a75f122 left a "Sanity check: A 3x multiplier" comment block above the first perf guard, and 21852ac layered a second "Multiplicative-dominant guard" block directly below it. The stale block described the `legacyMs * 3 + 50` formula that no longer exists, so both blocks coexisted and contradicted each other. Delete the stale block from the first test, remove the redundant copy from the second test, and lift the (now-single) rationale to the enclosing `describe('performance')` block. Each test is now one `expect` line — the rationale lives once, at the scope it applies to. Refs #12729. * 📝 docs: sharpen MAX_PERM_BITS guard message + test-sort consistency Two NITs from the follow-up audit: * The `MAX_PERM_BITS === 0` guard now names the specific refactors that could cause it (const object / string enum / all-string shape) and gives two concrete remediation paths (rewrite the reducer, or give `permissionBitSupersets` an explicit bit-width parameter). Previously the message just said "update permissionBitSupersets before continuing", which was vague. * The `requiredBits=15` unit test now applies the same `[...result].sort((a, b) => a - b)` normalization as the other tests so the set-equality assertions are uniform. The function happens to return values in ascending order, but the helper's JSDoc does not promise ordering, so sorting before comparing is the correct defensive pattern. Refs #12729. * 🔒 fix: enforce `permBits <= MAX_PERM_BITS` at the schema level Codex flagged a real silent regression: `permissionBitSupersets` enumerates `$in` candidates only in `[0, MAX_PERM_BITS]` (currently 15), so any ACL row with bits above the enum — e.g. `permBits = 31` from a future role or a manual DB write — would be excluded from reads that `$bitsAllSet` would have matched. Current write paths only produce values in `[0, 15]` via the `PermissionBits` / `RoleBits` enums, so no live data is affected, but the schema did not prevent out-of-range writes, so the divergence was reachable. Fix: add `min: 0`, `max: MAX_PERM_BITS`, and an `isInteger` validator to the `permBits` field in the AclEntry schema. `MAX_PERM_BITS` is derived from `PermissionBits` the same way `permissionBitSupersets` computes it, so when a new bit is added to the enum both the read-side enumeration and the write-side bound expand together. Tests: four new cases cover the upper bound, over-limit, negative, and non-integer inputs, each asserting `Mongoose.Error.ValidationError`. Plus updated JSDoc on `permissionBitSupersets` to document the invariant that the schema now enforces. Refs #12729. * ♻️ refactor: hoist `MAX_PERM_BITS` + enum-shape/ceiling guards to shared util Addresses one MINOR DRY finding and one NIT defensive-guard finding from the latest audit. `MAX_PERM_BITS` was duplicated in `methods/aclEntry.ts` and `schema/aclEntry.ts` with identical computations; they could silently diverge. Move the constant plus both module-load guards to `src/common/permissions.ts`: * `MAX_PERM_BITS === 0` guard — fail loudly if `PermissionBits` is ever refactored to a `const` object or string enum (applied in both sites now, not just methods). * `MAX_PERM_BITS > 255` guard — circuit-breaker for the `$in` enumeration strategy. At 4 bits the list tops out at 16; at 8 bits 256. Beyond that the approach degrades, so fail at module load rather than emit an unusably-large `$in` list. Both the schema and the methods file now import from the single `src/common/permissions.ts`. `readonly number[]` return type and `Object.freeze` cache-value protection from the prior commits are preserved. Refs #12729. * 🔒 fix: reject out-of-range `requiredBits` without caching (DoS fix) Codex flagged a real unbounded-cache DoS vector: `api/server/controllers/agents/v1.js` parses `req.query.requiredPermission` via `parseInt` and forwards it unvalidated to `findAccessibleResources`, which eventually calls `permissionBitSupersets(requiredBits)`. Because the old code memoized *every* distinct input in a process-global Map, an attacker could flood the cache with unique integers and grow memory without bound. Fix: when `requiredBits` is not an integer, is negative, or has any bits set above `MAX_PERM_BITS`, return a single shared frozen empty array and do NOT touch the cache. An empty `$in` list correctly matches zero rows (rows cannot satisfy a bit we do not support), so the response is also semantically correct — previously it "worked" only because invalid inputs coincidentally expanded to `[]` too, but at the cost of a cache entry each time. Five new tests exercise the rejection path: upper-bound overflow, mixed in-range+out-of-range bits, shared-instance identity across rejected inputs, a 2000-unique-value cache-growth probe, and a regression check that legitimate in-range inputs still get memoized normally. Refs #12729. * 🧪 test: probe `Map.prototype.set` to prove cache doesn't grow on rejection Strengthens the DoS cache-growth test the review pass flagged: reference identity alone allows a hypothetical regression like `supersetCache.set(requiredBits, EMPTY_SUPERSETS); return EMPTY_SUPERSETS;` to pass while still leaking one entry per attacker request. Add a second test that spies on `Map.prototype.set`, records the global call count before and after a burst of 1500 rejected inputs (500 each of over-MAX integers, negatives, and non-integers), and asserts the delta is zero. Manually verified the test has teeth: injecting the hypothetical regression in the implementation produced exactly 1500 extra `Map.set` calls and the new test failed as expected; reverting restored the clean state. Renames the existing identity-based test to `(reference identity)` so its scope is clear alongside the new `(Map-write probe)` companion. Refs #12729.	2026-04-19 22:28:48 -04:00
Luna	8f39f31c87	🤝 fix: Normalize Empty Handoff Fields to Restore Default Fallback (#12707) ... * fix(agents): normalize handoff prompt and parameter values to ensure default instructions * fix(agents): address lint errors and codex review comments	2026-04-19 11:53:09 -04:00
Danny Avila	034b672d0c	🫧 feat: Claude Opus 4.7 Reasoning Visibility (#12701) ... * 🫧 fix: Restore Claude Opus 4.7 Reasoning Visibility Claude Opus 4.7 omits `thinking` content from Messages API responses by default — empty thinking blocks still stream, but the `thinking` field is blank unless the caller passes `display: "summarized"` in the adaptive thinking config. This silenced the LibreChat "Thoughts" UI for Anthropic (and Anthropic-on-Bedrock) adaptive models. - Extend `ThinkingConfigAdaptive` in `packages/api/src/types/anthropic.ts` with an optional `display: 'summarized' | 'omitted'` field - Emit `{ type: 'adaptive', display: 'summarized' }` from `configureReasoning` in `packages/api/src/endpoints/anthropic/helpers.ts` - Emit `{ type: 'adaptive', display: 'summarized' }` from `bedrockInputParser` in `packages/data-provider/src/bedrock.ts` and update the local `ThinkingConfig` union - Update existing adaptive-thinking assertions to include the new field - Add dedicated tests asserting `display: 'summarized'` flows through both the Anthropic endpoint and the Bedrock parser See https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-7#thinking-content-omitted-by-default * refactor: Gate `display: summarized` on Opus 4.7+ Narrow the reasoning-visibility opt-in to the models that actually omit thinking content by default, instead of applying it to every adaptive model. Pre-Opus-4.7 adaptive models (Opus 4.6, Sonnet 4.6) already return summaries, so sending the field is unnecessary noise. - Add `omitsThinkingByDefault(model)` in `packages/data-provider/src/bedrock.ts` that returns true only for Opus 4.7+ (including future majors like Opus 5+) - Bedrock parser now only attaches `display: 'summarized'` when the helper matches, keeping the adaptive object unchanged for older models - Anthropic endpoint `configureReasoning` uses the same helper so its emit path matches the Bedrock one - Tests: replace the blanket `display: 'summarized'` assertions with model-specific ones (Opus 4.7 gets it, Opus 4.6 / Sonnet 4.6 do not), add a dedicated `omitsThinkingByDefault` suite covering naming variants and future versions * feat: Configurable Thought Visibility for Anthropic Adaptive Models Expose the Anthropic `thinking.display` API field as a user-facing parameter so users can override the `auto` default (which stays as the Opus-4.7+ opt-in added earlier in this PR). Also fixes the CI type error by widening the adaptive thinking type assignment via a resolver helper that returns a properly-typed object. - Add `ThinkingDisplay` enum (`auto` | `summarized` | `omitted`) and matching zod schema in `packages/data-provider/src/schemas.ts` - Add `thinkingDisplay` to `tConversationSchema`, `anthropicSettings`, and the pick lists for Bedrock input/parser + Anthropic agent params - Add `resolveThinkingDisplay(model, explicit)` helper in `packages/data-provider/src/bedrock.ts` that returns the wire value or undefined (auto → model default, explicit → always honored) - `bedrockInputParser` now reads `thinkingDisplay` from input and emits `display` only when the resolver returns a value; strips the field on non-adaptive-model branches so it does not leak - `configureReasoning` in the Anthropic endpoint threads `thinkingDisplay` through, uses