# Dispatch and poll

`scripts/relay.mjs` wraps Kimi's headless prompt mode, captures its structured stream, and writes a
`result.json`. Run one command, then read one file.

## Before the first run

```bash
command -v kimi
kimi --version
kimi login
```

Install with `brew install kimi-code` on macOS/Linux or use a native installer from the
[official Kimi Code documentation](https://moonshotai.github.io/kimi-code/en/). `kimi login` uses a
device-code flow without opening the TUI; `/login` is also available inside the TUI.

## Dispatching

```bash
node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo
```

`<skill-dir>` is the installed folder containing this skill's `SKILL.md`.

| Flag | Effect |
| --- | --- |
| `--brief <file>` | Brief path. Omit it to read the brief from stdin. |
| `--cd <dir>` | Working root and child process cwd (default: current directory). |
| `--lane <name>` | Fleet lane from `delegate-setup` config. Applies that lane's dials; fails if the lane's `implementer` is not this relay. Explicit dial flags win. |
| `--model <alias>` | Kimi model alias for this run (default: Kimi's own `default_model`). |
| `--session <id>` | Resume a specific Kimi session; send only the delta brief. |
| `--resume-last` | Resume the most recent Kimi session for this cwd (`kimi --continue`); send only the delta brief. |
| `--add-dir <dir>` | Add an extra workspace directory. Repeatable. Edits there are not reported in `touchedFiles`. |
| `--timeout <dur>` | Relay watchdog (default: `30m`; h/m/s strings). Kimi has no timeout flag. |
| `--out-dir <dir>` | Artifact directory (default: a fresh directory under the system temp dir). |
| `-h`, `--help` | Print the relay's header help. |

`--session` and `--resume-last` are mutually exclusive. The child cwd pins the primary workspace;
`--add-dir` adds extra workspaces only.

Headless `-p` mode always uses Kimi's auto permission mode. Kimi rejects `--prompt` combined with
`--yolo`, `--auto`, or `--plan`, so the relay passes no autonomy flags and has no `--read-only` or
`--full-access` option. Inspect `touchedFiles` and the diff after every run.

## Artifacts and result fields

Artifacts live outside the repo by default, so they do not appear in `touchedFiles`; an `--out-dir`
inside the worktree can make the artifacts appear there:

- `brief.txt` - the exact brief.
- `events.jsonl` - raw Kimi stdout events.
- `final.txt` - assistant text joined with a blank line between chunks; absent if none was emitted.
- `stderr.txt` - complete stderr.
- `result.json` - the stable `delegate-relay.result.v1` contract.

`result.json` fields:

- `schema`, `tool` (`"kimi"`), `status` (`completed` | `failed` | `timeout` | `aborted` | `kimi_unavailable`), `exitCode`, and
  `signal` (`null` unless the child died on a signal).
- `workdir`, `model` (the model alias or `null`), `resumed`, `kimiVersion`, `sessionId`, `startedAt`,
  and `finishedAt`.
- `briefPath`, `finalPath`, `eventsPath`, and `stderrPath`.
- `finalMessage` - assistant `content` strings joined with `"\n\n"`; tool calls and tool results are
  excluded.
- `touchedFiles` - `git status --porcelain` lines for the **final working tree under `--cd` only**,
  not an attribution of Kimi's edits: anything already dirty before dispatch shows up too, and edits
  Kimi makes inside `--add-dir` workspaces do not show up at all - inspect those trees yourself.
  Dispatch from a clean tree when you want the list to read as "what Kimi changed". `null` means git
  could not report; `[]` means git ran and the tree is clean.
- `stderrTail` - the last 20 non-empty stderr lines on any run that did not complete (`failed`, `timeout`, `aborted`), except a launch failure, which reports `failed` with no `stderrTail`.
- `error` - present for launch failures, when the relay watchdog fires (`timeout`), and on an `aborted` run.

Kimi's stream carries no token usage, so `result.json` has no `usage` field.

## Waiting for completion

The helper blocks. Use the orchestrator's background-command facility, or background it in a shell and
poll for `result.json`. The run is done only when the process exits and the file contains a `status`.

A pre-run usage error exits 2 and writes no result. A missing `kimi` exits 127 and writes
`status: "kimi_unavailable"`.

