agentjido / req_llm / 9d4bbbfce236ef495b9f46d9adc7acdac5394337-PR-222

Builds Branch Commit Type Ran Committer Via Coverage
9d4bbbfce236ef495b9f46d9adc7acdac5394337-PR-222 fix/capability-structure-pattern-matches Add centralized model capability helper functions - Create ReqLLM.Model with type-safe capability checks - Replace scattered get_in() calls across all providers - Fix Bedrock reasoning capability bug (checked map instead of .enabled field) - Prov... Pull #222 neilberkman github
49.06
5466cfd591f6062c3780fd1fdfbc8b629276ef61-PR-215 support-openai-tool-choice-required Allow OpenAI support for `tool_choice: required` Pull #215 bagrat github
52.71
87679f7ddf3bee2963e2045d91c857908208349c main Add OAuth2 token caching for Google Vertex AI (#174) OAuth2 token generation on every request adds 60-180ms overhead (file I/O, JWT signing, HTTP round trip). Tokens are valid for 1 hour, so this overhead is wasteful for repeated requests. Imple... push web-flow github
49.14
29628b74c06932ed0446c0df4c833c4a7564f4da-PR-174 feat/oauth2-token-cache Add OAuth2 token caching for Google Vertex AI OAuth2 token generation on every request adds 60-180ms overhead (file I/O, JWT signing, HTTP round trip). Tokens are valid for 1 hour, so this overhead is wasteful for repeated requests. Implementati... Pull #174 neilberkman github
49.14
7e8adff280d80a19edc59717c92307cf9f762260 main feat: Add Google Context Caching support for Gemini models (#193) Adds explicit context caching API for Gemini models to reduce costs by up to 90% when reusing large amounts of content. - Add ReqLLM.Providers.Google.CachedContent module for cach... push web-flow github
48.99
945b7128c4955aab6b401241ca7d785556e25a59-PR-193 feat/google-context-caching feat: Add Google Context Caching support for Gemini models Adds explicit context caching API for Gemini models to reduce costs by up to 90% when reusing large amounts of content. - Add ReqLLM.Providers.Google.CachedContent module for cache CRUD ... Pull #193 neilberkman github
48.94
68dcc54c0cb2c59d9fcd702b964062d11fbf00cf-PR-193 feat/google-context-caching feat: Add Google Context Caching support for Gemini models Adds explicit context caching API for Gemini models to reduce costs by up to 90% when reusing large amounts of content. - Add ReqLLM.Providers.Google.CachedContent module for cache CRUD ... Pull #193 neilberkman github
48.99
e86a7a74a4626952cb4e3805c9529067bceb0614 main test: Add Google Vertex Gemini test fixtures Add comprehensive test fixtures for all Vertex Gemini models: - gemini-2.0-flash: 10 fixtures (basic, streaming, tools, objects, token limits) - gemini-2.5-flash: 12 fixtures (includes reasoning/thinki... push neilberkman github
49.99
ed621d5051e7844e87f686d96002535f329b3593-PR-195 feat/vertex-gemini-support test: Add Google Vertex Gemini test fixtures Add comprehensive test fixtures for all Vertex Gemini models: - gemini-2.0-flash: 10 fixtures (basic, streaming, tools, objects, token limits) - gemini-2.5-flash: 12 fixtures (includes reasoning/thinki... Pull #195 neilberkman github
49.99
7dd6214b07262af39efd3c6d0310572da74fad06-PR-195 feat/vertex-gemini-support test: Add Google Vertex Gemini test fixtures Add comprehensive test fixtures for all Vertex Gemini models: - gemini-2.0-flash: 10 fixtures (basic, streaming, tools, objects, token limits) - gemini-2.5-flash: 12 fixtures (includes reasoning/thinki... Pull #195 neilberkman github
49.97
73ada3d1a5b6153315dc6eaa33a79956896814d5-PR-195 feat/vertex-gemini-support test: Add Google Vertex Gemini test fixtures Add comprehensive test fixtures for all Vertex Gemini models: - gemini-2.0-flash: 10 fixtures (basic, streaming, tools, objects, token limits) - gemini-2.5-flash: 12 fixtures (includes reasoning/thinki... Pull #195 neilberkman github
49.92
20e498f7947cf72d00b9b1f324db8f49b6d34a14 main Fix tool_budget_for pattern match regression from LLMDB integration (#221) The test helper tool_budget_for/1 was using an obsolete pattern match that expected {:ok, {provider, id, model}} but ReqLLM.model/1 now returns {:ok, model} after the LLMD... push web-flow github
50.18
aff7a726aa33c1bf8da2655255148c48247fdaae-PR-221 fix/tool-budget-pattern-match Fix tool_budget_for pattern match regression from LLMDB integration The test helper tool_budget_for/1 was using an obsolete pattern match that expected {:ok, {provider, id, model}} but ReqLLM.model/1 now returns {:ok, model} after the LLMDB integ... Pull #221 neilberkman github
50.14
5c69f8ddec5e58bd8cfc8adb471ea8160f78d3e8-PR-221 fix/tool-budget-pattern-match Fix tool_budget_for pattern match regression from LLMDB integration The test helper tool_budget_for/1 was using an obsolete pattern match that expected {:ok, {provider, id, model}} but ReqLLM.model/1 now returns {:ok, model} after the LLMDB integ... Pull #221 neilberkman github
50.13
367581c9c34e8aa809ece1dc571faa09110c8727 main deps(deps): bump jsv from 0.11.4 to 0.11.5 (#220) Bumps [jsv](https://github.com/lud/jsv) from 0.11.4 to 0.11.5. - [Changelog](https://github.com/lud/jsv/blob/main/CHANGELOG.md) - [Commits](https://github.com/lud/jsv/compare/v0.11.4...v0.11.5) -... push web-flow github
50.13