the resolver, and casts the adaptive config to `AnthropicClientOptions['thinking']` so the widened shape compiles against the stale installed SDK types - Add UI slider for `thinkingDisplay` in `parameterSettings.ts` next to `effort`, with three-position `com_ui_auto` / `com_ui_summarized` / `com_ui_omitted` labels - Add translation keys `com_endpoint_anthropic_thinking_display`, `com_endpoint_anthropic_thinking_display_desc`, `com_ui_summarized`, `com_ui_omitted` - Add tests: `resolveThinkingDisplay` suite (5 cases covering auto / explicit / unknown input), parser round-trip tests for all three modes on Opus 4.6 and Opus 4.7, Anthropic endpoint tests for explicit summarized/omitted overrides * fix: Drop `thinkingDisplay` When Adaptive Thinking Is Disabled If a user turns adaptive thinking off but had previously selected a `thinkingDisplay` value, the stale field was left in `additionalFields` and ended up merged into the Bedrock request's `additionalModelRequestFields`. That leaks a non-Bedrock key into the payload and can round-trip back into `llmConfig`. - Delete `additionalFields.thinkingDisplay` alongside `thinking` and `thinkingBudget` in the `thinking === false` branch of `bedrockInputParser` - Add a regression test asserting `thinking`, `thinkingBudget`, and `thinkingDisplay` are all absent when adaptive thinking is disabled on an Opus 4.7 request Reported by chatgpt-codex-connector on PR #12701. * refactor: Consolidate `ThinkingDisplay` Types and Preserve Persisted Display Address review findings on PR #12701: - [Codex P2] `bedrockInputSchema.transform` now extracts `thinking.display` from persisted `additionalModelRequestFields` back into the top-level `thinkingDisplay` field so explicit `'omitted'` round-trips through storage instead of being silently reverted to `'summarized'` on the next parse. - [Codex P2] `getLLMConfig` in the Anthropic endpoint now reads `.display` from a persisted `thinking` object (agents store the full Anthropic shape) and uses it as the fallback for `thinkingDisplay` when no top-level override is present. - [Audit #2] Collapse the three parallel wire-value types into a single `ThinkingDisplayWireValue = Exclude<ThinkingDisplay, 'auto'>` exported from `schemas.ts`; remove the duplicate `ThinkingDisplay` alias in `packages/api/src/types/anthropic.ts` (which collided with the enum name) and the `ThinkingDisplayValue` alias in `bedrock.ts`. - [Audit #3] Add `thinkingDisplay` to the `TEndpointOption` pick list next to `effort`. - [Audit #4] Add a TODO comment next to the `as AnthropicClientOptions['thinking']` cast explaining the stale `@librechat/agents` SDK types that require it. - Add tests: four round-trip cases asserting `bedrockInputSchema` recovers `display` from persisted AMRF (Opus 4.7 omitted, pre-4.7 summarized, unknown-value ignore, explicit top-level wins), and two `getLLMConfig` cases asserting the Anthropic endpoint preserves and overrides persisted `thinking.display`. * fix: Preserve Persisted `thinking.display` in bedrockInputParser The parser constructed a fresh adaptive thinking config without looking at any `display` already embedded in the incoming `additionalModelRequestFields.thinking`. On round-trip through `initializeBedrock`, a persisted user choice of `'omitted'` on Opus 4.7+ was silently reverted to `'summarized'` by the auto fallback. - Extract `extractPersistedDisplay` helper and reuse it in both the schema transform (form-state round-trip) and the parser (wire-request round-trip) - `bedrockInputParser` now feeds the persisted display as the resolver's explicit value when no top-level `thinkingDisplay` override is set - Add regression tests: parser preserves `display: 'omitted'` for persisted Opus 4.7 AMRF, and top-level `thinkingDisplay` still wins over persisted AMRF display Reported by chatgpt-codex-connector (P1) on PR #12701.	2026-04-16 21:56:52 -04:00
Danny Avila	e2e3284713	🦉 feat: Claude Opus 4.7 Model Support (#12698) ... * 🦉 feat: Claude Opus 4.7 Model Support - Add `claude-opus-4-7` to shared Anthropic models and `anthropic.claude-opus-4-7` to Bedrock models - Register 1M context window and 128K max output in anthropic token maps - Add token pricing ($5/$25), cache rates (6.25/0.5), and premium tier ($10/$37.50 above 200K) in tx.ts - Update `.env.example` with Opus 4.7 IDs in `ANTHROPIC_MODELS` and `BEDROCK_AWS_MODELS` examples - Add parallel Opus 4.7 test cases for token/cache/premium rates, context length, max output, name-variation matching, and 1M-context qualification * feat: Add `xhigh` Effort Level for Opus 4.7 - Add `xhigh` variant to `AnthropicEffort` enum between `high` and `max` - Expose `xhigh` in `anthropicSettings.effort.options` and the UI slider `enumMappings` - Reuse existing `com_ui_xhigh` translation key * test: Cover `xhigh` Effort and Exact Opus 4.7 Premium Rates - Assert `xhigh` position (between high and max), inclusion in `anthropicSettings.effort.options`, zod acceptance, and rejection of unknown values in schemas.spec.ts - Verify bedrockInputParser emits `output_config: { effort: 'xhigh' }` for adaptive `anthropic.claude-opus-4-7` - Verify getLLMConfig sets adaptive thinking and `output_config.effort = 'xhigh'` for `claude-opus-4-7` - Pin Opus 4.7 premium pricing to exact threshold/prompt/completion values (200000 / 10 / 37.5) so silent rate drift fails the test	2026-04-16 14:51:00 -04:00
Danny Avila	a613caced3	🧊 fix: In-Memory Endpoint Token Config Cache Isolation (#12673) ... * fix: endpoint token config not using shared cache in same process (initializing clients) * refactor: Update default max context tokens for agent initialization - Introduced a constant `DEFAULT_MAX_CONTEXT_TOKENS` set to 32000. - Updated the `initializeAgent` function to use this constant instead of hardcoded values for maximum context tokens, improving maintainability and clarity. * refactor: shared caching mechanism for token configuration - Introduced a memoized in-memory cache for Keyv instances to ensure shared access across the same namespace, improving cache efficiency. - Updated the `standardCache` function to utilize the new in-memory cache for the TOKEN_CONFIG namespace. - Refactored the `initializeCustom` function to use the `tokenConfigCache` for better cache management. - Removed redundant tokenCache parameter from `fetchModels` to streamline the function signature. * fix: match TOKEN_CONFIG TTL and add memoization tests Pass Time.THIRTY_MINUTES to tokenConfigCache() to match the TTL used by getLogStores.js, preventing load-order-dependent expiry behavior. Add 7 automated tests covering in-memory memoization: referential identity, cross-call-site data sharing, namespace isolation, first-caller TTL semantics, fallbackStore bypass, and tokenConfigCache parity with direct standardCache access. * fix: export DEFAULT_MAX_CONTEXT_TOKENS, address review nits - Export the constant so tests (and future consumers) reference it directly instead of hardcoding the numeric value. - Add independent TTL assertion for tokenConfigCache (R-1 nit). - Add tokenConfigCache mock to custom/initialize.spec.ts.	2026-04-15 09:41:42 -04:00
Danny Avila	c4bb41137d	🔑 fix: Clear Stale Client Registration on invalid_client During OAuth Token Refresh (#12643) ... * fix: clear stale client registration on invalid_client during token refresh When a token refresh fails with `invalid_client`, the stored DCR client registration is no longer valid on the authorization server. The existing error handler only checked for `unauthorized_client` and returned null, leaving the stale client_id cached in the database permanently. Every subsequent token refresh attempt would fail with the same error. Now when `invalid_client` is detected during refresh: 1. The stale client registration is deleted from the database 2. A `ReauthenticationRequiredError` is thrown to trigger a fresh OAuth flow with new dynamic client registration Also passes `deleteTokens` from MCPConnectionFactory to getTokens() so the cleanup has access to the token deletion method. * fix: address review findings for stale client cleanup on token refresh - Delete stale refresh token alongside client registration on invalid_client (Finding 1) - Add tests for all new code paths: cleanup, warning, case-insensitivity, cleanup failure (Finding 2) - Detect all vendor-specific client rejection patterns (client_id mismatch, client not found, unknown client) with case-insensitive matching (Finding 3) - Use else-if for mutually exclusive error branches (Finding 4) - Log warning when deleteTokens is not available on client rejection (Finding 6) - Fix log message to say "attempting to clear" before async cleanup (Finding 7) - Extract isClientRejectionMessage to shared utility, refactor MCPConnectionFactory.isClientRejection to use it * fix: address followup review findings - Extract isInvalidClientMessage (4 stale-client patterns) from isClientRejectionMessage to eliminate pattern duplication between utils.ts and tokens.ts (Finding 1) - Remove redundant staleIdentifier variable, reuse identifier already in scope (Finding 2) - Separate await from .then() on Promise.allSettled for readability (Finding 3) - Add dedicated unit tests for isInvalidClientMessage and isClientRejectionMessage (Finding 4) - Assert error message content in primary invalid_client test (Finding 5) - Add JSDoc on deleteTokens in GetTokensParams (Finding 6) --------- Co-authored-by: Mani Japra <mani@muonspace.com>	2026-04-13 10:12:54 -04:00
