| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| fix(coding-agent): stop anchoring auto-continue prompt on stale 'Next Steps'
The autoContinue post-compaction prompt echoed the summary's '## Next
Steps' heading, but that section is generated only from the compacted
tail; the kept ~20k recent tokens are not fed to the summarizer. When
the user pivoted within the kept window, 'Continue if you have next
steps.' anchored the model on the now-outdated plan instead of the
latest intent.
Move the prompt to prompts/system/auto-continue.md (per AGENTS.md
no-inline-prompts rule) and rewrite it to direct the model to re-read
the kept recent messages and follow the user's most recent request,
explicitly allowing it to stop when nothing remains.
Fixes #840
| 1 个月前 |
| feat(coding-agent): added per-turn AUTO_THINKING in coding-agent session
- Added AUTO_THINKING as a configured thinking level in settings, schema, SDK, and session plumbing.
- Implemented per-turn auto reasoning classification with online/local prompts, effort clamping, and skip guards.
- Updated model selectors, ACP options, footer/status UI, and events to render auto and auto->resolved states.
- Added AUTO_THINKING parse/clamp tests and fixed local-module cycle and hashline preview regressions.
| 1 天前 |
| feat(coding-agent): added per-turn AUTO_THINKING in coding-agent session
- Added AUTO_THINKING as a configured thinking level in settings, schema, SDK, and session plumbing.
- Implemented per-turn auto reasoning classification with online/local prompts, effort clamping, and skip guards.
- Updated model selectors, ACP options, footer/status UI, and events to render auto and auto->resolved states.
- Added AUTO_THINKING parse/clamp tests and fixed local-module cycle and hashline preview regressions.
| 1 天前 |
| feat(tools): added GitHub Actions workflow renderer and enhanced gh-* tool outputs
- Added gh-renderer.ts module with GitHub Actions workflow visualization for terminal output.
- Enhanced gh_pr_view tool to fetch and display inline review comments alongside pull request reviews.
- Improved gh_run_watch tool output with structured job state tracking and failed log formatting.
- Fixed gh_run_watch to resolve explicit branch watches against GitHub API branch head instead of local HEAD.
- Fixed gh_* tool outputs to spill full large results to artifacts instead of pre-truncating.
- Standardized trailing newlines across 100+ prompt template files for POSIX compliance.
| 1 个月前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| feat(coding-agent): added AgentRegistry for IRC session peer lookup
- Added AgentRegistry singleton with session registration/unregistration and IRC routing metadata for peer lookups.
- Added IRC messaging prompts and tooling with irc.enabled setting, list/send tool paths, and peer roster rendering.
- Changed /btw to session-side runEphemeralTurn, added background IRC exchange flushing, and fixed empty-input checks.
- Added unit tests for IRC tool and BtwController ephemeral behavior, including disabled, busy, not-found, and abort cases.
| 1 个月前 |
| feat(coding-agent): added tiny local model support for memory extraction and consolidation
- Added a new providers.memoryModel setting with tiny memory model options and ONLINE_MEMORY_MODEL_KEY default in settings.
- Updated Mnemosyne provider resolution so a configured local tiny model overrode remote completion and used new memory extraction and consolidation prompts.
- Expanded the tiny-model CLI registry to download and report all local tiny models (title plus memory) through a unified list.
| 2 天前 |
| feat(coding-agent): added tiny local model support for memory extraction and consolidation
- Added a new providers.memoryModel setting with tiny memory model options and ONLINE_MEMORY_MODEL_KEY default in settings.
- Updated Mnemosyne provider resolution so a configured local tiny model overrode remote completion and used new memory extraction and consolidation prompts.
- Expanded the tiny-model CLI registry to download and report all local tiny models (title plus memory) through a unified list.
| 2 天前 |
| feat(coding-agent/modes): added rule amendment flow before saving generated TTSR rules
- Added an amend option to the save selector that prompts for feedback and returns amend, rejected, or aborted outcomes.
- When the user chooses amend, the controller regenerated the candidate using prior rule content plus feedback before attempting to save.
- Updated prompt text and interaction tests to pass amendment context into candidate generation and validate the new save/amend flow.
| 1 天前 |
| feat(coding-agent): removed recipe tool and all runner implementations
- Deleted RecipeTool, runner logic, and all task runner backends (just, make, cargo, pkg, task).
- Removed recipe from BUILTIN_TOOLS, auto-injection in createTools, and HTML export renderer.
- Deleted recipe tool prompt template and runner module exports.
| 1 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| docs(coding-agent/prompts): added rule against re-auditing edits and routine diff checks
- Added a system prompt instruction to never re-audit applied edits.
- Added guidance to avoid routine git status and git diff checks, with exceptions for explicit requests and selective repo operations.
| 1 天前 |
| feat: added tiny-title generation core with worker flow and model specs
- Added providers.tinyModel with an online default and UI schema metadata; documented tiny-title updates in changelogs.
- Added tiny-title system prompt and title-text helpers to truncate input, wrap <user-message>, and normalize output.
- Added tiny-title model registry, local model specs, key validation, and cache-path helper.
- Added tiny-title transport/client/worker flow with spawn fallback, queued requests, ping checks, and graceful close.
- Updated generateSessionTitle to route by tiny-title model and race local generation against delayed online fallback.
| 2 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| feat(coding-agent): added ultrathink keyword detection and prompt notice injection
- Added a new ultrathink mode module with standalone, case-insensitive detection, rainbow editor highlighting, and a hidden notice payload.
- Updated CustomEditor and the shared TUI Editor to support optional zero-width text decoration and apply the ultrathink styling during input rendering.
- Extended AgentSession prompt handling to append the hidden ultrathink notice after user turns in both streaming and non-streaming message flows, excluding synthetic messages.
| 3 天前 |
| Revert "wip: gentle"
This reverts commit 99bae2ce6cfd1b72b8a76347a13f6a7dc7718d89.
| 5 天前 |
| feat(coding-agent): added turn-budget parsing, multipliers and hard caps
- Added +Nk/+Nm turn-budget parsing with whitespace-boundary matching, multipliers, and hard ! indicator.
- Added per-turn budget lifecycle plus APIs (getTurnBudget, recordEvalSubagentUsage) and hard-cap checks in eval runs.
- Added hard budget observability in eval preludes and docs by exposing budget.hard and documenting ceiling modes.
- Fixed streaming preview stutter with max-row tracking and padding, with tests for preview height and budget parsing.
| 1 天前 |