mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-07-07 06:42:30 +00:00
9f8b6d92c0
* ✨ 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. |
||
|---|---|---|
| .. | ||
| __tests__ | ||
| axios.spec.ts | ||
| axios.ts | ||
| azure.spec.ts | ||
| azure.ts | ||
| code.ts | ||
| common.spec.ts | ||
| common.ts | ||
| content.spec.ts | ||
| content.ts | ||
| email.ts | ||
| env.spec.ts | ||
| env.ts | ||
| events.ts | ||
| files.spec.ts | ||
| files.ts | ||
| generators.ts | ||
| graph.spec.ts | ||
| graph.ts | ||
| headers.spec.ts | ||
| headers.ts | ||
| http.ts | ||
| import.ts | ||
| index.ts | ||
| key.test.ts | ||
| key.ts | ||
| latex.spec.ts | ||
| latex.ts | ||
| llm.test.ts | ||
| llm.ts | ||
| math.integration.spec.ts | ||
| math.spec.ts | ||
| math.ts | ||
| memory.ts | ||
| message.spec.ts | ||
| message.ts | ||
| oidc.spec.ts | ||
| oidc.ts | ||
| openid.ts | ||
| path.spec.ts | ||
| path.ts | ||
| ports.spec.ts | ||
| ports.ts | ||
| promise.spec.ts | ||
| promise.ts | ||
| proxy.spec.ts | ||
| proxy.ts | ||
| quotes.spec.ts | ||
| quotes.ts | ||
| sanitizeTitle.spec.ts | ||
| sanitizeTitle.ts | ||
| text.spec.ts | ||
| text.ts | ||
| tokenizer.spec.ts | ||
| tokenizer.ts | ||
| tokenMap.ts | ||
| tokens.spec.ts | ||
| tokens.ts | ||
| tracing.ts | ||
| url.spec.ts | ||
| url.ts | ||
| yaml.ts | ||