Danny Avila	81275ff0e0	⏱️ refactor: User Job Tracking TTL and Proactive Cleanup to Redis Job Store (#12595) ... * refactor: Add user job tracking TTL to RedisJobStore - Introduced a new TTL for per-user job tracking sets, set to 24 hours, to enhance job management. - Updated RedisJobStoreOptions interface to include userJobsSetTtl for configuration. - Modified job creation and deletion methods to manage user job sets effectively, ensuring proper expiration and cleanup. - Enhanced comments for clarity on the new TTL functionality and its implications for user job tracking. * fix: Address review findings for user job tracking TTL - Remove redundant `del(userJobsKey)` in `getActiveJobIdsByUser` that raced with concurrent `createJob` on other replicas (Redis auto-deletes empty Sets after SREM) - Guard `userJobsSetTtl: 0` from silently destroying tracking sets (`EXPIRE key 0` deletes the key on Redis 7.0+) - Extract `deleteJobInternal` so `cleanup()` reuses the already-fetched userId instead of issuing a redundant HGETALL per stale job - Add integration tests for TTL behavior, proactive SREM, configurable userJobsSetTtl, and TTL refresh on repeated createJob * fix: Address follow-up review findings for RedisJobStore - Use deleteJobInternal in cleanup() terminal-but-in-running-set path to ensure userJobsKey SREM is not skipped - Clear local caches in deleteJob before the fallible getJob call so they are cleaned even on transient Redis errors - Add proactive SREM tests for aborted and error terminal statuses - Add test for tenant-qualified user tracking key format * fix: Preserve completedTtl for non-running jobs in cleanup() The cleanup() terminal-status branch should only remove tracking set membership, not delete the job hash. deleteJobInternal bypasses the completedTtl window that updateJob already applied, causing clients polling for final status to lose the job data early.	2026-04-09 17:42:54 -04:00
Danny Avila	452af50eff	🧮 fix: Atomize Redis Event Sequence Counters for Multi-Replica Deployments (#12578) ... * fix: atomize Redis event sequence counters for multi-replica deployments Replace in-memory sequenceCounters Map with shared atomic Redis counter (INCR via Lua script) so all replicas share an authoritative sequence source. Make syncReorderBuffer async to read current sequence from Redis instead of defaulting to 0 on non-publishing replicas. Closes #12575 * fix: harden emitChunk error handling and syncReorderBuffer race safety Wrap getNextSequence inside emitChunk's try/catch so a transient Redis failure is logged-and-swallowed, preserving the non-fatal chunk emission contract. In syncReorderBuffer, replace pending.clear() with selective discard of stale entries (seq < currentSeq) followed by flushPendingMessages, preventing loss of chunks that arrived during the async GET window. * fix: address review findings — harden error paths, validate types, DRY tests - Wrap syncReorderBuffer in try/catch in GenerationJobManager.subscribe() so a Redis GET failure degrades gracefully instead of crashing SSE reconnect. - Validate eval return type in getNextSequence; throw on unexpected type instead of silently computing NaN/-1 and dropping all messages. - Add NaN guard to parseInt in syncReorderBuffer for corrupted Redis values. - Consolidate two streams loops in destroy() into a single pass. - Extract createMockPublisher to shared helpers/publisher.ts (DRY). - Add tests for eval failure and unexpected eval return type in emitChunk. - Document performance tradeoff (2x RTT per emit) and TTL rationale. * test: add cross-replica integration tests for sequence desync fix (#12575) Three real-Redis tests that reproduce the exact multi-replica failure: - Late subscriber on a different replica syncs to the shared counter and receives chunks immediately (no 500ms force-flush). - Multiple subscribe/unsubscribe cycles across replicas maintain correct sequence alignment on every reconnect. - Shared counter key is cleaned up when the stream is destroyed. * fix: close syncReorderBuffer race, stop destroy() from nuking shared keys - Replace selective prune with Math.min(currentSeq, minPendingSeq) so chunks that arrive in pending during the async GET window are preserved instead of incorrectly pruned. Since unsubscribe() already clears pending, any entries at sync time are live messages from the current subscription and must not be discarded. - Remove DEL from destroy() — the sequence key is shared across replicas and a shutting-down instance must not nuke it for active publishers. Keys expire naturally via their 1-hour TTL; cleanup() handles single-stream lifecycle teardown. - Add race-condition test: pauses GET, injects a message into pending during the window, resolves GET, asserts the chunk is delivered. - Add emitDone/emitError eval failure tests to cover the asymmetric error contract (chunk swallows, done/error propagates). - Add explicit MockPublisher return type to helpers/publisher.ts. * fix: context-aware syncReorderBuffer to prevent duplicate delivery, silence test logs The Math.min(currentSeq, minPending) fix from the prior commit correctly handles the cross-replica race (chunk arriving during async GET), but causes duplicate delivery in same-replica mode: onAbort subscribes to the Redis channel during createJob, so chunks published before subscribe() may arrive via pub/sub AND earlyEventBuffer. The Math.min logic then flushes the pub/sub copy as a "live" message. Fix: add a clearPending parameter to syncReorderBuffer. The manager passes true when earlyEventBuffer was replayed (same-replica: pending entries are duplicates → clear them) and false/undefined when it was not (cross-replica: pending entries are live → preserve via Math.min). - Silence winston logger in stream test files via logger.silent = true, following the existing pattern in data-schemas/prompt.spec.ts. - Remove sequence key DEL from destroy() — shared across replicas, a shutting-down instance must not nuke the counter for active publishers. Keys expire via TTL; cleanup() handles stream teardown. * fix: share publisher client in cross-replica tests for Redis Cluster compat The cross-replica tests created publisherB via (ioredisClient as Redis) .duplicate(), which produces a plain Redis connection to a single node. In Redis Cluster, GET/EVAL on this client can't follow MOVED redirects, so syncReorderBuffer reads null → nextSeq=0 → chunks are buffered. Fix: share ioredisClient as the publisher for both replicas. It's the correct Cluster-aware client and handles slot routing automatically. Only subscriber connections need to be separate (pub/sub requirement). * fix: increase cross-replica test timeouts and use polling for CI cluster Replace fixed 300ms delivery waits with polling (50ms intervals, 2s max) to handle Redis Cluster's cross-node pub/sub broadcast latency in CI. Increase subscription activation wait from 100ms to 500ms to match the pattern used by existing same-instance tests. * chore: silence winston logs in remaining stream test files Add logger.silent = true to GenerationJobManager, RedisJobStore, and collectedUsage test files, matching the pattern already applied to RedisEventTransport and reconnect-reorder-desync tests. * fix: remove flaky cluster pub/sub tests, fix log suppression for resetModules Remove two cross-replica transport-level integration tests that are inherently non-deterministic in Redis Cluster: cluster pub/sub fan-out is async across nodes, so pre-subscribe PUBLISHes can arrive at the subscriber's node after SUBSCRIBE takes effect, causing random +/- 1 message counts. The core logic is already covered by deterministic unit tests (mock publisher) and GenerationJobManager integration tests (end-to-end with earlyEventBuffer). The cleanup test is retained. Switch log suppression from logger.silent (which doesn't survive jest.resetModules) to jest.spyOn(console, 'log').mockImplementation() for files that use resetModules (GenerationJobManager, RedisJobStore, collectedUsage). The logger.silent approach remains for files that don't use resetModules (RedisEventTransport, reconnect-reorder-desync). * fix: replace Lua EVAL+TTL with plain INCR, preserve live chunks during same-replica sync P1: syncReorderBuffer with clearPending=true was unconditionally clearing pending, dropping NEW chunks (seq >= currentSeq) from ongoing generation that arrived via pub/sub during the async GET. Fix: selectively prune only entries with seq < currentSeq (duplicates of earlyEventBuffer) and flush remaining live entries. P2: The 1-hour TTL on sequence keys could expire mid-stream during long quiet periods (e.g., slow tool calls), restarting the counter from zero and causing subscribers to silently drop all subsequent messages. Fix: remove the Lua EVAL+EXPIRE script entirely and use plain Redis INCR — no TTL. Keys are cleaned up explicitly by cleanup()/resetSequence() when streams end. Orphaned keys from crashed processes are a few bytes each, negligible compared to the production risk of TTL expiry. - Update mock publisher helper: eval → incr - Remove "unexpected eval type" tests (not applicable to incr) - Update remaining eval error tests to reference incr * fix: