| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2026-10-21 | Add idempotency support to aichat HTTP clients | dev | -3/+20 | |
| - 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/+128 | |
| - 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. | ||||
| 2026-10-04 | Updated submodule | Leonard Kugis | -0/+0 | |
| 2026-10-03 | Implemented automatic subquery compression | Leonard Kugis | -3/+84 | |
| 2026-10-03 | Fixed subquery tool double adding | Leonard Kugis | -32/+87 | |
| 2026-10-02 | Added submodule llm-functions-docker | Leonard Kugis | -0/+3 | |
| 2026-10-02 | Merged docker files into main repo | Leonard Kugis | -173/+1076 | |
| 2026-10-01 | feat: add built-in subquery tool with hierarchical query ids | aichat-agent | -10/+560 | |
| * 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. | ||||
| 2026-02-23 | chore: update models.yaml | sigoden | -89/+326 | |
| 2026-01-29 | chore: update models.yaml | sigoden | -297/+58 | |
| 2026-01-06 | chore: update models.yaml | sigoden | -473/+114 | |
| 2025-12-01 | chore: update models.yaml | sigoden | -20/+63 | |
| 2025-11-03 | chore: update models.yaml | sigoden | -194/+143 | |
| 2025-10-10 | chore: update models.yaml | sigoden | -9/+145 | |
| 2025-09-22 | chore: update models.yaml | sigoden | -26/+54 | |
| 2025-09-08 | chore: update models.yaml | sigoden | -41/+52 | |
| 2025-08-25 | chore: update models.yaml | sigoden | -6/+19 | |
| 2025-08-18 | chore: update models.yaml | sigoden | -14/+14 | |
| 2025-08-11 | chore: update models.yaml | sigoden | -42/+186 | |
| 2025-08-08 | chore: remove redundant text check in use_embeddings method (#1378) | curricane chen | -8/+5 | |
| Co-authored-by: chenmch <chenmch@diit.cn> | ||||
| 2025-08-08 | chore: clippy with rust 1.89 (#1379) | sigoden | -6/+6 | |
| 2025-08-04 | chore: update models.yaml | sigoden | -101/+102 | |
| 2025-08-02 | feat: eliminate return requirement for -e mode option selection (#1374) | renato-umeton | -22/+57 | |
| Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: sigoden <sigoden@gmail.com> | ||||
| 2025-08-01 | feat: switch to raw stream renderer when no_color/no_highlight (#1371) | sigoden | -3/+12 | |
| 2025-08-01 | refactor: update RoleLike trait (#1370) | sigoden | -27/+20 | |
| 2025-08-01 | feat: cache session token counts to avoid typing delay (#1369) | sigoden | -1/+14 | |
| 2025-07-31 | chore: update haiku model name to match openrouter interface (#1364) | danbeibei | -1/+1 | |
| 2025-07-30 | refactor: several improvements (#1363) | sigoden | -31/+31 | |
| 2025-07-30 | feat: bedrock supports session_token (#1362) | sigoden | -0/+11 | |
| 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 | |
| 2025-07-28 | chore: update models.yaml | sigoden | -23/+84 | |
| 2025-07-21 | chore: update models.yaml | sigoden | -7/+8 | |
| 2025-07-21 | feat: vertexai supports `global` location (#1354) | Andrew Grigorev | -2/+10 | |
| 2025-07-14 | chore: update models.yaml | sigoden | -19/+45 | |
| 2025-07-12 | fix: `.copy` does not work after session compression (#1350) | sigoden | -1/+1 | |
| 2025-07-07 | chore: release v0.30.0 (#1344) | sigoden | -8/+8 | |
| 2025-07-05 | fix: `.file` external commands capture stdout/stderr (#1343) | sigoden | -8/+49 | |
| 2025-07-05 | feat: ctrl+j for newline (#1342) | sigoden | -3/+6 | |
| 2025-07-04 | feat: enhence `.regenerate` (#1340) | sigoden | -2/+9 | |
| 2025-07-03 | refactor: update deps and models.yaml (#1339) | sigoden | -28/+52 | |
| 2025-06-28 | refactor: several improvements (#1336) | sigoden | -638/+597 | |
| 2025-06-28 | feat: support autodetecting dark/light theme (#1335) | sigoden | -31/+56 | |
| 2025-06-28 | fix: change temperature/top_p reading rules (#1333) | sigoden | -10/+19 | |
| 2025-06-28 | chore: clippy (#1334) | sigoden | -46/+39 | |
| 2025-06-23 | chore: update models.yaml | sigoden | -558/+65 | |
| 2025-06-23 | feat: abandon support for lingyiwanwu client (#1327) | sigoden | -24/+1 | |
| 2025-06-23 | fix: openai api omits content field from tool_calls message (#1326) | sigoden | -4/+2 | |
| 2025-06-17 | chore: update models.yaml | sigoden | -26/+40 | |
| 2025-06-09 | chore: update models.yaml | sigoden | -53/+24 | |
