* ⚡ feat: Add Gemini 3.8 Flash Support
Adds first-class support for Google's Gemini 3.8 Flash (`gemini-3.8-flash`,
GA 2026-09-02) for both the Gemini API (AI Studio) and Google Cloud Gemini
Enterprise Agent Platform, following the Gemini 3.7 Flash integration (#14818).
The Flash-family handler that PR generalized already carries the shape 3.8
needs, so registering the model is a one-line rule rather than new behavior:
it inherits the strip of deprecated sampling params (temperature/topP/topK),
the rejected penalty params, and `thinkingBudget`, defaults to `medium`
thinking, and — like 3.7 — errors on `minimal`, so an explicit `minimal` is
substituted with the nearest supported level, `low`.
- Context window (1,048,576) in googleModels; API + cache pricing in tx.ts
- Model dropdown (config.ts) and GOOGLE_MODELS examples for both integrations
- Register the model in the Flash-family thinking-rule table
- Apply the same introductory pricing as 3.6/3.7 Flash ($0.75 in / $3.75 out /
$0.075 cached, per 1M), reverting to $1.50 / $7.50 / $0.15 on 2027-01-01;
the existing comments at both call sites now name 3.8 alongside 3.6/3.7
- Tests mirroring the 3.7 Flash coverage: thinking default, legacy-param strip,
explicit level pass-through, `minimal` substitution, versioned aliases,
context window, model-key mapping, and rates
Refs #15516
Ref: https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash
Ref: https://ai.google.dev/gemini-api/docs/pricing
* 🔧 chore: Update @librechat/agents dependency to version 3.7.15 in package-lock.json and related package.json files
Claude Fable 5.1 (`claude-fable-5-1`, GA 2026-09-01) succeeds Claude Fable 5
at the same input/output prices, with a 1M context window and 128K max output.
The Mythos-class helpers added for Fable 5 already match it — `isMythosClassModel`
tests `claude-(?:fable|mythos)[-.]?\d`, so adaptive thinking, summarized-display
opt-in, sampling omission, 1M context, the 128K output clamp, prompt caching,
the Vertex multi-region gate, and the Bedrock PDF exemption all cover 5.1
without a code change. What was missing was registration and pricing.
Cache reads are the one rate that differs, and the substring matcher would have
silently gotten it wrong: `claude-fable-5-1` falls through to the `claude-fable-5`
key, which prices cache hits at the usual 0.1x base input ($1/MTok). Fable 5.1
and Mythos 5.1 price them at 0.025x ($0.25/MTok), so every cache read would have
billed 4x — on exactly the long agentic sessions this model is built for.
- Register `claude-fable-5-1` in the shared Anthropic list and
`global.anthropic.claude-fable-5-1` in the Bedrock list
- Add 1M context / 128K output entries for `claude-fable-5-1` and
`claude-mythos-5-1`
- Add $10/$50 rates and `{ write: 12.5, read: 0.25 }` cache rates for both
- Update the `.env.example` and Vertex `librechat.example.yaml` examples
- Test that 5.1 resolves to its own key rather than collapsing onto 5.0, across
token maps, pricing, cache rates, and Mythos-class detection
The three documented breaking changes from Fable 5 need no handling here:
LibreChat never sends a forced `tool_choice` on the Anthropic path (the agents
SDK omits the param when unset, so the API default `auto` applies); thinking
blocks an earlier model can't read are dropped server-side, unbilled; and
history is rebuilt from stored content parts rather than replayed signed
thinking blocks, so the prefix-binding check has nothing to reject.
Refs #15506
* ⚡ feat: Add Gemini 3.7 Flash Support
Adds first-class support for Google's Gemini 3.7 Flash (`gemini-3.7-flash`)
for both the Gemini API (AI Studio) and Google Cloud Gemini Enterprise Agent
Platform, following the Gemini 3.6 Flash integration (#14369).
- Context window (1,048,576) in googleModels; API + cache pricing in tx.ts.
- Model dropdown (config.ts) and GOOGLE_MODELS examples for both integrations.
- Register the model in the Flash-family handler so it inherits the existing
strip of deprecated sampling params (temperature/topP/topK), rejected
penalty params, and thinkingBudget, and defaults to `medium` thinking.
- Generalize that handler's enumerated table from a [id, level] tuple to a
rule object, so a model can also declare thinking levels it rejects. Gemini
3.7 Flash errors on `minimal` (which the Google endpoint offers in its
thinkingLevel slider), so an explicit `minimal` is substituted with the
nearest supported level, `low`. Explicit low/medium/high pass through
unchanged.
- Apply Google's introductory pricing ($0.75 in / $3.75 out / $0.075 cached,
per 1M) to Gemini 3.7 Flash and correct Gemini 3.6 Flash to the same rates.
Both revert to $1.50 / $7.50 / $0.15 on 2027-01-01; noted at both call sites.
Resolves#14802
Ref: https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash
Ref: https://ai.google.dev/gemini-api/docs/pricing
* 📝 docs: Match the House Style for Promotional Rate Comments
Align the Gemini 3.6/3.7 Flash introductory-pricing notes with the existing
Sonnet 5 convention in the same file: one comment per group, naming the models
and the exact values to restore, so the manual follow-up is unambiguous.
No rate changes.
* ⬆️ chore: Bump `@librechat/agents` to 3.4.7 for Gemini 3.7 Flash Prefill
Unblocks this PR. `NO_PREFILL_GEMINI_MODELS` is model-enumerated in the agents
SDK, so 3.4.6 does not know `gemini-3.7-flash` forbids a trailing `model`-role
turn — editing an assistant reply and resubmitting would reach Google as a
prefill and return HTTP 400 on a model this PR adds to the default list.
3.4.7 (danny-avila/agents#412, released via #413) adds it. Verified the
published tarball: `3.4.6...3.4.7` touches only
`dist/{cjs,esm}/llm/google/utils/common.*` — the prefill array and its comment.
`dist/types` is byte-identical, so there is no API surface change.
Raises the declared range in both workspaces alongside the lock. `^3.4.6`
already permitted 3.4.7, but the fix is required rather than merely compatible,
so the floor should say so.
* ✳️ feat: Claude Opus 5 Support
- Add claude-opus-5 to Anthropic/Bedrock model lists, token maps, and pricing
- Extend requiresExplicitThinkingDisabled to Opus 5 so thinking-off sticks
- Clamp xhigh/max effort to high when thinking is disabled (Opus 5 400)
* 🪣 fix: Use Bedrock Inference Profiles and Add Vertex Opus Models
Bare `anthropic.` Claude 4+ IDs are not invocable on-demand via Converse:
Bedrock rejects them with "Retry your request with the ID or ARN of an
inference profile that contains this model." Verified live against
us-west-2 for Fable 5, Opus 5, Opus 4.8, Sonnet 5, Sonnet 4.6, Opus 4.6,
Sonnet 4.5, Haiku 4.5, and Opus 4.1. Switch those defaults to the
`global.` profile (no regional pricing premium); Opus 4.1 has no global
profile, so it uses `us.`.
Also add the modern Opus family to the Vertex defaults. `loadEndpoints`
swaps the shared Anthropic list for the Vertex model names, so Opus was
invisible to every Vertex deployment that did not enumerate models by hand.
