fix(conductor): self-heal missing harness config via lh init --yes

conductor previously jumped straight to lh host, which succeeds even
without .agents/harness.config.json, then silently hit a hard failure
later reading .agents/memory/INDEX.md (lh doctor confirms: config not
initialised). New projects had no automatic recovery path — lh init
was documented as a manual step users had to remember.

- conductor now runs lh doctor first; if config is missing it runs
  lh init --yes (non-interactive defaults) and re-checks, before lh host
- still stops and reports the exact failing check if lh doctor finds
  something it can't self-heal (e.g. no verify commands configured)
- README/QUICKSTART updated: lh init/lh doctor documented as optional
  manual pre-flight, not a required step, since conductor self-heals

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

.github/agents/conductor.agent.md

@@ -13,43 +13,46 @@ Run the full lean harness pipeline. Edit no product files.
 
 ## PROCEDURE
 
-1. Run `lh host` first.
+1. Run `lh doctor`.
-2. Read the printed host strategy before any other action.
+2. If it reports `config not initialised`, run `lh init --yes` (non-interactive defaults), then run `lh doctor` again.
-3. If the strategy permits parallel lanes, use host fan-out.
+3. Do not proceed past a `lh doctor` failure you cannot self-heal (for example missing `verify.commands`); report the exact failing check and stop.
-4. If the strategy says sequential, run every lane one at a time.
+4. Run `lh host`.
-5. Run `lh run start` and capture the run id.
+5. Read the printed host strategy before any other action.
-6. Emit `lh run event` for every phase transition.
+6. If the strategy permits parallel lanes, use host fan-out.
-7. Load only `.agents/memory/INDEX.md` by default.
+7. If the strategy says sequential, run every lane one at a time.
-8. Pull memory shards only when the current phase needs them.
+8. Run `lh run start` and capture the run id.
-9. Start `scribe` after run start.
+9. Emit `lh run event` for every phase transition.
-10. Keep `scribe` non-blocking.
+10. Load only `.agents/memory/INDEX.md` by default.
-11. For design, invoke `interrogator`.
+11. Pull memory shards only when the current phase needs them.
-12. Require `.agents/specs/<slug>/decisions.md` before planning.
+12. Start `scribe` after run start.
-13. Enforce the user gate after design.
+13. Keep `scribe` non-blocking.
-14. Do not infer unanswered decisions.
+14. For design, invoke `interrogator`.
-15. For plan, invoke `architect`.
+15. Require `.agents/specs/<slug>/decisions.md` before planning.
-16. Require `.agents/specs/<slug>/spec.md`.
+16. Enforce the user gate after design.
-17. Invoke `splitter` to write `.agents/specs/<slug>/plan.dag.json`.
+17. Do not infer unanswered decisions.
-18. Validate the DAG with `lh graph`.
+18. For plan, invoke `architect`.
-19. Own the dynamic DAG after splitter returns.
+19. Require `.agents/specs/<slug>/spec.md`.
-20. For every checkpoint, read lane status and verifier output.
+20. Invoke `splitter` to write `.agents/specs/<slug>/plan.dag.json`.
-21. Re-plan at every checkpoint.
+21. Validate the DAG with `lh graph`.
-22. Spawn, kill, merge, or re-scope lanes only through updated `plan.dag.json` and `lh lane` commands.
+22. Own the dynamic DAG after splitter returns.
-23. For read lanes, run `scout` on the shared checkout.
+23. For every checkpoint, read lane status and verifier output.
-24. For write lanes, run `lh lane create` before any builder starts.
+24. Re-plan at every checkpoint.
-25. Assign each builder exactly one lane and one worktree.
+25. Spawn, kill, merge, or re-scope lanes only through updated `plan.dag.json` and `lh lane` commands.
-26. Give each builder its declared scope globs and acceptance ids.
+26. For read lanes, run `scout` on the shared checkout.
-27. Run builder and verifier in the Ralph loop.
+27. For write lanes, run `lh lane create` before any builder starts.
-28. Stop a lane only when all Ralph exit criteria hold.
+28. Assign each builder exactly one lane and one worktree.
-29. On failure, isolate cause, retry within bound, then re-plan around it.
+29. Give each builder its declared scope globs and acceptance ids.
-30. Escalate to the user on max Ralph iterations.
+30. Run builder and verifier in the Ralph loop.
-31. When build lanes pass, invoke `integrator`.
+31. Stop a lane only when all Ralph exit criteria hold.
-32. Require sequential integration even on parallel-capable hosts.
+32. On failure, isolate cause, retry within bound, then re-plan around it.
-33. Require one final full verify after all lane merges.
+33. Escalate to the user on max Ralph iterations.
-34. Invoke `reviewer` for final approval if not already done by integrator.
+34. When build lanes pass, invoke `integrator`.
-35. Run `scribe` for final journal and deltas.
+35. Require sequential integration even on parallel-capable hosts.
-36. Run `lh run end` with success or failure.
+36. Require one final full verify after all lane merges.
-37. Return only run id, changed lanes, verify status, and blockers.
+37. Invoke `reviewer` for final approval if not already done by integrator.
+38. Run `scribe` for final journal and deltas.
+39. Run `lh run end` with success or failure.
+40. Return only run id, changed lanes, verify status, and blockers.
 
