| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2026-10-21 | Add idempotency support to aichat HTTP clients | dev | -0/+11 | |
| - 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/+110 | |
| - 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. | ||||
| 2025-03-26 | refactor: replace `lazy_static` with `std::sync::LazyLock` (#1246) | mtul0729 | -7/+12 | |
| 2025-03-11 | feat: `--code` (tty) strips `<think>` tag (#1227) | sigoden | -1/+1 | |
| 2025-02-17 | refactor: several improvements (#1180) | sigoden | -2/+2 | |
| 2025-02-14 | refactor: several improvements (#1177) | sigoden | -1/+1 | |
| 2025-02-13 | feat: add model field `patch` (#1169) | sigoden | -3/+9 | |
| 2025-02-10 | refactor: several improvements (#1166) | sigoden | -2/+2 | |
| 2025-02-10 | feat: drop predefined models for ollama (#1165) | sigoden | -12/+17 | |
| 2025-02-10 | feat: supports fetching models during configuration initialization (#1161) | sigoden | -31/+92 | |
| 2025-02-08 | feat: supports selecting LLM during configuration initialization (#1158) | sigoden | -13/+48 | |
| 2025-02-03 | refactor: improve call_chat_completions function (#1143) | sigoden | -21/+7 | |
| 2025-02-02 | refactor: several improvements (#1138) | mtul0729 | -2/+3 | |
| 2025-01-27 | feat: ernie migrates to v2 api (#1130) | sigoden | -13/+0 | |
| 2025-01-22 | feat: add `--sync-models` cli option (#1114) | sigoden | -5/+8 | |
| 2025-01-21 | refactor: optimize configuration initialization (#1110) | sigoden | -96/+73 | |
| 2025-01-17 | refactor: send all text instead of word-by-word in dry_run mode (#1088) | sigoden | -14/+1 | |
| 2024-12-04 | refactor: improve retrieve model (#1036) | sigoden | -31/+7 | |
| - check the model type while retrieve model - select chat/reranker model even if it is missed in client models - find predefined-models for openai-compatible client with startsWith - remove client::ApiType | ||||
| 2024-11-06 | feat: add config `user_agent` (#971) | sigoden | -0/+3 | |
| 2024-10-29 | fix: unexpected Ctrl-C/Ctrl-D handling in non-stream REPL Chat (#957) | sigoden | -2/+12 | |
| 2024-10-29 | refactor: improve code quality (#956) | sigoden | -10/+14 | |
| 2024-10-19 | refactor: improve handling of no_stream/no_system_message (#936) | sigoden | -1/+1 | |
| 2024-09-24 | refactor: embeddings/rerank fn accept ref data (#878) | sigoden | -6/+6 | |
| 2024-09-13 | refactor: catch api error (#861) | sigoden | -0/+5 | |
| 2024-09-06 | fix: render stream failed due to read cursor position timeout (#835) | sigoden | -7/+7 | |
| 2024-09-02 | feat: migrate `cloudflare` client to `openai-compatible` (#821) | sigoden | -7/+10 | |
| 2024-07-30 | refactor: several improvements (#765) | sigoden | -2/+1 | |
| 2024-07-28 | feat: add `config.stream` and `.set stream` repl command (#759) | sigoden | -7/+28 | |
| 2024-07-28 | feat: abandon rag_dedicated client and improve (#757) | sigoden | -31/+46 | |
| 2024-07-27 | feat: support patching request url, headers and body (#756) | sigoden | -35/+129 | |
| 2024-07-27 | feat: change model patch structure (#754) | sigoden | -16/+23 | |
| 2024-07-27 | feat: set model patches with `AICHAT_{client}_PATCHES` (#753) | sigoden | -10/+10 | |
| 2024-07-27 | refactor: split clients/macros.rs from clients/common.rs (#750) | sigoden | -293/+0 | |
| 2024-07-26 | refactor: several optimizations (#749) | sigoden | -1/+0 | |
| 2024-07-22 | refactor: invalid model error message (#735) | sigoden | -1/+1 | |
| 2024-07-17 | refactor: config creation prompt aware of env var (#722) | sigoden | -5/+13 | |
| 2024-07-11 | refactor: improve estimate_token_length (#703) | sigoden | -15/+17 | |
| 2024-06-27 | feat: implement native rag url loader (#660) | sigoden | -26/+4 | |
| 2024-06-25 | refactor: rename model type `rerank` to `reranker` (#646) | sigoden | -2/+2 | |
| 2024-06-25 | feat: support rag-dedicated clients (jina and voyageai) (#645) | sigoden | -4/+6 | |
| 2024-06-22 | refactor: improve clients (#632) | sigoden | -2/+2 | |
| 2024-06-22 | feat: ernie support embeddings and rereank (#630) | sigoden | -3/+3 | |
| 2024-06-22 | refactor: some error messages (#627) | sigoden | -4/+4 | |
| 2024-06-21 | refactor: rename model.max_concurrent_chunks to model.max_batch_size (#626) | sigoden | -1/+1 | |
| 2024-06-21 | refactor: rename model.mode to model.type (#625) | sigoden | -3/+3 | |
| 2024-06-21 | feat: support rerank (#620) | sigoden | -7/+94 | |
| 2024-06-17 | refactor: improve code quatity (#604) | sigoden | -3/+3 | |
| 2024-06-14 | chore: clippy and format (#600) | sigoden | -12/+0 | |