* 📋 chore: Cover Opus 5 Gaps From PR #14420
Picks up items from the parallel community PR by @jona7o:
- Add claude-opus-5 to the librechat.example.yaml Vertex example (both the
legacy array and the deploymentName map), which already lists Fable 5
and Opus 4.8
- Mention Opus 5 in the configureReasoning doc comment, and note that its
early return is why the effort cap is enforced by the caller
- Assert Opus 5 carries no long-context premium pricing
- Cover the Sonnet 5 negative case for the effort cap, and the persisted
disabled-object round-trip carrying an effort
* 🌍 docs: Warn That Vertex Regional Endpoints Reject Modern Models
Anthropic serves Sonnet 4.6 and earlier on specific Vertex regional
endpoints; newer models (Opus 4.7+, Opus 5, Sonnet 5, Fable 5) require
`global` or a multi-region location and 404 on a specific region. The
`us-east5` default therefore cannot serve the Opus models added here, nor
the Sonnet 5 entry that predates this branch.
Documents the constraint at all three places an operator sets the region,
and at the fallback itself. Leaves the default unchanged: switching it to
`global` would silently alter data routing and residency for existing
deployments, which is a separate call.
* 🩹 fix: Restore PDF Exemption for Undated IDs and Gate Vertex Defaults
Two issues raised in review:
- BEDROCK_CLAUDE_4_PLUS_RE required a `-` after the major version, so it
matched `claude-opus-4-8` but not undated IDs like `claude-opus-5`.
Those models silently lost the Claude 4+ PDF exemption and fell back to
the 4.5 MB limit. Sonnet 5 and Fable 5 were already affected before this
branch; Fable/Mythos were also missing from the family alternation.
- The Vertex defaults advertised models that only `global` and the
multi-region locations serve, so a default `us-east5` deployment listed
Opus choices that 404 on first request. Filter the built-in defaults by
configured region instead of changing the region default, which would
alter data routing for existing deployments. An explicit `vertex.models`
list is the operator's choice and is never pruned.
* 🧩 fix: Match Bare Claude IDs in the Bedrock PDF Exemption
An application inference profile maps a LibreChat model ID with no
`anthropic.` segment, so `claude-opus-5` failed the Claude 4+ check and
fell back to the 4.5 MB PDF limit. Make the prefix optional and accept
both segment orders, mirroring BEDROCK_CLAUDE_4PLUS_THINKING in
librechat-data-provider, which matches on the family token for exactly
this reason.
Only reached for the Bedrock provider, so the looser prefix cannot leak
into other endpoints. Verified Claude 3.x, Nova, Llama, Cohere, and
Mistral IDs still fall through to the default limit.
* 🧹 fix: Drop Retired Claude 3.5 Models From Bedrock Defaults
The three Claude 3.5 entries reached end of life at AWS and return
ResourceNotFoundException in every prefix form (bare, `us.`, `global.` —
verified live against us-west-2), so selecting one was a hard error.
Their modern equivalents are already in the list: Sonnet 5 / Sonnet 4.6
supersede the 3.5 Sonnets, and Haiku 4.5 supersedes 3.5 Haiku.
Every remaining Anthropic default is now live-verified invocable.
`.env.example` swaps its retired example ID for Haiku 4.5.
* 🔒 refactor: Narrow Effort-Clamp Types Instead of Asserting
Both clamp sites reached into loosely-typed containers with assertions:
llm.ts used an `as unknown as { type?: string }` double assertion to read
the thinking type, and the Bedrock parser cast `output_config` to
`{ effort?: unknown }` before confirming it was an object. CLAUDE.md's
type-safety rules call for narrowing over both.
Adds `isThinkingDisabled` and `clampOutputConfigEffort` to
librechat-data-provider, using `in`-operator narrowing and a type
predicate so no assertion is needed at all. Both call sites now share one
implementation rather than duplicating the clamp.
Behavior is unchanged; existing clamp tests cover it.
* ⚡ feat: Add Gemini 3.6 Flash and Gemini 3.5 Flash-Lite Support
Adds first-class support for Google's Gemini 3.6 Flash (`gemini-3.6-flash`)
and Gemini 3.5 Flash-Lite (`gemini-3.5-flash-lite`) for both the Gemini API
(AI Studio) and Google Cloud/Vertex integrations.
- Context window (1M) in googleModels; API + cache pricing in tx.ts.
- Model dropdown (config.ts) and GOOGLE_MODELS examples for both integrations.
- Generalize the Gemini 3.5 Flash overrides into a flash-family handler that
strips deprecated temperature/topP/topK and applies each model's default
thinking level (3.6 Flash: medium, 3.5 Flash-Lite: minimal), with
longest-prefix resolution so flash-lite does not collide with flash.
Ref: https://ai.google.dev/gemini-api/docs/latest-model#api-changes-and-parameter-updates
* 🩹 fix: Strip unsupported penalty params for Gemini Flash family
Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash reject presencePenalty/
frequencyPenalty with HTTP 400 ("Penalty is not enabled for this model",
verified live). These pass through llmConfig via knownGoogleParams, so add
them to the flash-family strip list alongside the deprecated sampling params.
* 🩹 fix: Strip Flash-blocked params on custom Google endpoint path
For custom OpenAI-compatible endpoints with defaultParamsEndpoint=google,
getOpenAIConfig strips Flash-blocked params via getGoogleConfig but then
transformToOpenAIConfig re-applies raw addParams, undoing the strip. Filter
addParams through stripGeminiFlashBlockedParams before the transform so the
deprecated sampling / rejected penalty params cannot reach the provider.
* 🔧 chore: Update sharp package to version 0.35.3 in package-lock.json, api/package.json, and packages/api/package.json
* 🔧 chore: Update dependencies in package-lock.json to latest versions for @google/genai (2.13.0), @hono/node-server (1.19.14), fast-uri (3.1.4), hono (4.12.31), and svgo (2.8.3)
* 🔧 chore: Update dependencies in package.json and package-lock.json for @librechat/agents (3.2.67), @opentelemetry/sdk-node (0.221.0), and add new dependencies for @opentelemetry/propagator-jaeger (2.10.0) and protobufjs (7.6.5). Update monaco-editor version in client package.json to 0.56.0.
* 🔧 chore: Upgrade turbo package to version 2.10.5 in package.json and package-lock.json, and update schema reference in turbo.json
* 🩹 fix: Resolve CI breakage from bundled dependency bumps
Not related to the Gemini models — both are fallout from the dep bumps on
this branch:
- monaco-editor 0.56 changed IEditorHoverOptions.enabled from boolean to
'on' | 'off' | 'onKeyboardModifier'; update ArtifactCodeEditor to match
(mirrors the sibling occurrencesHighlight/matchBrackets pattern).
- sharp 0.35.3 fails resize+encode on a degenerate 1x1 PNG (vipspng: libpng
read error); the provider-file e2e fixture was 1x1, so use a 16x16 PNG.
Normal images are unaffected (verified 64x64 resize/encode/jpeg all OK).
* 📝 docs: Correct e2e image-fixture comment (bad IDAT CRC, not a sharp bug)
Root cause was the old 1x1 fixture's corrupt IDAT CRC (verified: IHDR/IEND
CRC OK, IDAT CRC BAD), which sharp 0.35.3's stricter libpng correctly rejects.
Not a dimension/resize edge case and not a sharp bug; comment now reflects that.
* ✨ feat: Add GPT-5.6 (Sol/Terra/Luna) OpenAI models
Adds the GPT-5.6 family (GA 2026-07-09) across the context, output,
pricing, cache, premium, and default-model maps, mirroring gpt-5.5.
