docs(agent-team): document input propagation errors and manual re-dispatch

catalog/agent-team/README.md

@@ -104,14 +104,28 @@ Then apply the OAuth token tweak to each `.lock.yml` per [`skills/install-workfl
 1. Open an issue describing what you want built.
 2. Add the single label `agent-team`.
 3. Watch the thread. Each role posts its contribution as a comment; the implementer opens a draft PR that closes the issue when merged.
-4. Human override at any time: add `state:blocked` to halt, edit a comment to steer the next agent, or manually `gh workflow run` a specific role to retry a stuck stage. Manual dispatches must pass the required `workflow_dispatch` inputs, and the downstream workflow markdown must read them via `${{ github.event.inputs.* }}`.
+4. Human override at any time: add `state:blocked` to halt, edit a comment to steer the next agent, or manually re-dispatch a specific role. Required inputs vary by role:
+
+   ```bash
+   # Re-dispatch the planner (spec exists; planner didn't fire or needs a retry)
+   gh workflow run planner-agent.yml --field issue_number=<N> --field iteration=<N>
+
+   # Re-dispatch the implementer — omit pr_number for a new PR, include it to update an existing one
+   gh workflow run implementer-agent.yml --field issue_number=<N> --field iteration=<N>
+   gh workflow run implementer-agent.yml --field issue_number=<N> --field iteration=<N> --field pr_number=<PR>
+
+   # Re-dispatch the reviewer
+   gh workflow run reviewer-agent.yml --field pr_number=<PR> --field issue_number=<N> --field iteration=<N>
+   ```
+
+   All three agents fail loudly if required inputs are missing — they never infer values from label state or recent activity.
 5. **Retrying a blocked task**: clear `state:blocked`, then re-add `agent-team`. Spec-agent treats it as a fresh dispatch (because the state:* labels are gone and the spec markers are already satisfied — actually: to redo from scratch, also delete the prior spec comment).
 
 ## Limits and gotchas
 
 - **Concurrency**: each workflow uses `concurrency: group: agent-team-issue-${issue_number}` so only one role runs at a time per issue.
 - **Max iterations**: default 3 (reviewer kickback → implementer). The counter lives on the `iteration` input passed through the dispatch chain, bumped exclusively by the reviewer on kickback.
-- **Input propagation**: planner / implementer / reviewer must fail loudly if required `workflow_dispatch` inputs are missing. Do not rely on label search or recent-activity inference as a fallback.
+- **Input propagation**: planner / implementer / reviewer fail loudly if required `workflow_dispatch` inputs are missing or unresolved — they never infer values from label state or recent activity. If you see `🛑 agent-team: workflow_dispatch inputs were not propagated. Re-dispatch with valid inputs.` on an issue, clear `state:blocked` and manually re-dispatch the stalled role with explicit `--field` arguments (see "Kicking off a task" step 4 above). The `pr_number` input to the implementer is optional: omit it on first dispatch (a new draft PR is created); include it on reviewer kickback so the implementer pushes updates to the existing PR branch rather than opening a new one.
 - **Non-UI only**: no screenshot capture. Reviewer validates via tests/CI status + reading the diff.
 - **Cost**: a single task can easily spend 4× the tokens of a monolithic workflow. Set `timeout-minutes` conservatively and monitor the first few runs.
 - **No auto-merge**: the reviewer approves but never merges. Humans merge.