## When a run misbehaves

- **`status: "kimi_unavailable"` (exit 127):** install the native Kimi Code CLI, authenticate with
  `kimi login`, and re-dispatch.
- **an `error` mentioning `version preflight` (`failed`, or `timeout` at exit 124):** the bounded
  `kimi --version` probe exited non-zero or hung past its cap (10s, or `--timeout` when shorter), so
  kimi was never dispatched; only the relay's own artifacts may already exist under `--out-dir`.
  Check the install by running `kimi --version` yourself.
- **`status: "failed"`:** read `stderrTail`, `stderrPath`, and the tail of `events.jsonl`. A common
  cause is an unconfigured model alias: `error: failed to run prompt: config.invalid: Model "<x>" is not configured in config.toml…`
- **`status: "aborted"`:** the relay itself was killed (its parent's timeout, a stopped task, a
  closed terminal) and forwarded the kill to kimi. The result is written before the relay exits;
  inspect the working tree before re-dispatching. On native Windows a hard kill of the relay is
  uncatchable (Node supports no `SIGTERM` handler there), so this status may never get written -
  a relay process that is gone without a `result.json` is an aborted run; inspect the working
  tree and `events.jsonl` directly.
- **`status: "failed"` with `signal: "SIGKILL"`:** the host killed the process, commonly through the
  OOM killer or a supervisor timeout. This is not a Kimi error; check host memory and re-dispatch, or
  split the task into smaller briefs.
- **`status: "timeout"`:** the `--timeout` watchdog killed the run; `error` reads
  `kimi did not finish within --timeout <dur>; killed by the relay watchdog`. Increase `--timeout` or
  split the task. The relay sends SIGTERM, waits 10 seconds, then sends SIGKILL if needed.
- **Empty `finalMessage`:** inspect `touchedFiles` and the diff. Add a
  `<structured_output_contract>` to the next brief to require a closing report.

## Recovering lost work

`events.jsonl` in the run directory records every event the implementer streamed. If finished
work is lost — the run killed late, or the working tree damaged afterward — read the event log
before re-dispatching: it identifies which files and tool commands were involved, which scopes
what needs redoing. Whether it also carries the edit contents depends on what the CLI streams,
so treat any reconstruction as unverified until it matches a working-tree diff — when the tree
still holds the work, preserve the tree rather than replaying the log.

## What the relay runs

The argv is equivalent to:

```bash
kimi --output-format stream-json [--model <alias>] [--session <id> | --continue] \
  [--add-dir <dir> ...] --prompt=<brief>
```

The prompt rides argv and is visible in the host process list. The relay rejects briefs over 120 KB
before launch because the OS caps a single argument. It spawns the native `kimi` binary directly with
the selected `--cd` as cwd; no shell or Kimi timeout flag is involved.

## The commit boundary

The relay never commits. Kimi edits the working tree; the orchestrator reviews, re-runs the gates, and
commits. See [review-and-land.md](review-and-land.md).

# Multi-task queues

The single-task loop scales to a queue: a removal across layers, a migration across files, or a
refactor sweep. Sequencing and bookkeeping make it trustworthy.

## Run sequentially, one commit per task

Run tasks **one at a time, in dependency order**, landing each after review and gates before
dispatching the next:

```bash
node "<skill-dir>/scripts/relay.mjs" --brief task-01.txt --cd /path/to/repo
```

- Later briefs can rely on earlier work only after it lands.
- One commit per task keeps history reviewable and each step revertible.
- A clean tree before each dispatch keeps `touchedFiles` honest.

Use parallel runs only for genuinely independent tasks in separate working trees. Sequential is the
default because it preserves clean task boundaries.

## Carry decided constraints forward

Fresh Kimi sessions do not remember earlier tasks. If task 2 chooses a helper name, fixture location,
or interface that task 5 needs, write that fact into task 5's brief.

Use a resumed Kimi session only for rework on the same task. Send a delta brief with `--resume-last`,
or with `--session <id>` from that task's `result.json`. Start unrelated queue items in fresh sessions.

## Keep a progress file

For more than two or three tasks, maintain one progress file beside the work:

- **Status table** - queued / at-implementer / reviewed+committed, with the commit hash.
- **Per-task review notes** - what landed, what you verified, and gate outcomes.
- **Needs your eyes** - design decisions, non-blocking nitpicks, and questions for the human.
- **End-of-run checklist** - the final cross-task verification.

Update it when each task lands, not in one batch at the end.

## Close with a coherence check

After the last task:

- Run the full test/build once more.
- Search repo-wide for the thing the queue changed.
- Replay migrations from a clean state and check drift when applicable.
- Push and open or update the PR only after the final tree is coherent.

## When to stop and ask

Proceed on work that follows from the agreed plan. Stop and surface when:

- A task cannot be completed correctly within its brief.
- Review calls the plan itself into question.
- Gates reveal a problem affecting already-landed tasks.

Report the landed state, commit hashes, and open question, then wait.

# Review and land

Kimi did the typing; you own the judgment. Verify against reality, never the self-report, and read the
diff as generated code because a green gate cannot catch every failure mode.