- gpt-5.6 (Sol alias), gpt-5.6-terra, gpt-5.6-luna
- 1.05M context / 128K output for all tiers
- Standard + long-context (>272K input) tiered pricing and cache rates
* 🐛 fix: Bill GPT-5.6 cache writes at documented 1.25x input surcharge
OpenAI prices GPT-5.6 cache writes above the base input rate (Sol $6.25,
Terra $3.125, Luna $1.25 per 1M vs $5/$2.50/$1 input). Correct the
cacheTokenValues write rates so explicit prompt-caching usage is billed
and reported accurately, and lock the surcharge with a test.
* ✨ feat: Expose GPT-5.6 max reasoning effort + long-context cache premium
Folds in the two deferred Codex findings:
1. Add `max` to the OpenAI `ReasoningEffort` enum and the reasoning_effort
parameter options/labels so GPT-5.6 (Sol/Terra/Luna) can request its
documented highest reasoning setting. Backend passthrough and zod
validation pick it up via the nativeEnum schema.
2. Apply the long-context (>272K input) premium to cache tokens. Adds
`premiumCacheTokenValues` + `getPremiumCacheRate`, threads
`inputTokenCount` into `getCacheMultiplier`, and wires it through both
structured-spend paths. Covers the gpt-5.4/5.5/5.6 family whose cache
write/read previously stayed at flat base rates on long-context calls.
* 🐛 fix: Bill GPT-5.6 cache writes + map max effort for OpenRouter Claude
Addresses Codex round-3 findings:
1. (P1) splitUsage only read `cache_creation`/`cache_creation_input_tokens`,
so OpenAI GPT-5.6's `cache_write_tokens` fell into inputOnly and billed at
the input rate instead of the 1.25x write rate. Extend UsageMetadata and
single-source the cache-creation read to also recognize `cache_write_tokens`
(nested and top-level).
2. (P2) `max` was exposed via OpenRouter (spreads OpenAI settings) but the
adaptive-Claude verbosity map had no `max`, so it was silently dropped. Map
max -> 'max' verbosity.
* 🐛 fix: Forward GPT-5.6 cache_write_tokens into emitted usage
Local Codex review (P1): the cache-write fix reached balance billing
(splitUsage/getCacheCreationTokens) but not the emitted-usage pipeline.
ModelEndHandler built the emitted event's cache_creation from only
cache_creation/cache_creation_input_tokens, so GPT-5.6 cache_write_tokens
were dropped and aggregateEmittedUsage classified them as ordinary input —
displayed/persisted cost undercounted and disagreed with the balance charge.
Fold cache_write_tokens (nested + top-level) into the emitted cache_creation.
* ✨ feat: Add Claude Sonnet 5 Support
Wire up the claude-sonnet-5 model across token, pricing, and model-list
config:
- Context window (1M) and max output (128K) in @librechat/api token maps
- Standard pricing ($3/$15 per MTok) and cache rates in data-schemas tx
- 128K output-token carve-out in anthropicSettings (the family-wide 64K
rule capped Sonnet 5 below its real limit); Bedrock/Vertex thinking and
1M-context detection already cover sonnet major >= 5 generically
- Add to shared Anthropic, Bedrock, and Vertex default model lists, plus
the .env.example examples
- Tests for context/output/pricing/matching across the affected packages
* ✅ test: Align Sonnet 5+ maxOutputTokens defaults with 128K spec
getLLMConfig defaults flow from anthropicSettings.maxOutputTokens.reset(),
which now returns 128K for Sonnet 5+. Update the future-proofing assertions
in llm.spec.ts (Sonnet 5.x and 6-9.x) that still expected the old family-wide
64K cap. Haiku stays 64K; Opus stays 128K.
* 🎚️ fix: Gate Sonnet 5 capability behaviors (sampling, thinking)
Adding claude-sonnet-5 to the default list exposed it without the Anthropic
capability gates, all confirmed against the live API:
- omitsSamplingParameters: Sonnet 5 returns 400 on non-default temperature/
top_p/top_k ('deprecated for this model'); now dropped so selecting the
model with saved sampling settings no longer fails.
- requiresExplicitThinkingDisabled: omitting 'thinking' runs adaptive ON by
default on Sonnet 5, so disabling thinking now sends { type: 'disabled' }
(verified: 200, no thinking block) instead of omitting the field.
- omitsThinkingByDefault: thinking.display defaults to omitted (empty thinking
blocks); the display resolver now returns 'summarized' for Sonnet 5+ so the
Thoughts UI keeps working (verified: 757-char summary returned).
Gates apply to both the direct Anthropic and Bedrock paths. Tests added in
bedrock.spec and llm.spec.
* 🩹 fix: Sonnet 5 Bedrock availability + thinking-off persistence
Round-2 Codex review (all verified against the live API / Anthropic docs):
- Sonnet 5 is NOT available on the legacy Bedrock InvokeModel/Converse surface
(Anthropic docs: 'use Claude in Amazon Bedrock or Claude Platform on AWS'),
which is what LibreChat's ChatBedrockConverse uses. Removed it from the
default Bedrock model lists (config + .env.example). Opus 4.8/4.7/Fable 5
stay — those ARE reachable via InvokeModel. Sonnet 5 remains on the direct
Anthropic API and Vertex, where it works.
- Reverted the Bedrock-side explicit-disabled thinking handling added last
round: with Sonnet 5 off Bedrock, no Bedrock model needs { type: 'disabled' },
so that path (and its round-trip concern) no longer applies.
- Direct Anthropic path: a persisted { type: 'disabled' } thinking object now
normalizes to a boolean flag in getLLMConfig, so a user's Sonnet 5
'thinking off' setting stays off across the model_parameters round trip
instead of flipping back to adaptive (a truthy object skipped the disabled
branch).
* ↩️ fix: Restore Sonnet 5 on Bedrock (Converse) — verified live
Reverses the round-2 removal: Sonnet 5 IS available on AWS Bedrock. Tested
live via the Converse API:
- global.anthropic.claude-sonnet-5 returns a normal response
- bare anthropic.claude-sonnet-5 needs an inference profile — but that's
identical to the already-shipping Opus 4.8 / Fable 5 / Sonnet 4.6 entries,
which all fail bare on-demand the same way
- temperature=0.5 -> 400 'deprecated for this model'; thinking {type:disabled}
suppresses reasoning — same as the direct API
The 'legacy' Bedrock docs page that claimed Sonnet 5 wasn't on the surface is
stale. Restored:
- anthropic.claude-sonnet-5 in bedrockModels + .env.example
- the Bedrock explicit-disabled thinking handling (requiresExplicitThinkingDisabled
-> { type: 'disabled' })
- the Finding 4 round-trip fix in bedrockInputSchema (coerce a persisted
disabled AMRF.thinking to thinking=false instead of !!thinking -> true), with
an end-to-end schema->parser test proving 'thinking off' stays sticky.
Direct-path round-trip fix (getLLMConfig thinkingFlag) is unchanged.
* 💵 fix: Sonnet 5 intro pricing + sticky disabled thinking on Bedrock reload
Round-4 Codex review (both verified):
- Pricing: Anthropic lists Sonnet 5 at introductory $2/$10 per MTok (cache
$2.50/$0.20) through 2026-08-31, reverting to $3/$15 ($3.75/$0.30) on
Sep 1 (confirmed on platform.claude.com/pricing). The static tx multiplier
table is used for real balance transactions, so the post-intro rates were
overcharging ~50% during the launch window. Switched to the intro rates with
a revert comment on both the token and cache entries.
