Address review: refresh docs + drop legacy master wording

ead8c12→main·dipree·1mo ago·5 files·+226 added/-95 removed

Self-review after merging main:

• Rewrite docs/architecture/review-command.md for the current command: entire inspect (review alias), inspectors + judge panel + chair, --list, bare-invocation selection, panel synthesis, judges/chair schema, removed review attach, and accurate ModelLister status (only claude-code advertises; codex/gemini = Default + Custom).
• Update the CLAUDE.md summary to match.
• Drop the legacy "[master]" marker in --agents and show "judges=" in the --configure catalog; update the stale runReviewListAgents comment.
• Document the chair's two passes (independent verdict + panel merge) in PanelSynthesisProvider.
• Update the affected --agents test.

Sessions

225c7b24b28bView transcript

?\List me all the potential command combinations for review.Pi·Opus 4.8·16 steps

Changes

5

• MCLAUDE.md+3/-3

• cmd/entire/cli/review

• Mcmd.go+9/-9

• Mcmd_test.go+1/-1

• Msynthesis_panel.go+4/-1

• docs/architecture

• Mreview-command.md+209/-81

495 unmodified lines

496
497
498
499
499
500
501
501
502
503
503
504
505
506

495 unmodified lines

- Test with `mise run test` - strategy tests are in `*_test.go` files
- Keep this file and `docs/architecture/sessions-and-checkpoints.md` current when changing strategy behavior (`AGENTS.md` is a symlink to this file)

### `entire review` Command
### `entire inspect` Command

`entire review` runs a set of configured review skills inside an agent session. The review session is an immutable fact attached to a checkpoint — no verdict, no status tracking, no empty commits. On the next `git commit`, the review session is condensed into the checkpoint metadata alongside normal sessions, permanently recording that the code was reviewed and which skills were run.
`entire inspect` runs a named review profile: a set of **inspector** agents run a shared task in parallel, then a panel of **judges** evaluates their reports (a **chair** merges a multi-judge panel into the final verdict). Inspector sessions are immutable facts attached to checkpoints; the final verdict is stored locally in the review manifest. On the next `git commit`, inspector sessions are condensed into the checkpoint metadata, permanently recording that the code was reviewed and which skills were run.

Configured per-agent in `.entire/settings.json` (`EntireSettings.Review`); launchable agents (claude-code, codex, gemini-cli) receive `ENTIRE_REVIEW_*` env vars that the `UserPromptSubmit` hook reads to tag the session as `Kind = "agent_review"`. Multi-agent runs use a TUI dashboard + opt-in cross-agent synthesis. Profiles live in `.entire/settings.json` under `review_profiles`; adapter-backed inspectors (claude-code, codex, gemini-cli) receive `ENTIRE_REVIEW_*` env vars that the `UserPromptSubmit` hook reads to tag the session as `Kind = "agent_review"`. Multi-agent runs use a TUI dashboard + automatic judge-panel synthesis.

See [Review Command](docs/architecture/review-command.md) for the full command surface, settings schema, env-var handshake, multi-agent UI, anti-features (do NOT recreate), and key-file map.