re-arm flush timeout after syncReorderBuffer when gaps remain syncReorderBuffer clears flushTimeout before processing, but if pending still has gaps after flushPendingMessages, no timeout is re-armed. Without new messages arriving to trigger scheduleFlushTimeout, those buffered entries sit indefinitely — stalling the stream after reconnect. * chore: address final review — fix stale docs, rename clearPending, tighten tests Fix all 10 findings from final review pass: F1: Fix stale TTL comment in destroy() — no TTL exists after EVAL removal F2: Fix stale EVAL reference in emitChunk JSDoc → INCR + PUBLISH F3: Fix syncReorderBuffer JSDoc — describes old broken behavior, not the current selective prune F4: Rename clearPending → pruneStaleEntries for clarity at call sites F5: Add publish-not-called assertion to INCR failure test F6: Replace Math.min(...spread) with explicit loop to avoid heap alloc F7: Remove resetSequence from IEventTransport interface (no external callers; implementation detail only) F8: Consolidate cleanup/resetSequence overlap — cleanup() owns the DEL, resetReorderBuffer() (now private) handles buffer state only F9: Fix import order in reconnect test (value before type imports) F10: Export MockPublisher interface from helpers/publisher.ts * chore: fix stale resetSequence references and hadBufferReplay JSDoc Two comments referenced resetSequence() which was removed in the F7/F8 refactor (now private resetReorderBuffer(), which doesn't DEL the key). Only cleanup() deletes the Redis key. Also update hadBufferReplay JSDoc to say "prune stale entries" instead of the pre-refactor "clear pending". * chore: grammar * fix: use earlyReplayCount as prune cutoff instead of Redis counter The boolean pruneStaleEntries flag used currentSeq (from Redis GET) as the prune threshold, but INCR can advance the counter past a live chunk's seq during the GET window. Example: earlyEventBuffer held seqs 0-4, generation emits seq 5 during GET, INCR advances counter to 6, GET returns 6, prune condition 5 < 6 deletes the live chunk. Fix: pass the earlyEventBuffer replay count (5) as the prune cutoff. Entries with seq < earlyReplayCount are true duplicates; entries at or above are live regardless of what the Redis counter reads. After pruning, the unified Math.min(currentSeq, minPending) logic handles both same-replica and cross-replica paths correctly. Add a targeted test that exercises this exact race: pauses GET, emits seq 5 during the window, resolves GET with counter=6, asserts seq 5 is preserved (would have been dropped with the old boolean approach). * fix: pass earlyReplayCount for skipBufferReplay path to prune pub/sub duplicates When skipBufferReplay is true (resume scenario), earlyEventBuffer events are delivered via the resume sync payload, not replayed directly. But earlyReplayCount was left at 0, so syncReorderBuffer treated all pending entries as live — meaning delayed pub/sub copies of those buffered events could be delivered again, duplicating content. Fix: capture earlyEventBuffer.length before the skip/replay branch so the count is always passed to syncReorderBuffer regardless of delivery method. Seqs 0..earlyReplayCount-1 are pruned as duplicates whether they were replayed or delivered via sync payload. * fix: keep nextSeq monotonic in syncReorderBuffer after async GET handleOrderedChunk can deliver in-order messages and advance nextSeq during the async GET window. If those messages leave pending empty, the unconditional nextSeq = currentSeq could regress nextSeq below its already-advanced value, reopening a delivered gap and causing subsequent messages to be buffered until force-flush. Fix: wrap both nextSeq assignments with Math.max(nextSeq, ...) so syncReorderBuffer never moves the delivery frontier backward. * fix: cap nextSeq at earlyReplayCount, add 24h safety TTL, add post-GET race test Finding 1 (CRITICAL): When earlyReplayCount > 0 and pending is empty, nextSeq was set to currentSeq — but INCR can advance the counter past a live chunk whose pub/sub hasn't arrived yet. Cap at earlyReplayCount instead (what was actually delivered), so in-flight chunks are not skipped. Adds test for the message-arrives-AFTER-GET-resolves scenario. Finding 3: Add a 24-hour safety-net TTL set once on first INCR only (val === 1), never refreshed. This caps orphan lifetime from crashed processes without risking mid-stream counter resets. Finding 6: Replace setTimeout(100) in cleanup test with polling loop. Finding 9: Fix variadic DEL mock + add expire mock for the new TTL. Revert P2 fix (earlyReplayCount for skipBufferReplay path) — when skipBufferReplay is true, the resume sync payload delivers everything up to currentSeq, so syncReorderBuffer should trust the Redis counter as the frontier, not the buffer length. * chore: log expire failures consistently with other fire-and-forget errors	2026-04-09 09:57:54 -04:00
Danny Avila	96312aa4fd	🎯 fix: Use Resolved Provider for Agent Token Lookup on Custom Endpoints (#12574) ... * fix: Use resolved provider for agent token lookup on custom endpoints The providerEndpointMap lookup in initializeAgent used the original provider name (e.g. "EduGPT") instead of the resolved overrideProvider ("openai"). Since providerEndpointMap only contains 4 built-in providers, custom providers resolved to undefined, causing getModelMaxTokens to miss the token map and fall back to 18000 tokens. With agent instructions + tool schemas consuming most of that budget, createPruneMessages would strip all messages on the first turn. * fix: Use correct EndpointTokenConfig type in test * refactor: Unify test factory, remove non-discriminating test Address review findings: - Remove Test 2 ("uses the model real context window") which passed with and without the fix due to getModelMaxTokens defaulting to openAI when endpoint is undefined (JS default parameter semantics) - Merge createCustomProviderMocks into createMocks via provider, overrideProvider, and useRealTokenLookup parameters - Hoist jest.requireActual to file scope for shared access * refactor: Address followup review findings - Replace loose `maxContextTokens > 18000` assertion with precise computed value `Math.round((65536 - 4096) * 0.95)` so the outcome assertion is meaningful and self-documenting - Hoist `customProvider` to describe-level constant `CUSTOM_PROVIDER` - Document `overrideProvider` semantics and `useRealTokenLookup` in factory JSDoc - Add comment on real `optionalChainWithEmptyCheck` noting its zero-handling semantics are load-bearing for the maxContextTokens=0 test * style: Use // for inline comment, clarify pipeline assertion role	2026-04-08 15:07:38 -04:00
Danny Avila	15fc27950d	⚡ refactor: Short-Circuit Config Override Resolution (#12553)	2026-04-07 22:38:08 -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	ea28dbfa89	🧹 chore: Clean Up Config Fields (#12537) ... * chore: remove unused `interface.endpointsMenu` config field * chore: address review — restore JSDoc UI-only example, add Zod strip test * chore: remove unused `interface.sidePanel` config field * chore: restrict fileStrategy/fileStrategies schema to valid storage backends * fix: use valid FileStorage value in AppService test * chore: address review — version bump, exhaustiveness guard, JSDoc, configSchema test * chore: remove debug logger.log from MessageIcon render path * fix: rewrite MessageIcon render tests to use render counting instead of logger spying * chore: bump librechat-data-provider to 0.8.407 * chore: sync example YAML version to 1.3.7	2026-04-03 12:22:58 -04:00
Danny Avila	fa4a43da21	🔐 fix: Strip code_challenge from Admin OAuth requests before Passport (#12534) ... * 🔐 fix: Strip code_challenge from admin OAuth requests before Passport openid-client v6's Passport Strategy uses `currentUrl.searchParams.size === 0` to distinguish initial authorization requests from OAuth callbacks. The admin-panel-specific `code_challenge` query parameter caused the strategy to misclassify the request as a callback and return 401 Unauthorized. * 🔐 fix: Strip code_challenge from admin OAuth requests before Passport openid-client v6's Passport Strategy uses `currentUrl.searchParams.size === 0` to distinguish initial authorization requests from OAuth callbacks. The admin-panel-specific `code_challenge` query parameter caused the strategy to misclassify the request as a callback and return 401 Unauthorized. - Fix regex to handle `code_challenge` in any query position without producing malformed URLs, and handle empty `code_challenge=` values (`[^&]*` vs `[^&]+`) - Combine `storePkceChallenge` + `stripCodeChallenge` into a single `storeAndStripChallenge` helper to enforce read-store-strip ordering - Apply defensively to all 7 admin OAuth providers - Add 12 unit tests covering stripCodeChallenge and storeAndStripChallenge * refactor: Extract PKCE helpers to utility file, harden tests - Move stripCodeChallenge and storeAndStripChallenge to api/server/utils/adminPkce.js — eliminates _test production export and avoids loading the full auth.js module tree in tests - Add missing req.originalUrl/req.url assertions to invalid-challenge and no-challenge test branches (regression blind spots) - Hoist cache reference to module scope in tests (was redundantly re-acquired from mock factory on every beforeEach) * chore: Address review NITs — imports, exports, naming, assertions - Fix import order in auth.js (longest-to-shortest per CLAUDE.md) - Remove unused PKCE_CHALLENGE_TTL/PKCE_CHALLENGE_PATTERN exports - Hoist strip arrow to module-scope stripChallengeFromUrl - Rename auth.test.js → auth.spec.js (project convention) - Tighten cache-failure test: toBe instead of toContain, add req.url * refactor: Move PKCE helpers to packages/api with dependency injection Move stripCodeChallenge and storeAndStripChallenge from api/server/utils into packages/api/src/auth/exchange.ts alongside the existing PKCE verification logic. Cache is now injected as a Keyv parameter, matching the dependency-injection pattern used throughout packages/api/. - Add PkceStrippableRequest interface for minimal req typing - auth.js imports storeAndStripChallenge from @librechat/api - Delete api/server/utils/adminPkce.js - Move tests to packages/api/src/auth/adminPkce.spec.ts (TypeScript, real Keyv instances, no getLogStores mock needed)	2026-04-02 21:03:44 -04:00