- Bedrock disabled-thinking persistence: initializeBedrock feeds persisted
model_parameters straight through bedrockInputParser (NOT bedrockInputSchema),
where additionalModelRequestFields is a known key — so a prior
thinking:{type:'disabled'} was ignored and rebuilt as adaptive on reload.
bedrockInputParser now surfaces a persisted disabled AMRF.thinking as
thinking=false so it re-emits {type:'disabled'}. Verified end-to-end against
the real initializeBedrock call path.
* 📖 feat: Add Claude Fable 5 Support
Claude Fable 5 (`claude-fable-5`) is Anthropic's most capable widely
released model (GA 2026-06-09). Its naming drops the opus/sonnet/haiku
tier, so LibreChat's name-parsing helpers miss it; this teaches them the
Mythos-class family (Fable / Mythos) and registers the model.
- Add `parseMythosClassVersion` and route Fable/Mythos through
`supportsAdaptiveThinking`, `omitsThinkingByDefault`,
`omitsSamplingParameters`, and `supportsContext1m`
- Extend the Bedrock detection regexes (beta headers + adaptive-thinking
branch) and `checkPromptCacheSupport` to match `claude-(fable|mythos)`
- Return 128K max output for Fable/Mythos in `maxOutputTokens.reset`/`set`
- Register `claude-fable-5` in shared Anthropic + Bedrock model lists,
1M context / 128K output token maps, and $10/$50 pricing with 12.5/1
cache rates (`claude-mythos-5` added to token + pricing maps only,
since it is limited-availability)
- Update `.env.example` and the Vertex `librechat.example.yaml` examples
- Add parallel tests across tokens, Anthropic llm config, the Bedrock
parser, and tx pricing
* 🧹 refactor: Centralize Mythos-class detection; address review feedback
- Add `isMythosClassModel` + `MYTHOS_CLASS_FAMILIES` in schemas.ts as the
single source of truth for the Fable/Mythos family; route every gate
(adaptive thinking, omit-thinking, omit-sampling, 1M context, prompt cache,
128K max-output reset/set) through it. A future sibling class is now a
one-line edit.
- [Codex P2] Exclude Mythos-class from getBedrockAnthropicBetaHeaders: Fable/
Mythos ship 128K output + fine-grained tool streaming by default, and the
legacy output-128k-2025-02-19 beta is 3.7-Sonnet-only on Bedrock and risks
request rejection. They still get adaptive thinking + effort.
- [Copilot] Add Mythos 5 test parity (name variations, cache rates, pinned
$10/$50) in tx.spec; add Mythos context/max-output/name-match in tokens.spec;
fix the stale claude-3-7-sonnet-only comment in bedrock.ts.
- Add isMythosClassModel unit tests covering all declared families.
* 📝 docs: Clarify Mythos-class Bedrock requirements; correct beta-omit rationale
Verified live against Bedrock (acct 951834775723, us-west-2):
- anthropic.claude-fable-5 IS a real Bedrock catalog model, INFERENCE_PROFILE-only
exactly like the existing anthropic.claude-opus-4-7/4-8 and claude-sonnet-4-6
default entries (refutes the "invalid model id" review claim).
- Mythos-class also requires opting into Anthropic data sharing (Bedrock Data
Retention API) before invocation.
Changes:
- .env.example: note that Mythos-class (Fable/Mythos) is inference-profile-only on
Bedrock and needs the data-sharing opt-in.
- bedrock.ts: reword the beta-omit comment to the verified rationale — output-128k /
fine-grained-tool-streaming are built-in/no-op for the 4.7+ generation, so omitting
them is lossless (dropped the unverified "Bedrock may reject" wording).
* 🔄 refactor: Reorganize imports in schemas.ts and tx.spec.ts
- Moved `TFeedback` and `Tools` imports to the top of `schemas.ts` for better readability.
- Adjusted import order in `tx.spec.ts` to maintain consistency and improve clarity.
* feat: add Claude Opus 4.8 support
* fix: omit sampling params for Claude Opus 4.8
* fix: flatten Bedrock beta header merge
* fix: strip Bedrock sampling params for Opus 4.8
* 🦉 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
* chore: remove deprecated Gemini 2.0 models from default models list
Remove gemini-2.0-flash-001 and gemini-2.0-flash-lite from the Google
default models array, as they have been deprecated by Google.
Closes#12444
* fix: add mistral-large-3 max context tokens (256k)
Add mistral-large-3 with 255000 max context tokens to the mistralModels
map. Without this entry, the model falls back to the generic
mistral-large key (131k), causing context window errors when using
tools with Azure AI Foundry deployments.
Closes#12429
* test: add mistral-large-3 token resolution tests and fix key ordering
Add test coverage for mistral-large-3 context token resolution,
verifying exact match, suffixed variants, and longest-match precedence
over the generic mistral-large key. Reorder the mistral-large-3 entry
after mistral-large to follow the file's documented convention of
listing newer models last for reverse-scan performance.
* ✨ feat: Add support for new GPT-5.4 and GPT-5.4-pro models
- Introduced new token values and cache settings for 'gpt-5.4' and 'gpt-5.4-pro' in the API model configurations.
- Updated maximum output limits for the new models in the tokens utility.
- Included 'gpt-5.4' and 'gpt-5.4-pro' in the shared OpenAI models list for consistent access across the application.
* 🔧 update: Enhance GPT-5.4 and GPT-5.4-pro model configurations
- Refined token pricing and cache settings for 'gpt-5.4' and 'gpt-5.4-pro' in the API model configurations.
- Added tests for cache multipliers and maximum token limits for the new models.
- Updated shared OpenAI models list to include 'gpt-5.4-thinking' and added a note for verifying pricing before release.
* 🔧 update: Add clarification to token pricing for 'gpt-5.4-pro'
- Added a comment to the 'gpt-5.4-pro' model configuration in tokens.ts to specify that it shares the same token window as 'gpt-5.4', enhancing clarity for future reference.
* 🔧 fix: Use longest-match in findMatchingPattern, remove deprecated PaLM2/Codey models
findMatchingPattern now selects the longest matching key instead of the
first reverse-order match, preventing cross-provider substring collisions
(e.g., "gpt-5.2-chat-2025-12-11" incorrectly matching Google's "chat-"
pattern instead of OpenAI's "gpt-5.2"). Adds early exit when key length
equals model name length. Reorders aggregateModels spreads so OpenAI is
last (preferred on same-length ties). Removes deprecated PaLM2/Codey
entries from googleModels.
* refactor: re-order models based on more likely usage
* refactor: Improve key matching logic in findMatchingPattern
Updated the findMatchingPattern function to enhance key matching by ensuring case-insensitive comparisons and maintaining the longest match priority. Clarified comments regarding key ordering and performance implications, emphasizing the importance of defining older models first for efficiency and the handling of same-length ties. This refactor aims to improve code clarity and maintainability.
* test: Enhance findMatchingPattern tests for edge cases and performance
Added new test cases to the findMatchingPattern function, covering scenarios such as empty model names, case-insensitive matching, and performance optimizations. Included checks for longest match priority and ensured deprecated PaLM2/Codey models are no longer present in token entries. This update aims to improve test coverage and validate the function's behavior under various conditions.
* test: Update findMatchingPattern test to use last key for exact match validation
Modified the test for findMatchingPattern to utilize the last key from the openAIMap for exact match checks, ensuring the test accurately reflects the expected behavior of the function. This change enhances the clarity and reliability of the test case.