 ## INPUTS
 
@@ -75,10 +78,14 @@ Run the full lean harness pipeline. Edit no product files.
 - Stop when max Ralph iterations are reached.
 - Stop when `lh graph` keeps failing after re-plan.
 - Stop when host strategy forbids required action.
+- Stop when `lh doctor` fails on a check `lh init --yes` cannot fix (for example missing `verify.commands`); report it, don't guess a fix.
 
 ## NEVER DO THIS
 
 - Never edit source files yourself.
+- Never skip `lh doctor` at start.
+- Never run `lh init` with prompts; always `--yes` (non-interactive).
+- Never re-run `lh init` if `lh doctor` already reports `config` ok.
 - Never skip `lh host`.
 - Never skip `lh run start`.
 - Never bypass the design user gate.

README.md

@@ -140,11 +140,13 @@ export CONTEXT7_API_KEY="<your key>"   # add to ~/.bashrc or ~/.zshrc
 
 ```bash
 cd your-repo
-lh init            # first-run wizard; writes .agents/harness.config.json
+lh init            # optional: first-run wizard; writes .agents/harness.config.json
-lh doctor          # confirm everything is wired
+lh doctor          # optional: confirm everything is wired
 ```
 
-Then, in Copilot CLI or VS Code Copilot:
+`conductor` runs `lh doctor` itself and self-heals a missing config with `lh init --yes`
+before doing anything else, so the two commands above are an optional manual pre-flight, not
+a required step. Then, in Copilot CLI or VS Code Copilot:
 
 ```
 Use the conductor agent to build a rate limiter for the public API

docs/QUICKSTART.md

@@ -172,17 +172,20 @@ subcommand, who calls it, and when.
 | `lh lane create/status/merge` | `conductor`, `builder`, `integrator` | Automatically, before a write lane starts and when it merges |
 | `lh memory get/put/scan` | `interrogator`, `architect`, `builder`, `scribe` | Automatically, to pull relevant shards before work and record facts/failures after |
 | `lh graph` | `verifier` (always), plus `architect`/`splitter`/`conductor`/`reviewer`/`scout`/`integrator` at their own checkpoints | Automatically — it's exit criterion #3, never skipped |
-| `lh init` | You (or `scripts/onboard.mjs` on your behalf) | Once per repo, at setup, or to repair a missing `.agents/` baseline |
+| `lh doctor` | `conductor` (first thing, before `lh host`), also you whenever you want to check the environment yourself | Automatically at the start of every pipeline run — `conductor`'s step 1 |
-| `lh doctor` | You | Whenever you want to check the environment yourself — before starting, after upgrading Node/git/the plugin, or to diagnose a stuck run. Also run once automatically right after `lh init` |
+| `lh init --yes` | `conductor`, automatically, only if `lh doctor` reports `config not initialised` | Self-heals a missing `.agents/` baseline with non-interactive defaults, then re-runs `lh doctor` |
 | `lh report <run-id>` | You | After a run, when you want a human-readable markdown summary instead of raw NDJSON. No agent generates this for you |
 
-So the only commands you are expected to type by hand in everyday use are `lh init` (setup),
+So in everyday use you don't have to type `lh init` or `lh doctor` by hand at all —
-`lh doctor` (diagnostics), and `lh report` (reading a past run's summary). Everything else —
+`conductor` runs `lh doctor` first, and if that reports the repo isn't initialised, it runs
-`lh index`, `lh host`, `lh run`, `lh lane`, `lh memory`, `lh graph` — is invoked by the agents
+`lh init --yes` for you (defaults, no prompts) and re-checks before doing anything else. It
-as a scripted, mandatory step in their own instructions. You'd only run one of those manually
+still stops and reports the exact failing check if `lh doctor` finds something it can't
-if you're debugging outside the agent flow (e.g. `lh graph` on its own to check structure
+self-heal (for example no verify commands configured yet in a brand-new, empty repo).
-before opening Copilot at all, or `lh memory get --shard failures` to read what the harness has
+`lh init`/`lh doctor` remain available for you to run by hand too — useful before starting
-learned).
+(to pre-flight a repo), after upgrading Node/git/the plugin, or to diagnose a stuck run outside
+the agent flow. The only command with no agent equivalent at all is `lh report` (reading a past
+run's summary). Everything else — `lh index`, `lh host`, `lh run`, `lh lane`, `lh memory`,
+`lh graph` — is invoked by the agents as a scripted, mandatory step in their own instructions.
 
 ## 5. Know when it's actually done