Danny Avila	6ecd1b510f	📎 fix: Route Unrecognized File Types via supportedMimeTypes Config (#12508) ... * fix: check supportedMimeTypes before routing unrecognized file types In processAttachments, files not matching the hardcoded mime type categories (image, PDF, video, audio) were silently dropped. Now resolves the endpoint's file config and checks the file type against supportedMimeTypes before routing to the documents pipeline. Files not matching any config are still skipped (original behavior). Closes #12482 * feat: encode generic document types for supported providers Remove restrictive mime type filter in encodeAndFormatDocuments that only allowed PDFs and application/* types. Add a generic encoding path for non-PDF, non-Bedrock files using the provider's native format (Anthropic base64 document, OpenAI file block, Google media block). Files are already validated upstream by supportedMimeTypes. * fix: guard file.type and cache file config in processAttachments - Add file.type truthiness check before checkType to prevent coercion of null/undefined to string 'null'/'undefined' - Cache mergedFileConfig and endpointFileConfig on the instance so addPreviousAttachments doesn't recompute per message * refactor: harden generic document encoding with validation and tests - Extract formatDocumentBlock helper to eliminate ~30 lines of duplicate provider-dispatch code between PDF and generic paths - Add size validation in generic encoding path using configuredFileSizeLimit (was fetched but unused) - Guard Bedrock from generic path — non-bedrockDocumentFormats types are now skipped instead of silently tracking metadata - Only push metadata to result.files when a document block was actually created, preventing silent inconsistent state - Enable Anthropic citations for text/plain, text/html, text/markdown (supported by Anthropic's document API) - Fix != to !== for Providers.AZURE comparison - Add 9 tests covering all four provider branches, Bedrock exclusion, size limit enforcement, and unhandled provider * fix: resolve filename type mismatch in formatDocumentBlock filename parameter is string | undefined but OpenAIFileBlock and OpenAIInputFileBlock require string. Default to 'document' when filename is undefined. * fix: use endpoint name for file config lookup in processAttachments Agent runs can have agent.provider set to a base provider (e.g., openAI) while agent.endpoint is a custom endpoint name. Using provider for the getEndpointFileConfig lookup bypassed custom endpoint supportedMimeTypes config. Now uses agent.endpoint, matching the pattern in addDocuments. * perf: filter non-Bedrock files before fetching streams Bedrock only supports types in bedrockDocumentFormats. Previously, getFileStream was called for all files and unsupported types were discarded after download. Now pre-filters the file list for Bedrock to avoid unnecessary network and memory overhead for large unsupported attachments. * refactor: clean up processAttachments file config handling - Remove redundant ?? null intermediaries; use instance properties directly in the else-if condition - Add JSDoc @type annotations for _mergedFileConfig and _endpointFileConfig in the constructor * refactor: harden document encoding and add routing tests - Hoist configuredFileSizeLimit above the loop to avoid recomputing mergeFileConfig per file - Replace Buffer.from decode with base64 length formula in the generic size check to avoid unnecessary heap allocation - Use nullish coalescing (??) for filename fallback - Clean up test: remove unnecessary type cast, use createMockRequest helper for size-limit test - Add 14 tests for processAttachments categorization logic covering supportedMimeTypes routing, null/undefined guards, standard type passthrough, and edge cases * fix: use optional chaining for checkType in routing tests FileConfig.checkType is typed as optional. Use optional chaining to satisfy strict type checking. * fix: skip stream fetches for unsupported providers, block Bedrock generic routing - Return early from encodeAndFormatDocuments when the provider is neither document-supported nor Bedrock, avoiding unnecessary getFileStream calls for providers that would discard all results - Add !isBedrock guard to the supportedMimeTypes fallback branch in processAttachments so permissive patterns like '.*' don't route non-Bedrock types into documents that would be silently dropped - Add test for Bedrock + non-Bedrock-document-type skipping * fix: respect supportedMimeTypes config for Bedrock endpoints Remove !isBedrock guard from the generic supportedMimeTypes routing branch. If a user configures permissive supportedMimeTypes for a Bedrock endpoint, the upload validation already accepted the file. The encoding layer pre-filters to Bedrock-supported types before fetching streams, so unsupported types are handled there without silently dropping files the user explicitly allowed.	2026-04-01 23:04:43 -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	cb41ba14b2	🔁 fix: Pass recursionLimit to OpenAI-Compatible Agents API Endpoint (#12510) ... * fix: pass recursionLimit to processStream in OpenAI-compatible agents API The OpenAI-compatible endpoint never passed recursionLimit to LangGraph's processStream(), silently capping all API-based agent calls at the default 25 steps. Mirror the 3-step cascade already used by the UI path (client.js): yaml config default → per-agent DB override → max cap. * refactor: extract resolveRecursionLimit into shared utility Extract the 3-step recursion limit cascade into a shared resolveRecursionLimit() function in @librechat/api. Both openai.js and client.js now call this single source of truth. Also fixes falsy-guard edge cases where recursion_limit=0 or maxRecursionLimit=0 would silently misbehave, by using explicit typeof + positive checks. Includes unit tests covering all cascade branches and edge cases. * refactor: use resolveRecursionLimit in openai.js and client.js Replace duplicated cascade logic in both controllers with the shared resolveRecursionLimit() utility from @librechat/api. In openai.js: hoist agentsEConfig to avoid double property walk, remove displaced comment, add integration test assertions. In client.js: remove inline cascade that was overriding config after initial assignment. * fix: hoist processStream mock for test accessibility The processStream mock was created inline inside mockResolvedValue, making it inaccessible via createRun.mock.results (which returns the Promise, not the resolved value). Hoist it to a module-level variable so tests can assert on it directly. * test: improve test isolation and boundary coverage Use mockReturnValueOnce instead of mockReturnValue to prevent mock leaking across test boundaries. Add boundary tests for downward agent override and exact-match maxRecursionLimit.	2026-04-01 21:13:07 -04:00
Danny Avila	f8405e731b	🗂️ fix: Allow Empty-Overrides Scope Creation in Admin Config (#12492) ... * fix: Allow empty-overrides scope creation when priority is provided The upsertConfigOverrides handler short-circuited when overrides was empty, returning a plain message instead of creating the config document. This broke the admin panel's "create blank scope" flow which sends `{ overrides: {}, priority: N }` — the missing `config` property in the response caused an `_id` error on the client. The early return now only triggers when both overrides are empty and no priority is provided. Per-section permission checks are scoped to cases where override sections are actually present. * test: Add tests for empty-overrides scope creation with priority * test: Address review nits for empty-overrides scope tests - Add res.statusCode/res.body assertions to capability-check test - Add 403/401 tests for empty overrides + priority path - Use mockResolvedValue(null) for consistency on bare jest.fn() - Remove narrating comment; fold intent into test name	2026-03-31 21:46:48 -04:00
Dustin Healy	2451bf54cf	🛡️ fix: Restrict System Grants to Role Principals (#12491) ... * 🛡️ fix: restrict system grants to role principals only Narrows GrantPrincipalType to PrincipalType.ROLE, rejecting GROUP and USER with 400. Removes grant cascade cleanup from group/user deletion handlers and their route wiring since only roles can hold grants. * 🛡️ fix: address review findings for grants roles-only restriction Add missing GROUP rejection test for revokeGrant (symmetric with getPrincipalGrants and assignGrant coverage), add extensibility comment to GrantPrincipalType, and document the checkRoleExists guard.	2026-03-31 19:25:14 -04:00