* 💰 feat: Add gpt-5.3 context window and pricing
* 💰 feat: Add OpenAI cached input pricing and `gpt-5.2-pro` model
- Add cached input pricing (write/read) for gpt-4o, gpt-4.1, gpt-5.x,
o1, o3, o4-mini models with correct per-family discount tiers
- Add gpt-5.2-pro pricing ($21/$168), context window, and max output
- Pro models (gpt-5-pro, gpt-5.2-pro) correctly excluded from cache
pricing as OpenAI does not support caching for these
* 🔍 fix: Address review findings for OpenAI pricing
- Add o1-preview to cacheTokenValues (50% discount, same as o1)
- Fix comment to enumerate all models per discount tier
- Add cache tests for dated variants (gpt-4o-2024-08-06, etc.)
- Add gpt-5-mini/gpt-5-nano to 10% ratio invariant test
- Replace forEach with for...of in new test code
- Fix inconsistent test description phrasing
- Add gpt-5.3-preview to context window tests
- Added support for the new Gemini 3.1 models, including 'gemini-3.1-pro-preview' and 'gemini-3.1-pro-preview-customtools'.
- Updated pricing logic to apply standard and premium rates based on token usage thresholds for the new models.
- Enhanced tests to validate pricing behavior for both standard and premium scenarios.
- Modified configuration files to include Gemini 3.1 models in the default model lists and token value mappings.
- Updated environment example file to reflect the new model options.
* 🤖 feat: Claude Sonnet 4.6 support
- Updated .env.example to include claude-sonnet-4-6 in the list of available models.
- Enhanced token value assignments in api/models/tx.js and packages/api/src/utils/tokens.ts to accommodate claude-sonnet-4-6.
- Added tests in packages/data-provider/specs/bedrock.spec.ts to verify support for claude-sonnet-4-6 in adaptive thinking and context-1m functionalities.
- Modified bedrock.ts to correctly parse and identify the version of claude-sonnet-4-6 for adaptive thinking checks.
- Included claude-sonnet-4-6 in sharedAnthropicModels and bedrockModels for consistent model availability.
* chore: additional Claude Sonnet 4.6 tests
- Added unit tests for Claude Sonnet 4.6 in `tokens.spec.js` to verify context length and max output tokens.
- Updated `helpers.ts` documentation to reflect adaptive thinking support for Sonnet 4.6.
- Enhanced `llm.spec.ts` with tests for context headers and adaptive thinking configurations for Claude Sonnet 4.6.
- Improved `bedrock.spec.ts` to ensure correct parsing and handling of Claude Sonnet 4.6 model variations with adaptive thinking.
* feat: Implement new features for Claude Opus 4.6 model
- Added support for tiered pricing based on input token count for the Claude Opus 4.6 model.
- Updated token value calculations to include inputTokenCount for accurate pricing.
- Enhanced transaction handling to apply premium rates when input tokens exceed defined thresholds.
- Introduced comprehensive tests to validate pricing logic for both standard and premium rates across various scenarios.
- Updated related utility functions and models to accommodate new pricing structure.
This change improves the flexibility and accuracy of token pricing for the Claude Opus 4.6 model, ensuring users are charged appropriately based on their usage.
* feat: Add effort field to conversation and preset schemas
- Introduced a new optional `effort` field of type `String` in both the `IPreset` and `IConversation` interfaces.
- Updated the `conversationPreset` schema to include the `effort` field, enhancing the data structure for better context management.
* chore: Clean up unused variable and comments in initialize function
* chore: update dependencies and SDK versions
- Updated @anthropic-ai/sdk to version 0.73.0 in package.json and overrides.
- Updated @anthropic-ai/vertex-sdk to version 0.14.3 in packages/api/package.json.
- Updated @librechat/agents to version 3.1.34 in packages/api/package.json.
- Refactored imports in packages/api/src/endpoints/anthropic/vertex.ts for consistency.
* chore: remove postcss-loader from dependencies
* feat: Bedrock model support for adaptive thinking configuration
- Updated .env.example to include new Bedrock model IDs for Claude Opus 4.6.
- Refactored bedrockInputParser to support adaptive thinking for Opus models, allowing for dynamic thinking configurations.
- Introduced a new function to check model compatibility with adaptive thinking.
- Added an optional `effort` field to the input schemas and updated related configurations.
- Enhanced tests to validate the new adaptive thinking logic and model configurations.
* feat: Add tests for Opus 4.6 adaptive thinking configuration
* feat: Update model references for Opus 4.6 by removing version suffix
* feat: Update @librechat/agents to version 3.1.35 in package.json and package-lock.json
* chore: @librechat/agents to version 3.1.36 in package.json and package-lock.json
* feat: Normalize inputTokenCount for spendTokens and enhance transaction handling
- Introduced normalization for promptTokens to ensure inputTokenCount does not go negative.
- Updated transaction logic to reflect normalized inputTokenCount in pricing calculations.
- Added comprehensive tests to validate the new normalization logic and its impact on transaction rates for both standard and premium models.
- Refactored related functions to improve clarity and maintainability of token value calculations.
* chore: Simplify adaptive thinking configuration in helpers.ts
- Removed unnecessary type casting for the thinking property in updatedOptions.
- Ensured that adaptive thinking is directly assigned when conditions are met, improving code clarity.
* refactor: Replace hard-coded token values with dynamic retrieval from maxTokensMap in model tests
* fix: Ensure non-negative token values in spendTokens calculations
- Updated token value retrieval to use Math.max for prompt and completion tokens, preventing negative values.
- Enhanced clarity in token calculations for both prompt and completion transactions.
* test: Add test for normalization of negative structured token values in spendStructuredTokens
- Implemented a test to ensure that negative structured token values are normalized to zero during token spending.
- Verified that the transaction rates remain consistent with the expected standard values after normalization.
* refactor: Bedrock model support for adaptive thinking and context handling
- Added tests for various alternate naming conventions of Claude models to validate adaptive thinking and context support.
- Refactored `supportsAdaptiveThinking` and `supportsContext1m` functions to utilize new parsing methods for model version extraction.
- Updated `bedrockInputParser` to handle effort configurations more effectively and strip unnecessary fields for non-adaptive models.
- Improved handling of anthropic model configurations in the input parser.
* fix: Improve token value retrieval in getMultiplier function
- Updated the token value retrieval logic to use optional chaining for better safety against undefined values.
- Added a test case to ensure that the function returns the default rate when the provided valueKey does not exist in tokenValues.
* ✨ feat: Add Moonshot Provider Support
- Updated the `isKnownCustomProvider` function to include `Providers.MOONSHOT` in the list of recognized custom providers.
- Enhanced the `providerConfigMap` to initialize `MOONSHOT` with the custom initialization function.
- Introduced `MoonshotIcon` component for visual representation in the UI, integrated into the `UnknownIcon` component.
- Updated various files across the API and client to support the new `MOONSHOT` provider, including configuration and response handling.
This update expands the capabilities of the application by integrating support for the Moonshot provider, enhancing both backend and frontend functionalities.
* ✨ feat: Add Moonshot/Kimi Model Pricing and Tests
- Introduced new pricing configurations for Moonshot and Kimi models in `tx.js`, including various model variations and their respective prompt and completion values.
- Expanded unit tests in `tx.spec.js` and `tokens.spec.js` to validate pricing and token limits for the newly added Moonshot/Kimi models, ensuring accurate calculations and handling of model variations.
- Updated utility functions to support the new model structures and ensure compatibility with existing functionalities.
This update enhances the pricing model capabilities and improves test coverage for the Moonshot/Kimi integration.
* ✨ feat: Enhance Token Pricing Documentation and Configuration
- Added comprehensive documentation for token pricing configuration in `tx.js` and `tokens.ts`, emphasizing the importance of key ordering for pattern matching.
