6cfa0c55d2
Removes kilo, kimi, kimi-code, copilot, windsurf, augment, trae, qwen, hermes, cline, codebuddy and pi end to end: capability descriptors, installer branches and converters (bin/install.js 14.9k -> 11.2k lines), TypeScript converters, hook surfaces and runtime homes, review lanes qwen/kimi-code, the two pi migrations, Kimi payload normalization in the hook guards, dead hostBehaviors vocabulary, launcher home probes, fixtures, runtime-specific tests and the prose that presented them as supported. Installer output for the six kept runtimes is byte-identical to before the prune. The Kimi tool-vocabulary tests in workflow-guard, read-guard and read-injection-scanner are left in place pending a decision.
7.1 KiB
How to set up cross-AI review
Goal: Configure which AI reviewers participate in plan review, run a review of a planned phase, and use the feedback to converge on a plan with no HIGH-severity concerns.
Prerequisites: The phase has been planned ({phase}-PLAN.md files exist in .planning/phases/). At least one external AI CLI is installed and authenticated.
Decide which reviewers to use
MSD Core can route review requests to any combination of: Claude (separate session), Codex CLI, CodeRabbit, OpenCode, Cursor, Antigravity CLI, Ollama, LM Studio, and llama.cpp.
That list is not fixed. Each of those is a declared reviewer lane, and a capability can ship its own — see Ship a reviewer lane in your capability. To see exactly which lanes your installation has, run msd-tools review-lane sections.
Each reviewer runs the same structured prompt against your PLAN.md files independently. Because different models have different blind spots, multi-reviewer consensus catches more issues than any single reviewer.
If you have no external CLIs installed yet, install at least one:
# Antigravity CLI (free with Google credentials)
curl -fsSL https://antigravity.google/cli/install.sh | bash
# Codex CLI
npm install -g @openai/codex
Set default reviewers (optional)
By default, /msd-review runs all detected CLIs. To pin a subset as project defaults:
/msd-config --integrations
The integrations wizard covers API keys, code-review CLI routing, and the review.default_reviewers list. Set the list to the reviewers you want as the no-flag default — for example ["codex","claude"].
Alternatively, set it directly with msd-tools:
msd config-set review.default_reviewers '["codex","claude"]'
For the full integration settings schema (API keys, model overrides per reviewer, local server host addresses), see Configuration.
If you need multiple independent reviewer voices from the same adapter, configure review.reviewer_instances and add those instance names to review.default_reviewers. Instance names run only through review.default_reviewers; they are not valid /msd-review flags. See Reviewer instances for the schema.
Run a review
Standard review (uses your configured defaults or all detected CLIs)
/msd-review --phase 3
MSD invokes each reviewer in sequence, collects structured feedback (Summary, Strengths, Concerns at HIGH/MEDIUM/LOW, Suggestions, Risk Assessment), and writes the combined output to .planning/phases/03-.../03-REVIEWS.md.
Select a single reviewer for a one-off run
/msd-review --phase 3 --agy
/msd-review --phase 3 --codex
/msd-review --phase 3 --cursor
Any explicit flag overrides both the --all default and review.default_reviewers for that run.
Run every available reviewer in parallel
/msd-review --phase 3 --all
--all always overrides config and runs the full detected set, including any configured local model servers (Ollama, LM Studio, llama.cpp).
Local model server reviewers
If you run Ollama or LM Studio locally, they are included automatically with --all when the server is reachable. You can also target them explicitly:
/msd-review --phase 3 --ollama
/msd-review --phase 3 --lm-studio
Configure the host addresses and model selection under review.* keys via /msd-config --integrations if the defaults (localhost:11434 / localhost:1234) do not apply.
Read the review output
The {padded_phase}-REVIEWS.md file contains:
- Individual reviews from each reviewer with severity-classified concerns
- A Consensus Summary section that synthesises concerns raised by two or more reviewers — start here for the highest-priority signal
- A Divergent Views section for areas where reviewers disagreed
models:andmodel_sources:frontmatter maps — the resolved model each reviewer actually ran under, and how that value was determined
Which model produced a review
Compare two reviewers' verdicts only after checking what actually produced each one — models: in the frontmatter gives the model per reviewer, and model_sources: gives the mechanism that recovered it.
If a reviewer's entry reads unknown, pin it: set review.models.<slug> for that lane (the key suffix is not always the lane's slug — Antigravity's is review.models.agy) so the next run records pinned. See Code-review CLI routing for the full key table.
Some unknown values are expected, not a bug to chase: lanes that accept no model at all (cursor, coderabbit), and any lane whose CLI didn't disclose one on this run. pinned is a certain value; banner and transcript are recovered from third-party CLI output and can degrade to unknown after an upstream release changes that output.
A models: entry like gpt-5.6-sol (reasoning=high) is not a formatting quirk: the (reasoning=<level>) suffix reflects a reasoning effort MSD itself applied to that lane, driven by your effort.* config — not the CLI's own default.
Incorporate feedback into the plan
Once you have reviewed the output, replan incorporating the feedback:
/msd-plan-phase 3 --reviews
The planner reads REVIEWS.md and adjusts the plans to address the concerns before saving.
Automate the plan–review–replan loop
For phases where you want to iterate until all HIGH-severity concerns are resolved, use the convergence loop:
/msd-plan-review-convergence 3
This runs plan-phase → review → replan → re-review up to three cycles (default). The loop exits when the HIGH-concern count reaches zero.
Convergence with a specific reviewer
/msd-plan-review-convergence 3 --codex
/msd-plan-review-convergence 3 --agy
Convergence with all reviewers and a higher cycle cap
/msd-plan-review-convergence 3 --all --max-cycles 5
Stall detection: if the HIGH-concern count is not decreasing across cycles, MSD warns you. When the cycle cap is reached with open HIGH concerns, an escalation gate asks whether to proceed or review manually.
Conditionals: which reviewers to choose
| Situation | Recommended approach |
|---|---|
| You have Antigravity already installed | --agy is always a good starting reviewer |
| You want free multi-reviewer coverage | --agy (Google credentials) + --claude |
| Your project is OpenAI-heavy | add --codex for an OpenAI-model perspective |
| You want to avoid API costs entirely | configure Ollama with a local model and use --ollama |
| You need maximum coverage before a release | /msd-plan-review-convergence N --all |
| You're iterating quickly and want fast feedback | pick one CLI: /msd-review --phase N --agy |
Related
- Verify and ship
- Ship a reviewer lane in your capability — add a reviewer MSD does not ship with, by declaring it in a capability manifest
- Configuration
- Commands
- docs index