Danny Avila	c0ce7fee91	🚫 refactor: Remove Interface Config from Override Processing (#12473) ... Add INTERFACE_PERMISSION_FIELDS set defining the interface fields that seed role permissions at startup (prompts, agents, marketplace, etc.). These fields are now stripped from DB config overrides in the merge layer because updateInterfacePermissions() only runs at boot — DB overrides for these fields create a client/server permission mismatch. Pure UI fields (endpointsMenu, modelSelect, parameters, presets, sidePanel, customWelcome, etc.) continue to work in overrides as before. YAML startup path is completely unaffected.	2026-03-31 11:07:31 -04:00
Dustin Healy	3d1b883e9d	👨‍👨‍👦‍👦 feat: Admin Users API Endpoints (#12446) ... * feat: add admin user management endpoints Add /api/admin/users with list, search, and delete handlers gated by ACCESS_ADMIN + READ_USERS/MANAGE_USERS system grants. Handler factory in packages/api uses findUsers, countUsers, and deleteUserById from data-schemas. * fix: address convention violations in admin users handlers * fix: add pagination, self-deletion guard, and DB-level search limit - listUsers now uses parsePagination + countUsers for proper pagination matching the roles/groups pattern - findUsers extended with optional limit/offset options - deleteUser returns 403 when caller tries to delete own account - searchUsers passes limit to DB query instead of fetching all and slicing in JS - Fix import ordering per CLAUDE.md, complete logger mock - Replace fabricated date fallback with undefined * fix: deterministic sort, null-safe pagination, consistent search filter - Add sort option to findUsers; listUsers sorts by createdAt desc for deterministic pagination - Use != null guards for offset/limit to handle zero values correctly - Remove username from search filter since it is not in the projection or AdminUserSearchResult response type * fix: last-admin deletion guard and search query max-length - Prevent deleting the last admin user (look up target role, count admins, reject with 400 if count <= 1) - Cap search query at 200 characters to prevent regex DoS - Add tests for both guards * fix: include missing capability name in 403 Forbidden response * fix: cascade user deletion cleanup, search username, parallel capability checks - Cascade Config, AclEntry, and SystemGrant cleanup on user deletion (matching the pattern in roles/groups handlers) - Add username to admin search $or filter for parity with searchUsers - Parallelize READ_* capability checks in listAllGrants with Promise.all * fix: TOCTOU safety net, capability info leak, DRY/style cleanup, data-layer tests - Add post-delete admin recount with CRITICAL log if race leaves 0 admins - Revert capability name from 403 response to server-side log only - Document thin deleteUserById limitation (full cascade is a future task) - DRY: extract query.trim() to local variable in searchUsersHandler - Add username to search projection, response type, and AdminUserSearchResult - Functional filter/map in grants.ts parallel capability check - Consistent null guards and limit>0 guard in findUsers options - Fallback for empty result.message on delete response - Fix mockUser() to generate unique _id per call - Break long destructuring across multiple lines - Assert countUsers filter and non-admin skip in delete tests - Add data-layer tests for findUsers limit, offset, sort, and pagination * chore: comment out admin delete user endpoint (out of scope) * fix: cast USER principalId to ObjectId for ACL entry cleanup ACL entries store USER principalId as ObjectId (via grantPermission casting), but deleteAclEntries is a raw deleteMany that passes the filter through. Passing a string won't match stored ObjectIds, leaving orphaned entries. * chore: comment out unused requireManageUsers alongside disabled delete route * fix: add missing logger.warn mock in capabilities test * fix: harden admin users handlers — type safety, response consistency, test coverage - Unify response shape: AdminUserSearchResult.userId → id, add AdminUserListItem type - Fix unsafe req.query type assertion in searchUsersHandler (typeof guards) - Anchor search regex with ^ for prefix matching (enables index usage) - Add total/capped to search response for truncation signaling - Add parseInt radix, remove redundant new Date() wrap - Add tests: countUsers throw, countUsers call args, array query param, capped flag * fix: scope deleteGrantsForPrincipal to tenant, deterministic search sort, align test mocks - Add tenantId option to AdminUsersDeps.deleteGrantsForPrincipal and pass req.user.tenantId at the call site, matching the pattern already used by the roles and groups handlers - Add sort: { name: 1 } to searchUsersHandler for deterministic results - Align test mock deleteUserById messages with production output ('User was deleted successfully.') - Make capped-results test explicitly set limit: '20' instead of relying on the implicit default * test: add tenantId propagation test for deleteGrantsForPrincipal Add tenantId to createReqRes user type and test that a non-undefined tenantId is threaded through to deleteGrantsForPrincipal. * test: remove redundant deleteUserById override in tenantId test --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2026-03-30 23:06:50 -04:00
Danny Avila	fd01dfc083	💰 fix: Lazy-Initialize Balance Record at Check Time for Overrides (#12474) ... * fix: Lazy-initialize balance record when missing at check time When balance is configured via admin panel DB overrides, users with existing sessions never pass through the login middleware that creates their balance record. This causes checkBalanceRecord to find no record and return balance: 0, blocking the user. Add optional balanceConfig and upsertBalanceFields deps to CheckBalanceDeps. When no balance record exists but startBalance is configured, lazily create the record instead of returning canSpend: false. Pass the new deps from BaseClient, chatV1, and chatV2 callers. * test: Add checkBalance lazy initialization tests Cover lazy balance init scenarios: successful init with startBalance, insufficient startBalance, missing config fallback, undefined startBalance, missing upsertBalanceFields dep, and startBalance of 0. * fix: Address review findings for lazy balance initialization - Use canonical BalanceConfig and IBalanceUpdate types from @librechat/data-schemas instead of inline type definitions - Include auto-refill fields (autoRefillEnabled, refillIntervalValue, refillIntervalUnit, refillAmount, lastRefill) during lazy init, mirroring the login middleware's buildUpdateFields logic - Add try/catch around upsertBalanceFields with graceful fallback to canSpend: false on DB errors - Read balance from DB return value instead of raw startBalance constant - Fix misleading test names to describe observable throw behavior - Add tests: upsertBalanceFields rejection, auto-refill field inclusion, DB-returned balance value, and logViolation assertions * fix: Address second review pass findings - Fix import ordering: package type imports before local type imports - Remove misleading comment on DB-fallback test, rename for clarity - Add logViolation assertion to insufficient-balance lazy-init test - Add test for partial auto-refill config (autoRefillEnabled without required dependent fields) * refactor: Replace createMockReqRes factory with describe-scoped consts Replace zero-argument factory with plain const declarations using direct type casts instead of double-cast through unknown. * fix: Sort local type imports longest-first, add missing logViolation assertion - Reorder local type imports in spec file per AGENTS.md (longest to shortest within sub-group) - Add logViolation assertion to startBalance: 0 test for consistent violation payload coverage across all throw paths	2026-03-30 22:51:07 -04:00
