5 Commits

Author SHA1 Message Date
centdix
cdcc56461b feat: add black-box ai eval benchmarks (#8618) 2026-04-13 14:05:46 +02:00
centdix
e0d35ade72 chore: fix Claude action + add skills for codex + update autonomous mode docs (#8489)
* chore: fix Claude action overlap with /ai-fast

* chore: add Codex skills under .agents

* chore: remove user_invocable from Codex skills

* docs: require draft PR creation in autonomous mode
2026-03-24 09:23:06 +00:00
hugocasa
96229575e6 chore: dev tooling — wm-ts-nav navigator, format hooks, review skill (#8337)
* chore: remove wm-cursor, add local-review skill, update PR skill for EE

- Remove the unused wm-cursor script and all references to it in
  README_WORKMUX_DEV.md and worktree-common.sh
- Add /local-review skill for code review (bugs + CLAUDE.md compliance)
- Add EE companion PR workflow to the /pr skill

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* chore: add wm-ts-nav tree-sitter navigator and fix format hooks

- Add wm-ts-nav: standalone tree-sitter code navigator with SQLite index
  for fast symbol search, definition lookup, and file outlines across
  Rust, TypeScript, and Svelte files (~12ms warm, ~1s cold for 482 files)
- Fix format hooks: surface errors instead of swallowing with 2>/dev/null,
  use direct prettier path with svelte plugin, add success feedback
- Add wm-ts-nav commands to settings allow list
- Document wm-ts-nav usage in CLAUDE.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(wm-ts-nav): add refs command and --parent filter

- refs: find usages of a symbol in code, skipping comments and strings
  (tree-sitter AST walk, ~46ms for 482 files vs grep's 4ms but no noise)
- --parent filter on search: find all methods on a type across all files
  (e.g. search "%" --kind function --parent ServiceName)
- Update CLAUDE.md with clearer when-to-use guidance

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(wm-ts-nav): index refs in DB with import-path resolution

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(wm-ts-nav): add body, callers, callees commands and refs --file/--caller

- body: extract a symbol's source code from disk using indexed line ranges
- callers: cross-file call graph via SQL join of refs + symbols tables
- callees: list all identifiers referenced within a symbol's body
- refs --file: scope results to files matching a substring
- refs --caller: annotate each ref with the containing function name

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(wm-ts-nav): add auto-rebuilding wrapper script

The `wm-ts-nav/nav` wrapper checks if source files are newer than the
binary and rebuilds automatically. Invoked via `sh wm-ts-nav/nav` to
avoid needing executable permissions after clone.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: tighten CLAUDE.md nav section for actionable guidance

Remove redundant question→command mapping, latency numbers, and
excessive examples. Lead with "prefer wm-ts-nav over Read to save
context window" and keep only the patterns that change behavior.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* chore: revert backend/Cargo.lock to main

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* chore: promote wm-ts-nav in workflow, copy binary to worktrees

- CLAUDE.md: integrate wm-ts-nav into Workflow step 1 and Core
  Principles so agents use outline/body before full file reads
- workmux: copy built binary via files.copy
- worktree-common.sh: copy binary in wm_copy_dependencies for webmux

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(wm-ts-nav): fix double indexing, add TSX grammar, remove needless clone

- Reuse index stats from the pre-query update instead of indexing twice
  on the Index command
- Add Lang::Tsx variant so .tsx/.jsx files use LANGUAGE_TSX instead of
  LANGUAGE_TYPESCRIPT (Svelte stays on TS since script blocks are pure TS)
- Remove source.clone() for non-Svelte files — move directly instead

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(wm-ts-nav): fix svelte line numbers, add class methods, innermost caller

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-13 12:07:49 +00:00
centdix
b121f4388b docs: move autonomous-mode reference to system prompt (#8173)
* docs: move autonomous-mode reference from CLAUDE.md to system prompt

Remove the autonomous-mode.md bullet from CLAUDE.md and instead reference
it via the workmux system prompt, matching the workmux-web pattern. Also
remove the duplicated "Dev Environment (tmux)" section from
autonomous-mode.md since that info is already in the system prompt.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: add autonomous-mode.md reference to wmdev sandbox system prompt

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 10:43:19 +00:00
centdix
ff180de4de refactor: slim down claude instructions for lean context and fast iteration (#8136)
* refactor: slim down claude instructions for lean context and fast iteration

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: add private and license feature flags to enterprise validation docs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add /refine skill for end-of-session doc evolution

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: remove architecture.md overview doc per research findings

General codebase overviews distract agents and trigger unnecessary
exploration. Keep only operational docs (validation, enterprise).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add autonomous mode doc for bypass permission workflows

Covers: plan-first requirement, tmux pane usage for checking
backend/frontend logs, manual testing via Playwright MCP,
Playwright gotchas, and end-of-task summary expectations.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add mermaid, playwright, and asciinema tools to autonomous mode doc

Claude should use mmdc for diagrams during planning, playwright CLI for
screenshots of frontend changes, and asciinema for terminal recordings
of CLI changes. All attached to the PR.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: use pastebin for screenshot/recording uploads

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: address PR review findings

- Remove stale docs/architecture.md reference from /refine skill
- Fix script name: ./update-sqlx -> ./update_sqlx.sh
- Remove .claude/settings.local.json mention from enterprise doc

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 07:00:19 +00:00