| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2026-10-21 | Thread idempotency key through the request path | dev | -15/+37 | |
| Propagate the per-request Idempotency-Key (generated once in the retry loop) through request construction so every retry attempt reuses the same key rather than minting a new one. - Add field to ChatCompletionsData. - Generate a single key per logical request in chat_completions and chat_completions_streaming. - Thread the key through request_builder (macro-based clients), Bedrock, and VertexAI so the header is attached once and reused on retries. | ||||
| 2026-10-21 | Add idempotency support to aichat HTTP clients | dev | -0/+14 | |
| - Add boolean to client config. When enabled, a fresh (UUID) header is sent with each logical request attempt so the outer retry loop reuses the same submission instead of starting duplicate work on providers that support it (e.g. Sail Research). The key is generated once per logical request (before the retry loop) and reused across all retry attempts via the cloned ChatCompletionsData/request builders, so providers debounce duplicate generations. - Wire the header in request_builder (macro-based clients) and Bedrock's chat_completions_builder. - Document the option in config.example.yaml. | ||||
| 2026-10-21 | Add request timeout and retry support to aichat HTTP clients | dev | -7/+116 | |
| - Add timeout, retries, retry_delay_ms, and retry_max_delay_ms options to client extra config to bound long-running requests and retry failed attempts with exponential backoff. - Apply a total request timeout via reqwest .timeout(). - Implement retry with exponential backoff for non-streaming and streaming chat completions. - Disable reqwest-eventsource internal auto-reconnect so it does not loop forever; outer retry logic is now the single owner of retry behavior. - Document the new options in config.example.yaml. | ||||
| 2026-10-03 | Fixed subquery tool double adding | Leonard Kugis | -1/+2 | |
| 2026-10-01 | feat: add built-in subquery tool with hierarchical query ids | aichat-agent | -2/+28 | |
| * Add config options subquery and subquery_max_depth. * Register an internal subquery function that spawns a fresh LLM query with the current model configuration but without the full context. The model selects context numerically (message_indexes) or by text excerpt (excerpts). * Subqueries can use tools, including further nested subqueries up to subquery_max_depth. * Queries and subqueries get hierarchical ids ([0], [0/1], [0/1/2]) that prefix tool-call prints and spinner messages. | ||||
| 2025-07-30 | refactor: several improvements (#1363) | sigoden | -31/+31 | |
| 2025-07-30 | feat: bedrock supports session_token (#1362) | sigoden | -0/+10 | |
| 2025-07-29 | feat: gemini pass API key in header for security (#1360) | Aman | -4/+5 | |
| Co-authored-by: Aman Shaw <amanshaw4511@protonmail.com> Co-authored-by: aman <aman.saw@batonsystems.com> | ||||
| 2025-07-28 | feat: env vars take precedence over client config (#1361) | sigoden | -8/+6 | |
| 2025-07-21 | feat: vertexai supports `global` location (#1354) | Andrew Grigorev | -2/+10 | |
| 2025-06-28 | chore: clippy (#1334) | sigoden | -6/+5 | |
| 2025-06-23 | feat: abandon support for lingyiwanwu client (#1327) | sigoden | -2/+1 | |
| 2025-06-23 | fix: openai api omits content field from tool_calls message (#1326) | sigoden | -4/+2 | |
| 2025-04-14 | chore: clippy | sigoden | -3/+3 | |
| 2025-03-26 | refactor: replace `lazy_static` with `std::sync::LazyLock` (#1246) | mtul0729 | -11/+15 | |
| 2025-03-11 | feat: `--code` (tty) strips `<think>` tag (#1227) | sigoden | -1/+1 | |
| 2025-03-11 | fix: miss </think> tag while tool calling (#1226) | sigoden | -0/+4 | |
| 2025-03-05 | fix: openai-compatible handles empty tool call arguments (#1217) | sigoden | -0/+6 | |
| 2025-03-03 | fix: bedrock handles empty tool call arguments (#1213) | Julian Blank | -0/+6 | |
| 2025-02-27 | feat: bumping Azure OpenAI API Version to 2024-12-01-preview (#1205) | Dominique Broeglin | -1/+1 | |
| 2025-02-26 | refactor: several improvements (#1203) | sigoden | -7/+30 | |
| 2025-02-26 | feat: support claude-3-7-sonnet (#1201) | sigoden | -36/+81 | |
| 2025-02-18 | fix: better handle OpenAI-Compatible streaming responses (#1184) | wwsheng009 | -1/+2 | |
| 2025-02-17 | feat: remove supports for fireworks/siliconflow/together (#1181) | sigoden | -4/+1 | |
| 2025-02-17 | refactor: several improvements (#1180) | sigoden | -2/+2 | |
| 2025-02-14 | refactor: several improvements (#1177) | sigoden | -1/+1 | |
| 2025-02-14 | feat: remove supports for hyperbolic and novita (#1176) | sigoden | -3/+1 | |
| 2025-02-14 | feat: add patch `max_tokens: null` to openai/github o* serial models (#1174) | sigoden | -1/+5 | |
| 2025-02-14 | feat: abandon model field `supports_reasoning` (revert #1145) (#1173) | sigoden | -13/+0 | |
| 2025-02-13 | feat: abandon model field `no_temperature` (revert #1164) (#1170) | sigoden | -6/+0 | |
| 2025-02-13 | feat: add model field `patch` (#1169) | sigoden | -3/+16 | |
| 2025-02-10 | refactor: several improvements (#1166) | sigoden | -2/+2 | |
| 2025-02-10 | feat: drop predefined models for ollama (#1165) | sigoden | -14/+18 | |
| 2025-02-10 | feat: add model field `no_temperature` (#1164) | sigoden | -0/+6 | |
| 2025-02-10 | feat: new model field `system_prompt_prefix` (#1163) | sigoden | -20/+45 | |
| 2025-02-10 | feat: supports fetching models during configuration initialization (#1161) | sigoden | -34/+95 | |
| 2025-02-08 | refactor: update deps (#1159) | sigoden | -4/+4 | |
| 2025-02-08 | feat: supports selecting LLM during configuration initialization (#1158) | sigoden | -15/+50 | |
| 2025-02-06 | feat: support model alias (#1150) | sigoden | -17/+23 | |
| 2025-02-06 | refactor: several improvements (#1149) | sigoden | -1/+1 | |
| 2025-02-04 | feat: add model field `supports_reasoning` (#1145) | sigoden | -0/+13 | |
| 2025-02-03 | refactor: improve call_chat_completions function (#1143) | sigoden | -21/+7 | |
| 2025-02-03 | feat: strip reasoning contents (#1141) | sigoden | -4/+23 | |
| 2025-02-03 | feat: display reasoning tokens (#1139) | sigoden | -1/+27 | |
| 2025-02-02 | refactor: several improvements (#1138) | mtul0729 | -2/+3 | |
| 2025-01-28 | feat: add novita client (#1132) | sigoden | -1/+2 | |
| 2025-01-27 | feat: ernie migrates to v2 api (#1130) | sigoden | -346/+8 | |
| 2025-01-22 | feat: support hyperbolic client (#1115) | sigoden | -1/+2 | |
| 2025-01-22 | feat: add `--sync-models` cli option (#1114) | sigoden | -19/+29 | |
| 2025-01-21 | refactor: no gaurd vision model (#1111) | sigoden | -4/+0 | |