Danny Avila	2bf0f892d6	🛡️ fix: Add Origin Binding to Admin OAuth Exchange Codes (#12469) ... * fix(auth): add origin binding to admin OAuth exchange codes Bind admin OAuth exchange codes to the admin panel's origin at generation time and validate the origin on redemption. This prevents an intercepted code (via referrer leakage, logs, or network capture) from being redeemed by a different origin within the 30-second TTL. - Store the admin panel origin alongside the exchange code in cache - Extract the request origin (from Origin/Referer headers) on the exchange endpoint and pass it for validation - Reject code redemption when the request origin does not match the stored origin (code is still consumed to prevent replay) - Backward compatible: codes without a stored origin are accepted * fix(auth): add PKCE proof-of-possession to admin OAuth exchange codes Add a PKCE-like code_challenge/code_verifier flow to the admin OAuth exchange so that intercepting the exchange code alone is insufficient to redeem it. The admin panel generates a code_verifier (stored in its HttpOnly session cookie) and sends sha256(verifier) as code_challenge through the OAuth initiation URL. LibreChat stores the challenge keyed by OAuth state and attaches it to the exchange code. On redemption, the admin panel sends the verifier and LibreChat verifies the hash match. - Add verifyCodeChallenge() helper using SHA-256 - Store code_challenge in ADMIN_OAUTH_EXCHANGE cache (pkce: prefix, 5min TTL) - Capture OAuth state in callback middleware before passport processes it - Accept code_verifier in exchange endpoint body - Backward compatible: no challenge stored → PKCE check skipped * fix(auth): harden PKCE and origin binding in admin OAuth exchange - Await cache.set for PKCE challenge storage with error handling - Use crypto.timingSafeEqual for PKCE hash comparison - Drop case-insensitive flag from hex validation regexes - Add code_verifier length validation (max 512 chars) - Normalize Origin header via URL parsing in resolveRequestOrigin - Add test for undefined requestOrigin rejection - Clarify JSDoc: hex-encoded SHA-256, not RFC 7636 S256 * fix(auth): fail closed on PKCE callback cache errors, clean up origin/buffer handling - Callback middleware now redirects to error URL on cache.get failure instead of silently continuing without PKCE challenge - resolveRequestOrigin returns undefined (not raw header) on parse failure - Remove dead try/catch around Buffer.from which never throws for string input * chore(auth): remove narration comments, scope eslint-disable to lines * chore(auth): narrow query.state to string, remove narration comments in exchange.ts * fix(auth): address review findings — warn on missing PKCE challenge, validate verifier length, deduplicate URL parse - Log warning when OAuth state is present but no PKCE challenge found - Add minimum length check (>= 1) on code_verifier input validation - Update POST /oauth/exchange JSDoc to document code_verifier param - Deduplicate new URL(redirectUri) parse in createOAuthHandler - Restore intent comment on pre-delete pattern in exchangeAdminCode * test(auth): replace mock cache with real Keyv, remove all as-any casts - Use real Keyv in-memory store instead of hand-rolled Map mock - Replace jest.fn mocks with jest.spyOn on real Keyv instance - Remove redundant store.has() assertion, use cache.get() instead - Eliminate all eslint-disable and as-any suppressions - User fixture no longer needs any cast (Keyv accepts plain objects) * fix(auth): add IUser type cast for test fixture to satisfy tsc	2026-03-30 16:54:00 -04:00
Danny Avila	1455f15b7b	📄 feat: Model-Aware Bedrock Document Size Validation (#12467) ... * 📄 fix: Model-Aware Bedrock Document Size Validation Remove the hard 4.5MB clamp on Bedrock document uploads so that Claude 4+ (PDF) and Nova (PDF/DOCX) models can accept larger files per AWS documentation. The default 4.5MB limit is preserved for other models/formats, and fileConfig can now override it in either direction—consistent with every other provider. * address review: restore Math.min for non-exempt docs, tighten regexes, add tests - Restore Math.min clamp for non-exempt Bedrock documents (fileConfig can only lower the hard 4.5 MB API limit, not raise it); only exempt models (Claude 4+ PDF, Nova PDF/DOCX) use ?? to allow fileConfig override - Replace copied isBedrockClaude4Plus regex with cleaner anchored pattern that correctly handles multi-digit version numbers (e.g. sonnet-40) and removes dead Alt 1 branch matching no real Bedrock model IDs - Tighten isBedrockNova from includes() to startsWith() to prevent substring matching in unexpected positions - Add integration test verifying model is threaded to validateBedrockDocument - Add boundary tests for exempt + low configuredFileSizeLimit, non-exempt + high configuredFileSizeLimit, and exempt model accepting files up to 32 MB - Revert two tests that were incorrectly inverted to prove wrong behavior - Fix inaccurate JSDoc and misleading test name * simplify: allow fileConfig to override Bedrock limit in either direction Make Bedrock consistent with all other providers — fileConfig sets the effective limit unconditionally via ?? rather than clamping with Math.min. The model-aware defaults (4.5 MB for non-exempt, 32 MB for exempt) remain as sensible fallbacks when no fileConfig is set. * fix: handle cross-region inference profile IDs in Bedrock model matchers Bedrock cross-region inference profiles prepend a region code to the model ID (e.g. "us.amazon.nova-pro-v1:0", "eu.anthropic.claude-sonnet-4-..."). Both isBedrockNova and isBedrockClaude4Plus would miss these prefixed IDs, silently falling back to the 4.5 MB default for eligible models. Switch both matchers to use (?:^|\.) to anchor the vendor segment so the pattern matches with or without a leading region prefix.	2026-03-30 16:50:10 -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
Dustin Healy	a4a17ac771	⛩️ feat: Admin Grants API Endpoints (#12438) ... * feat: add System Grants handler factory with tests Handler factory with 4 endpoints: getEffectiveCapabilities (expanded capability set for authenticated user), getPrincipalGrants (list grants for a specific principal), assignGrant, and revokeGrant. Write ops dynamically check MANAGE_ROLES/GROUPS/USERS based on target principal type. 31 unit tests covering happy paths, validation, 403, and errors. * feat: wire System Grants REST routes Mount /api/admin/grants with requireJwtAuth + ACCESS_ADMIN gate. Add barrel export for createAdminGrantsHandlers and AdminGrantsDeps. * fix: cascade grant cleanup on role deletion Add deleteGrantsForPrincipal to AdminRolesDeps and call it in deleteRoleHandler via Promise.allSettled after successful deletion, matching the groups cleanup pattern. 3 tests added for cleanup call, skip on 404, and resilience to cleanup failure. * fix: simplify cascade grant cleanup on role deletion Replace Promise.allSettled wrapper with a direct try/catch for the single deleteGrantsForPrincipal call. * fix: harden grant handlers with auth, validation, types, and RESTful revoke - Add per-handler auth checks (401) and granular capability gates (READ_* for getPrincipalGrants, possession check for assignGrant) - Extract validatePrincipal helper; rewrite validateGrantBody to use direct type checks instead of unsafe `as string` casts - Align DI types with data layer (ResolvedPrincipal.principalType widened to string, getUserPrincipals role made optional) - Switch revoke route from DELETE body to RESTful URL params - Return 201 for assignGrant to match roles/groups create convention - Handle null grantCapability return with 500 - Add comprehensive test coverage for new auth/validation paths * fix: deduplicate ResolvedPrincipal, typed body, defensive auth checks - Remove duplicate ResolvedPrincipal from capabilities.ts; import the canonical export from grants.ts - Replace Record<string, unknown> with explicit GrantRequestBody interface - Add defensive 403 when READ_CAPABILITY_BY_TYPE lookup misses - Document revoke asymmetry (no possession check) with JSDoc - Use _id only in resolveUser (avoid Mongoose virtual reliance) - Improve null-grant error message - Complete logger mock in tests * refactor: move ResolvedPrincipal to shared types to fix circular dep Extract ResolvedPrincipal from admin/grants.ts to types/principal.ts so middleware/capabilities.ts imports from shared types rather than depending upward on the admin handler layer. * chore: remove dead re-export, align logger mocks across admin tests - Remove unused ResolvedPrincipal re-export from grants.ts (canonical source is types/principal.ts) - Align logger mocks in roles.spec.ts and groups.spec.ts to include all log levels (error, warn, info, debug) matching grants.spec.ts * fix: cascade Config and AclEntry cleanup on role deletion Add deleteConfig and deleteAclEntries to role deletion cascade, matching the group deletion pattern. Previously only grants were cleaned up, leaving orphaned config overrides and ACL entries. * perf: single-query batch for getEffectiveCapabilities Add getCapabilitiesForPrincipals (plural) to the data layer — a single $or query across all principals instead of N+1 parallel queries. Wire it into the grants handler so getEffectiveCapabilities hits the DB once regardless of how many principals the user has. * fix: defer SystemCapabilities access to factory call time Move all SystemCapabilities usage (VALID_CAPABILITIES, MANAGE_CAPABILITY_BY_TYPE, READ_CAPABILITY_BY_TYPE) inside the createAdminGrantsHandlers factory. External test suites that mock @librechat/data-schemas without providing SystemCapabilities crashed at import time when grants.ts was loaded transitively. * test: add data-layer and handler test coverage for review findings - Add 6 mongodb-memory-server tests for getCapabilitiesForPrincipals: multi-principal batch, empty array, filtering, tenant scoping - Add handler test: all principals filtered (only PUBLIC) - Add handler test: granting an implied capability succeeds - Add handler test: all cascade cleanup operations fail simultaneously - Document platform-scope-only tenantId behavior in JSDoc * fix: resolveUser fallback to user.id, early-return empty principals - Match capabilities middleware pattern: _id?.toString() ?? user.id to handle JWT-deserialized users without Mongoose _id - Move empty-array guard before principals.map() to skip unnecessary normalizePrincipalId calls - Add comment explaining VALID_PRINCIPAL_TYPES module-scope asymmetry * refactor: derive VALID_PRINCIPAL_TYPES