- Clarified the process for defining base and specific patterns to ensure accurate pricing retrieval based on model names.
- Improved code comments to guide future additions of model families, enhancing maintainability and understanding of the pricing structure.
This update improves the clarity and usability of the token pricing configuration, facilitating better integration and future enhancements.
* chore: import order
* chore: linting
* 🔧 chore: Update @librechat/agents to version 3.0.35
* ✨ feat: Add DeepSeek Model Pricing and Token Handling
- Introduced pricing and token limits for 'deepseek-chat' and 'deepseek-reasoner' models, including prompt and completion rates.
- Enhanced tests to validate pricing and token limits for DeepSeek models, ensuring correct handling of model variations and provider prefixes.
- Updated cache multipliers for DeepSeek models to reflect new pricing structure.
- Improved max output token handling for DeepSeek models, ensuring consistency across different endpoints.
* 🤖 feat: Latest Grok Model Pricing & Context Rates
- Introduced 'grok-4-fast', 'grok-4-1-fast', and 'grok-code-fast' models with their respective prompt and completion rates.
- Enhanced unit tests to validate prompt and completion rates for the new models, including variations with prefixes.
- Updated token limits for the new models in the tokens utility, ensuring accurate handling in tests.
* 🔧 refactor: Optimize JSON Export Logic in useExportConversation Hook
Updated the export logic to create a Blob from the JSON string before downloading, improving compatibility and performance for file downloads. This change enhances the handling of deeply nested exports while maintaining the file size reduction achieved in previous updates.
* 🤖 feat: Claude Opus 4.5 Token Rates and Window Limits
- Introduced new model 'claude-opus-4-5' with defined prompt and completion values in tokenValues and cacheTokenValues.
- Updated tests to validate prompt, completion, and cache rates for the new model.
- Enhanced model name handling to accommodate variations for 'claude-opus-4-5' across different contexts.
- Adjusted schemas to ensure correct max output token limits for the new model.
* ci: Add tests for "prompt-caching" beta header in Claude Opus 4.5 models
- Implemented tests to verify the addition of the "prompt-caching" beta header for the 'claude-opus-4-5' model and its variations.
- Updated future-proofing logic to ensure correct max token limits for Claude 4.x and 5.x Opus models, adjusting defaults to 64K where applicable.
- Enhanced existing tests to reflect changes in expected max token values for future Claude models.
* chore: Remove redundant max output check for Anthropic settings
- Eliminated the unnecessary check for ANTHROPIC_MAX_OUTPUT in the anthropicSettings schema, streamlining the logic for handling max output values.
* feat: Add support for model in token configurations and tests
* chore: Update @librechat/agents to version 3.0.26 in package.json and package-lock.json
* updated gpt5-pro
it is here and on openrouter
https://platform.openai.com/docs/models/gpt-5-pro
* feat: Add gpt-5-pro pricing
- Implemented handling for the new gpt-5-pro model in the getValueKey function.
- Updated tests to ensure correct behavior for gpt-5-pro across various scenarios.
- Adjusted token limits and multipliers for gpt-5-pro in the tokens utility files.
- Enhanced model matching functionality to include gpt-5-pro variations.
* refactor: optimize model pricing and validation logic
- Added new model pricing entries for llama2, llama3, and qwen variants in tx.js.
- Updated tokenValues to include additional models and their pricing structures.
- Implemented validation tests in tx.spec.js to ensure all models resolve correctly to pricing.
- Refactored getValueKey function to improve model matching and resolution efficiency.
- Removed outdated model entries from tokens.ts to streamline pricing management.
* fix: add missing pricing
* chore: update model pricing for qwen and gemma variants
* chore: update model pricing and add validation for context windows
- Removed outdated model entries from tx.js and updated tokenValues with new models.
- Added a test in tx.spec.js to ensure all models with pricing have corresponding context windows defined in tokens.ts.
- Introduced 'command-text' model pricing in tokens.ts to maintain consistency across model definitions.
* chore: update model names and pricing for AI21 and Amazon models
- Refactored model names in tx.js for AI21 and Amazon models to remove versioning and improve consistency.
- Updated pricing values in tokens.ts to reflect the new model names.
- Added comprehensive tests in tx.spec.js to validate pricing for both short and full model names across AI21 and Amazon models.
* feat: add pricing and validation for Claude Haiku 4.5 model
* chore: increase default max context tokens to 18000 for agents
* feat: add Qwen3 model pricing and validation tests
* chore: reorganize and update Qwen model pricing in tx.js and tokens.ts
---------
Co-authored-by: khfung <68192841+khfung@users.noreply.github.com>
* fix: update @librechat/agents to v2.4.83 to handle reasoning edge case encountered with GLM models
* feat: GLM Context Window & Pricing Support
* feat: Add support for glm4 model in token values and tests
* refactor: modularize openai llm config logic into new getOpenAILLMConfig function (#9412)
* ✈️ refactor: Migrate Anthropic's getLLMConfig to TypeScript (#9413)
* refactor: move tokens.js over to packages/api and update imports
* refactor: port tokens.js to typescript
* refactor: move helpers.js over to packages/api and update imports
* refactor: port helpers.js to typescript
* refactor: move anthropic/llm.js over to packages/api and update imports
* refactor: port anthropic/llm.js to typescript with supporting types in types/anthropic.ts and updated tests in llm.spec.js
* refactor: move llm.spec.js over to packages/api and update import
* refactor: port llm.spec.js over to typescript
* 📝 Add Prompt Parameter Support for Anthropic Custom Endpoints (#9414)
feat: add anthropic llm config support for openai-like (custom) endpoints
* fix: missed compiler / type issues from addition of getAnthropicLLMConfig
* refactor: update tokens.ts to export constants and functions, enhance type definitions, and adjust default values
* WIP: first pass, decouple `llmConfig` from `configOptions`
* chore: update import path for OpenAI configuration from 'llm' to 'config'
* refactor: enhance type definitions for ThinkingConfig and update modelOptions in AnthropicConfigOptions
* refactor: cleanup type, introduce openai transform from alt provider
* chore: integrate removeNullishValues in Google llmConfig and update OpenAI exports
* chore: bump version of @librechat/api to 1.3.5 in package.json and package-lock.json
* refactor: update customParams type in OpenAIConfigOptions to use TConfig['customParams']
* refactor: enhance transformToOpenAIConfig to include fromEndpoint and improve config extraction
* refactor: conform userId field for anthropic/openai, cleanup anthropic typing
* ci: add backward compatibility tests for getOpenAIConfig with various endpoints and configurations
* ci: replace userId with user in clientOptions for getLLMConfig
* test: add Azure OpenAI endpoint tests for various configurations in getOpenAIConfig
* refactor: defaultHeaders retrieval for prompt caching for anthropic-based custom endpoint (litellm)
* test: add unit tests for getOpenAIConfig with various Anthropic model configurations
* test: enhance Anthropic compatibility tests with addParams and dropParams handling
* chore: update @librechat/agents dependency to version 2.4.78 in package.json and package-lock.json
* chore: update @librechat/agents dependency to version 2.4.79 in package.json and package-lock.json
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* adding beta header context-1m-2025-08-07 to claude sonnet 4 to increase contact window to 1M tokens
* adding context-1m beta header to test cases
* ci: Update Anthropic `getLLMConfig` tests and headers for model variations
- Refactored test cases to ensure proper handling of model variations for 'claude-sonnet-4'.
- Cleaned up unused mock implementations in tests for better clarity and performance.
