| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2026-10-21 | Add idempotency support to aichat HTTP clients | dev | -3/+6 | |
| - 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 | -0/+12 | |
| - 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 | Implemented automatic subquery compression | Leonard Kugis | -1/+3 | |
| 2026-10-01 | feat: add built-in subquery tool with hierarchical query ids | aichat-agent | -0/+2 | |
| * 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 | feat: bedrock supports session_token (#1362) | sigoden | -0/+1 | |
| 2025-06-23 | feat: abandon support for lingyiwanwu client (#1327) | sigoden | -6/+0 | |
| 2025-02-24 | feat: add `cmd_prelude` and remove `prelude` (#1197) | sigoden | -3/+3 | |
| 2025-02-17 | feat: remove supports for fireworks/siliconflow/together (#1181) | sigoden | -23/+6 | |
| 2025-02-14 | feat: remove supports for hyperbolic and novita (#1176) | sigoden | -12/+0 | |
| 2025-02-14 | feat: abandon model field `supports_reasoning` (revert #1145) (#1173) | sigoden | -2/+0 | |
| 2025-02-10 | feat: drop predefined models for ollama (#1165) | sigoden | -15/+11 | |
| 2025-02-04 | feat: add model field `supports_reasoning` (#1145) | sigoden | -0/+1 | |
| 2025-01-28 | feat: add novita client (#1132) | sigoden | -0/+6 | |
| 2025-01-27 | feat: ernie migrates to v2 api (#1130) | sigoden | -2/+3 | |
| 2025-01-22 | refactor: change default sync_models_url (#1116) | sigoden | -3/+3 | |
| 2025-01-22 | feat: support hyperbolic client (#1115) | sigoden | -0/+6 | |
| 2025-01-22 | feat: add `--sync-models` cli option (#1114) | sigoden | -0/+2 | |
| 2025-01-18 | feat: support minimax client (#1091) | sigoden | -0/+6 | |
| 2025-01-10 | feat: discontinue `rag_min_score_*` config items (#1081) | sigoden | -7/+5 | |
| 2024-12-14 | feat: supports override agent instructions via agent config (#1057) | sigoden | -2/+2 | |
| 2024-12-06 | refactor: change config field name (#1042) | sigoden | -1/+1 | |
| append_command_to_history_file => save_shell_history | ||||
| 2024-12-06 | feat: update cohere api to v2 (#1041) | sigoden | -1/+1 | |
| 2024-12-01 | feat: append shell execute command to history file (#1026) | sigoden | -0/+1 | |
| 2024-11-13 | feat: remove supports for huggingface (#988) | sigoden | -6/+0 | |
| 2024-11-11 | refactor: improve RAG (#982) | sigoden | -1/+1 | |
| - set max default_chuck_size to 2000 - set default rag_top_k to 4 - change reciprocal_rank_fusion weights | ||||
| 2024-11-07 | feat: add hunyuan client (#980) | sigoden | -1/+7 | |
| 2024-11-06 | chore: update config.example.yaml | sigoden | -1/+1 | |
| 2024-11-06 | feat: add config `user_agent` (#971) | sigoden | -0/+1 | |
| 2024-10-23 | refactor: update models for latest claude-3-5-sonnet (#946) | sigoden | -2/+2 | |
| 2024-10-23 | feat: support xai (grok) client (#945) | sigoden | -0/+6 | |
| 2024-10-17 | refactor: improve RAG search (#931) | sigoden | -8/+14 | |
| 2024-10-08 | feat: prelude supports <session>:<role> (#913) | sigoden | -1/+1 | |
| 2024-10-03 | feat: remove support for octoai (#901) | sigoden | -6/+0 | |
| 2024-10-03 | feat: abandon replicate client (#900) | sigoden | -4/+0 | |
| 2024-09-14 | feat: add `.save agent-config` repl command (#870) | sigoden | -7/+7 | |
| 2024-09-09 | refactor: abandon config `rag_min_score_rerank` (#852) | sigoden | -1/+3 | |
| 2024-09-08 | chore: update config.example.yaml and models.yaml | sigoden | -2/+2 | |
| 2024-09-04 | feat: add siliconflow client (#831) | sigoden | -9/+15 | |
| 2024-09-03 | feat: use dynamic batch size for embedding (#826) | sigoden | -2/+3 | |
| 2024-09-03 | chore: update config.example.com | sigoden | -1/+1 | |
| 2024-09-02 | feat: add huggingface client (#822) | sigoden | -0/+8 | |
| 2024-09-02 | chore: update config.example.yaml | sigoden | -22/+22 | |
| 2024-09-02 | feat: migrate `cloudflare` client to `openai-compatible` (#821) | sigoden | -3/+3 | |
| 2024-09-01 | refactor: openai_compatible client config (#820) | sigoden | -2/+0 | |
| 2024-09-01 | refactor: minor improvement (#818) | sigoden | -13/+0 | |
| 2024-09-01 | feat: migrate `ollama`/`qianwen` clients to `openai-compatible` (#816) | sigoden | -5/+7 | |
| 2024-08-24 | feat: support ai21 client (#800) | sigoden | -0/+6 | |
| 2024-08-23 | chore: update config.example.yaml | sigoden | -3/+15 | |
| 2024-08-22 | feat: support github client (#798) | sigoden | -0/+6 | |
| 2024-08-17 | feat: enable custom `api_base` for most clients (#793) | sigoden | -11/+19 | |