from capability maps Make MANAGE_CAPABILITY_BY_TYPE and READ_CAPABILITY_BY_TYPE non-Partial Records over a shared GrantPrincipalType union, then derive VALID_PRINCIPAL_TYPES from the map keys. This makes divergence between the three data structures structurally impossible. * feat: add GET /api/admin/grants list-all-grants endpoint Add listAllGrants data-layer method and handler so the admin panel can fetch all grants in a single request instead of fanning out N+M calls per role and group. Response is filtered to only include grants for principal types the caller has read access to. * fix: update principalType to use GrantPrincipalType for consistency in grants handling - Refactor principalType in createAdminGrantsHandlers to use GrantPrincipalType instead of PrincipalType for better type accuracy. - Ensure type consistency across the grants handling logic in the API. * fix: address admin grants review findings — tenantId propagation, capability validation, pagination, and test coverage Propagate tenantId through all grant operations for multi-tenancy support. Extract isValidCapability to accept full SystemCapability union (base, section, assign) and reuse it in both Mongoose schema validation and handler input checks. Replace listAllGrants with paginated listGrants + countGrants. Filter PUBLIC principals from getCapabilitiesForPrincipals queries. Export getCachedPrincipals from ALS store for fast-path principal resolution. Move DELETE capability param to query string to avoid colon-in-URL issues. Remove dead code and add comprehensive handler and data-layer test coverage. * refactor: harden admin grants — FilterQuery types, auth-first ordering, DELETE path param, isValidCapability tests Replace Record<string, unknown> with FilterQuery<ISystemGrant> across all data-layer query filters. Refactor buildTenantFilter to a pure tenantCondition function that returns a composable FilterQuery fragment, eliminating the $or collision between tenant and principal queries. Move auth check before input validation in getPrincipalGrantsHandler, assignGrantHandler, and revokeGrantHandler to avoid leaking valid type names to unauthenticated callers. Switch DELETE route from query param back to path param (/:capability) with encodeURIComponent per project conventions. Add compound index for listGrants sort. Type VALID_PRINCIPAL_TYPES as Set<GrantPrincipalType>. Remove unused GetCachedPrincipalsFn type export. Add dedicated isValidCapability unit tests and revokeGrant idempotency test. * refactor: batch capability checks in listGrantsHandler via getHeldCapabilities Replace 3 parallel hasCapabilityForPrincipals DB calls with a single getHeldCapabilities query that returns the subset of capabilities any principal holds. Also: defensive limit(0) clamp, parallelized assignGrant auth checks, principalId type-vs-required error split, tenantCondition hoisted to factory top, JSDoc on cascade deps, DELETE route encoding note. * fix: normalize principalId and filter undefined in getHeldCapabilities Add normalizePrincipalId + null guard to getHeldCapabilities, matching the contract of getCapabilitiesForPrincipals. Simplify allCaps build with flatMap, add no-tenantId cross-check and undefined-principalId test cases. * refactor: use concrete types in GrantRequestBody, rename encoding test Replace unknown fields with explicit string types in GrantRequestBody, matching the established pattern in roles/groups/config handlers. Rename misleading 'encoded' test to 'with colons' since Express auto-decodes req.params. * fix: support hierarchical parent capabilities in possession checks hasCapabilityForPrincipals and getHeldCapabilities now resolve parent base capabilities for section/assignment grants. An admin holding manage:configs can now grant manage:configs:<section> and transitively read:configs:<section>. Fixes anti-escalation 403 blocking config capability delegation. * perf: use getHeldCapabilities in assignGrant to halve DB round-trips assignGrantHandler was making two parallel hasCapabilityForPrincipals calls to check manage + capability possession. getHeldCapabilities was introduced in this PR specifically for this pattern. Replace with a single batched call. Update corresponding spec assertions. * fix: validate role existence before granting capabilities Grants for non-existent role names were silently persisted, creating orphaned grants that could surprise-activate if a role with that name was later created. Add optional checkRoleExists dep to assignGrant and wire it to getRoleByName in the route file. * refactor: tighten principalType typing and use grantCapability in tests Narrow getCapabilitiesForPrincipals parameter from string to PrincipalType, removing the redundant cast. Replace direct SystemGrant.create() calls in getCapabilitiesForPrincipals tests with methods.grantCapability() to honor the schema's normalization invariant. Add getHeldCapabilities extended capability tests. * test: rename misleading cascade cleanup test name The test only injects failure into deleteGrantsForPrincipal, not all cascade operations. Rename from 'cascade cleanup fails' to 'grant cleanup fails' to match the actual scope. * fix: reorder role check after permission guard, add tenantId to index Move checkRoleExists after the getHeldCapabilities permission check so that a sub-MANAGE_ROLES admin cannot probe role name existence via 400 vs 403 response codes. Add tenantId to the { principalType, capability } index so listGrants queries in multi-tenant deployments can use a covering index instead of post-scanning for tenant condition. Add missing test for checkRoleExists throwing. * fix: scope deleteGrantsForPrincipal to tenant on role deletion deleteGrantsForPrincipal previously filtered only on principalType + principalId, deleting grants across all tenants. Since the role schema supports multi-tenancy (compound unique index on name + tenantId), two tenants can share a role name like 'editor'. Deleting that role in one tenant would wipe grants for identically-named roles in other tenants. Add optional tenantId parameter to deleteGrantsForPrincipal. When provided, scopes the delete to that tenant plus platform-level grants. Propagate req.user.tenantId through the role deletion cascade. * fix: scope grant cleanup to tenant on group deletion Same cross-tenant gap as the role deletion path: deleteGroupHandler called deleteGrantsForPrincipal without tenantId, so deleting a group would wipe its grants across all tenants. Extract req.user.tenantId and pass it through. * test: add HTTP integration test for admin grants routes Supertest-based test with real MongoMemoryServer exercising the full Express wiring: route registration, injected auth middleware, handler DI deps, and real DB round-trips. Covers GET /, GET /effective, POST / + DELETE / lifecycle, role existence validation, and 401 for unauthenticated callers. Also documents the expandImplications scope: the /effective endpoint returns base-level capabilities only; section-level resolution is handled at authorization check time by getParentCapabilities. * fix: use exact tenant match in deleteGrantsForPrincipal, normalize principalId, harden API CRITICAL: deleteGrantsForPrincipal was using tenantCondition (a read-query helper) for deleteMany, which includes the { tenantId: { $exists: false } } arm. This silently destroyed platform-level grants when a tenant-scoped role/group deletion occurred. Replace with exact { tenantId } match for deletes so platform-level grants survive tenant-scoped cascade cleanup. Refactor deleteGrantsForPrincipal signature from fragile positional overload (sessionOrTenantId union + maybeSession) to a clean options object: { tenantId?, session? }. Update all callers and test assertions. Add normalizePrincipalId to hasCapabilityForPrincipals to match the pattern already used by getHeldCapabilities — prevents string/ObjectId type mismatch on USER/GROUP principal queries. Also: export GrantPrincipalType from barrel, add upper-bound cap to listGrants, document GROUP/USER existence check trade-off, add integration tests for tenant-isolation property of deleteGrantsForPrincipal. * fix: forward tenantId to getUserPrincipals in resolvePrincipals resolvePrincipals had tenantId available from the caller but only forwarded it to getCachedPrincipals (cache lookup). The DB fallback via getUserPrincipals omitted it. While the Group schema's applyTenantIsolation Mongoose plugin handles scoping via AsyncLocalStorage in HTTP request context, explicitly passing tenantId makes the contract visible and prevents silent cross-tenant group resolution if called outside request context. * fix: remove unused import and add assertion to 401 integration test Remove unused SystemCapabilities import flagged by ESLint. Add explicit body assertion to the 401 test so it has a jest expect() call. * chore: hoist grant limit constants to scope, remove dead isolateModules Move GRANTS_DEFAULT_LIMIT / GRANTS_MAX_LIMIT from inside listGrants function body to createSystemGrantMethods scope so they are evaluated once at module load. Remove dead jest.isolateModules + jest.doMock block in integration test — the ~/models mock was never exercised since handlers are built with explicit DI deps. --------- Co-authored-by: Danny Avila <danny@librechat.ai>	2026-03-30 16:49:23 -04:00