* refactor: regex in header retrieval for 'claude-sonnet-4' models
* refactor: default tokens for 'claude-sonnet-4' to `1,000,000`
* refactor: add token value retrieval and pattern matching to model tests
---------
Co-authored-by: Dirk Petersen <no-reply@nowhere.com>
* refactor: Update AnthropicClient to support Claude model naming changes
* Renamed `isClaude3` to `isClaudeLatest` to accommodate newer Claude models.
* Updated logic to determine if the model is part of the Claude family.
* Adjusted `useMessages` property to reflect the new model naming convention.
* Cleaned up client properties during disposal to match the updated naming.
* feat: Claude-4 Support
* feat: Add Thinking and Prompt caching support for Claude 4
* chore: Update ANTHROPIC_MODELS in .env.example for latest model versions
* feat: Add support for new OpenAI models (o4-mini, o3) and update related logic
* 🔧 fix: Rename 'resubmitFiles' to 'isResubmission' for consistency across types and hooks
* 🔧 fix: Replace hardcoded 'pending_req' with CacheKeys.PENDING_REQ for consistency in cache handling
* 🔧 fix: Update cache handling to use Time.ONE_MINUTE instead of hardcoded TTL and streamline imports
* 🔧 fix: Enhance message handling logic to correctly identify parent messages and streamline imports in useSSE
* fix: Agent Builder setting not applying in useSideNavLinks
* fix: Remove unused type imports in useSideNavLinks
* feat: gpt-4.1
* fix: Update getCacheMultiplier and getMultiplier tests to use dynamic token values
* feat: Add gpt-4.1 to the list of vision models
* chore: Bump version of librechat-data-provider to 0.7.792
* chore: remove unused redis file
* chore: bump keyv dependencies, and update related imports
* refactor: Implement IoRedis client for rate limiting across middleware, as node-redis via keyv not compatible
* fix: Set max listeners to expected amount
* WIP: memory improvements
* refactor: Simplify getAbortData assignment in createAbortController
* refactor: Update getAbortData to use WeakRef for content management
* WIP: memory improvements in agent chat requests
* refactor: Enhance memory management with finalization registry and cleanup functions
* refactor: Simplify domainParser calls by removing unnecessary request parameter
* refactor: Update parameter types for action tools and agent loading functions to use minimal configs
* refactor: Simplify domainParser tests by removing unnecessary request parameter
* refactor: Simplify domainParser call by removing unnecessary request parameter
* refactor: Enhance client disposal by nullifying additional properties to improve memory management
* refactor: Improve title generation by adding abort controller and timeout handling, consolidate request cleanup
* refactor: Update checkIdleConnections to skip current user when checking for idle connections if passed
* refactor: Update createMCPTool to derive userId from config and handle abort signals
* refactor: Introduce createTokenCounter function and update tokenCounter usage; enhance disposeClient to reset Graph values
* refactor: Update getMCPManager to accept userId parameter for improved idle connection handling
* refactor: Extract logToolError function for improved error handling in AgentClient
* refactor: Update disposeClient to clear handlerRegistry and graphRunnable references in client.run
* refactor: Extract createHandleNewToken function to streamline token handling in initializeClient
* chore: bump @librechat/agents
* refactor: Improve timeout handling in addTitle function for better error management
* refactor: Introduce createFetch instead of using class method
* refactor: Enhance client disposal and request data handling in AskController and EditController
* refactor: Update import statements for AnthropicClient and OpenAIClient to use specific paths
* refactor: Use WeakRef for response handling in SplitStreamHandler to prevent memory leaks
* refactor: Simplify client disposal and rename getReqData to processReqData in AskController and EditController
* refactor: Improve logging structure and parameter handling in OpenAIClient
* refactor: Remove unused GraphEvents and improve stream event handling in AnthropicClient and OpenAIClient
* refactor: Simplify client initialization in AskController and EditController
* refactor: Remove unused mock functions and implement in-memory store for KeyvMongo
* chore: Update dependencies in package-lock.json to latest versions
* refactor: Await token usage recording in OpenAIClient to ensure proper async handling
* refactor: Remove handleAbort route from multiple endpoints and enhance client disposal logic
* refactor: Enhance abort controller logic by managing abortKey more effectively
* refactor: Add newConversation handling in useEventHandlers for improved conversation management
* fix: dropparams
* refactor: Use optional chaining for safer access to request properties in BaseClient
* refactor: Move client disposal and request data processing logic to cleanup module for better organization
* refactor: Remove aborted request check from addTitle function for cleaner logic
* feat: Add Grok 3 model pricing and update tests for new models
* chore: Remove trace warnings and inspect flags from backend start script used for debugging
* refactor: Replace user identifier handling with userId for consistency across controllers, use UserId in clientRegistry
* refactor: Enhance client disposal logic to prevent memory leaks by clearing additional references
* chore: Update @librechat/agents to version 2.4.14 in package.json and package-lock.json
* wip: first pass, dropdown for selecting sequential agents
* refactor: Improve agent selection logic and enhance performance in SequentialAgents component
* wip: seq. agents working ideas
* wip: sequential agents style change
* refactor: move agent form options/submission outside of AgentConfig
* refactor: prevent repeating code
* refactor: simplify current agent display in SequentialAgents component
* feat: persist form value handling in AgentSelect component for agent_ids
* feat: first pass, sequential agnets agent update
* feat: enhance message display with agent updates and empty text handling
* chore: update Icon component to use EModelEndpoint for agent endpoints
* feat: update content type checks in BaseClient to use constants for better readability
* feat: adjust max context tokens calculation to use 90% of the model's max tokens
* feat: first pass, agent run message pruning
* chore: increase max listeners for abort controller to prevent memory leaks
* feat: enhance runAgent function to include current index count map for improved token tracking
* chore: update @librechat/agents dependency to version 2.2.5
* feat: update icons and style of SequentialAgents component for improved UI consistency
* feat: add AdvancedButton and AdvancedPanel components for enhanced agent settings navigation, update styling for agent form
* chore: adjust minimum height of AdvancedPanel component for better layout consistency
* chore: update @librechat/agents dependency to version 2.2.6
* feat: enhance message formatting by incorporating tool set into agent message processing, in order to allow better mix/matching of agents (as tool calls for tools not found in set will be stringified)
* refactor: reorder components in AgentConfig for improved readability and maintainability
* refactor: enhance layout of AgentUpdate component for improved visual structure
* feat: add DeepSeek provider to Bedrock settings and schemas
* feat: enhance link styling in mobile.css for better visibility and accessibility
* fix: update banner model import in update banner script; export Banner model
* refactor: `duplicateAgentHandler` to include tool_resources only for OCR context files
* feat: add 'qwen-vl' to visionModels for enhanced model support
* fix: change image format from JPEG to PNG in DALLE3 response
* feat: reorganize Advanced components and add localizations
* refactor: simplify JSX structure in AgentChain component to defer container styling to parent
* feat: add FormInput component for reusable input handling
* feat: make agent recursion limit configurable from builder
* feat: add support for agent capabilities chain in AdvancedPanel and update data-provider version
* feat: add maxRecursionLimit configuration for agents and update related documentation
* fix: update CONFIG_VERSION to 1.2.3 in data provider configuration
* feat: replace recursion limit input with MaxAgentSteps component and enhance input handling
* feat: enhance AgentChain component with hover card for additional information and update related labels
* fix: pass request and response objects to `createActionTool` when using assistant actions to prevent auth error
* feat: update AgentChain component layout to include agent count display
* feat: increase default max listeners and implement capability check function for agent chain
* fix: update link styles in mobile.css for better visibility in dark mode
* chore: temp. remove agents package while bumping shared packages
* chore: update @langchain/google-genai package to version 0.1.11
* chore: update @langchain/google-vertexai package to version 0.2.2
* chore: add @librechat/agents package at version 2.2.8
* feat: add deepseek.r1 model with token rate and context values for bedrock
* 🔧 refactor: Update settings to use 'as const' for improved type safety and make gpt-4o-mini default model (cheapest)
* 📖 docs: Update README to reflect support for GPT-4.5 in image analysis feature
* 🔧 refactor: Update model handling to use default settings and improve encoding logic
* 🔧 refactor: Enhance model version extraction logic for improved compatibility with future GPT and omni models
* feat: GPT-4.5 tx/token update, vision support
* fix: $ref resolution logic in OpenAPI handling
* feat: add new 'anthropic-beta' header for Claude 3.7 to include token-efficient tools; ref: https://docs.anthropic.com/en/docs/build-with-claude/tool-use/token-efficient-tool-use
* fix: missing console color methods for admin scripts
* feat: Anthropic Claude 3.7 Sonnet Support
* feat: update eventsource to version 3.0.2 and upgrade @modelcontextprotocol/sdk to 1.4.1
* fix: update DynamicInput to handle number type and improve initial value logic
* feat: first pass Anthropic Reasoning (Claude 3.7)
* feat: implement streaming support in AnthropicClient with reasoning UI handling
* feat: add missing xAI (grok) models
* 🤖 refactor: streamline model selection logic for title model in GoogleClient
* refactor: add options for empty object schemas in convertJsonSchemaToZod
* refactor: add utility function to check for empty object schemas in convertJsonSchemaToZod
* fix: Google MCP Tool errors, and remove Object Unescaping as Google fixed this
* fix: google safetySettings
* feat: add safety settings exclusion via GOOGLE_EXCLUDE_SAFETY_SETTINGS environment variable
* fix: rename environment variable for console JSON string length
* fix: disable portal for dropdown in ExportModal component
* fix: screenshot functionality to use image placeholder for remote images
* feat: add visionMode property to BaseClient and initialize in GoogleClient to fix resendFiles issue
* fix: enhance formatMessages to include image URLs in message content for Vertex AI
* fix: safety settings for titleChatCompletion
* fix: remove deprecated model assignment in GoogleClient and streamline title model retrieval
* fix: remove unused image preloading logic in ScreenshotContext
* chore: update default google models to latest models shared by vertex ai and gen ai
* refactor: enhance Google error messaging
* fix: update token values and model limits for Gemini models
* ci: fix model matching
* chore: bump version of librechat-data-provider to 0.7.699
* fix: google-thinking model safety settings fix
* chore: update pricing/context for deepseek models
* ci: update Deepseek model token limits to use dynamic mapping
* feat: Add BedrockIcon component to SVG library
* feat: EModelEndpoint.bedrock
* feat: first pass, bedrock chat. note: AgentClient is returning `agents` as conversation.endpoint
* fix: declare endpoint in initialization step
* chore: Update @librechat/agents dependency to version 1.4.5
* feat: backend content aggregation for agents/bedrock
* feat: abort agent requests
* feat: AWS Bedrock icons
* WIP: agent provider schema parsing
* chore: Update EditIcon props type
* refactor(useGenerationsByLatest): make agents and bedrock editable
* refactor: non-assistant message content, parts
* fix: Bedrock response `sender`
* fix: use endpointOption.model_parameters not endpointOption.modelOptions
* fix: types for step handler
* refactor: Update Agents.ToolCallDelta type
* refactor: Remove unnecessary assignment of parentMessageId in AskController
* refactor: remove unnecessary assignment of parentMessageId (agent request handler)
* fix(bedrock/agents): message regeneration
* refactor: dynamic form elements using react-hook-form Controllers
* fix: agent icons/labels for messages
* fix: agent actions
* fix: use of new dynamic tags causing application crash
* refactor: dynamic settings touch-ups
* refactor: update Slider component to allow custom track class name
* refactor: update DynamicSlider component styles
* refactor: use Constants value for GLOBAL_PROJECT_NAME (enum)
* feat: agent share global methods/controllers
* fix: agents query
* fix: `getResponseModel`
* fix: share prompt a11y issue
* refactor: update SharePrompt dialog theme styles
* refactor: explicit typing for SharePrompt
* feat: add agent roles/permissions
* chore: update @librechat/agents dependency to version 1.4.7 for tool_call_ids edge case
* fix(Anthropic): messages.X.content.Y.tool_use.input: Input should be a valid dictionary
* fix: handle text parts with tool_call_ids and empty text
* fix: role initialization
* refactor: don't make instructions required
* refactor: improve typing of Text part
* fix: setShowStopButton for agents route
* chore: remove params for now
* fix: add streamBuffer and streamRate to help prevent 'Overloaded' errors from Anthropic API
* refactor: remove console.log statement in ContentRender component
* chore: typing, rename Context to Delete Button
* chore(DeleteButton): logging
* refactor(Action): make accessible
* style(Action): improve a11y again
* refactor: remove use/mention of mongoose sessions
* feat: first pass, sharing agents
* feat: visual indicator for global agent, remove author when serving to non-author
* wip: params
* chore: fix typing issues
* fix(schemas): typing
* refactor: improve accessibility of ListCard component and fix console React warning
* wip: reset templates for non-legacy new convos
* Revert "wip: params"
This reverts commit f8067e91d4.
* Revert "refactor: dynamic form elements using react-hook-form Controllers"
This reverts commit 2150c4815d.
* fix(Parameters): types and parameter effect update to only update local state to parameters
* refactor: optimize useDebouncedInput hook for better performance
* feat: first pass, anthropic bedrock params
* chore: paramEndpoints check for endpointType too
* fix: maxTokens to use coerceNumber.optional(),
* feat: extra chat model params
* chore: reduce code repetition
* refactor: improve preset title handling in SaveAsPresetDialog component
* refactor: improve preset handling in HeaderOptions component
* chore: improve typing, replace legacy dialog for SaveAsPresetDialog
* feat: save as preset from parameters panel
* fix: multi-search in select dropdown when using Option type
* refactor: update default showDefault value to false in Dynamic components
* feat: Bedrock presets settings
* chore: config, fix agents schema, update config version
* refactor: update AWS region variable name in bedrock options endpoint to BEDROCK_AWS_DEFAULT_REGION
* refactor: update baseEndpointSchema in config.ts to include baseURL property
* refactor: update createRun function to include req parameter and set streamRate based on provider
* feat: availableRegions via config
* refactor: remove unused demo agent controller file
* WIP: title
* Update @librechat/agents to version 1.5.0
* chore: addTitle.js to handle empty responseText
* feat: support images and titles
* feat: context token updates
* Refactor BaseClient test to use expect.objectContaining
* refactor: add model select, remove header options params, move side panel params below prompts
* chore: update models list, catch title error
* feat: model service for bedrock models (env)
* chore: Remove verbose debug log in AgentClient class following stream
* feat(bedrock): track token spend; fix: token rates, value key mapping for AWS models
* refactor: handle streamRate in `handleLLMNewToken` callback
* chore: AWS Bedrock example config in `.env.example`
* refactor: Rename bedrockMeta to bedrockGeneral in settings.ts and use for AI21 and Amazon Bedrock providers
* refactor: Update `.env.example` with AWS Bedrock model IDs URL and additional notes
* feat: titleModel support for bedrock
* refactor: Update `.env.example` with additional notes for AWS Bedrock model IDs