## Check tests before trusting gates

If the diff touches existing tests, review those edits first:

- Treat unbriefed test edits as a contract change, not part of the fix.
- Treat newly skipped, disabled, or commented-out tests as failing until proven otherwise.
- Treat loosened assertions the same way: contains/truthy replacing exact matches, broadened error
  types, and widened tolerances all weaken the gate.

## Re-run the gates yourself

`result.json` carries Kimi's claims, not evidence. Re-run the project's actual test, lint, and build
commands in the working tree and read their output. Passing is necessary, not sufficient.

For changes with a specialized verification shape:

- **Migrations or schema:** round-trip them and check for drift.
- **Removals or renames:** grep for dangling references.
- **Stateful behavior:** exercise the behavior, not just compilation.

## Read the diff against the brief

Start with `touchedFiles`, open the diff, and compare it to the brief:

- **Scope creep** - changes the brief excluded.
- **Scope shortfall** - missed behavior, edges, or cleanup.
- **Quiet judgment calls** - defensible but unasked decisions that need review.

## The implementer sweep

Check every diff for patterns gates often miss:

- Hardcoded success or fixture data on a real-work path.
- Catch-all error handling that returns a default instead of propagating or recovering.
- Imports, dependencies, methods, and signatures not present in the installed version.
- Unused imports, uncalled helpers, unreachable branches, and scaffolding comments.
- A second client, error idiom, or logging style beside the repo's existing one.
- Tests that assert internals instead of behavior, or near-duplicate test bodies.
- Optional parameters, config flags, and abstractions with no caller.
- Guards for impossible cases that hide trust-boundary validation.

Send anything blocking back to Kimi as a delta brief, or fix it in the tree, and report either choice
to the human. Run relevant guard skills if installed.

## The commit boundary

When the gates pass and the diff holds, **the orchestrator commits**, never the implementer. Write a
clear message describing what landed.

From dispatch until that commit, the uncommitted working tree is the authoritative copy of the
implementer's work — the only one you can commit from, and often the only copy at all. Never run `git checkout`, `reset`, `clean`, or a branch switch in the
workspace between those two points — however messy an interrupted run looks, inspect it first:
`git status`, `git diff`, `git diff --cached` for anything the implementer staged (plain
`git diff` is blind to the index), and open any untracked files (`??` in `git status`) directly —
they are the implementer's new files, and no diff shows their contents. The tree is evidence,
not clutter. After that inspection the
verdict can legitimately be to discard — work built on a premise you have since corrected, for
example — and then `git checkout`/`clean` is the right tool. The ban is on reflexive cleanup
before anyone has looked.

## Rework: send the delta

Continue the same session with only the correction:

```bash
echo "The fix is right, but the test mocks the DB session. Use the real migrated fixture and remove the
unused import." | node "<skill-dir>/scripts/relay.mjs" --resume-last --cd /path/to/repo
```

Use `--session <id>` instead when resuming the specific id recorded in `result.json`. Kimi itself
rejects combining `--continue` and `--session`; the relay rejects `--resume-last` plus `--session`
before launch. Rework gets the same gate rerun, test review, diff review, and implementer sweep.

Headless Kimi always uses auto permission mode and has no CLI-enforced read-only mode. Confirm
`touchedFiles` after every fresh or resumed run.

## Surface, do not absorb

The human opted into delegation, so committing verified, gate-passing work is the contract. Keep them
in the loop when the work changes shape:

- Report design decisions and defensible-but-unrequested turns.
- Note non-blocking nitpicks you did not block on.
- Stop and ask if correct completion requires going beyond the brief.

For a queue, keep these notes in the progress file described in
[multi-task-queues.md](multi-task-queues.md).

# Writing the brief

A brief is the entire task as Kimi will see it. It runs in a separate session with **no memory of your
conversation, no access to prior notes, and no shared context** - only the text you send and whatever
it can inspect in the workspace. If a constraint is not in the brief or discoverable in the repo, it
does not exist for Kimi.

## Model choice and resumed sessions

Kimi uses `default_model` from its `config.toml`, so a fresh dispatch does not require `--model`. Pass
`--model <alias from your kimi config>` only when the human wants one of their configured model
aliases. Do not invent an alias.

A resumed run keeps the session context. Send only the delta brief with `--resume-last` or
`--session <id>`.

## The shape that works

Use a compact, block-structured brief. State the task, what done means, the few constraints that
matter, and the report Kimi must return.

```xml
<task>
One or two sentences: the concrete job and where it lives. Then the specifics - current state, what to
change, and explicitly what to leave untouched. The leave-untouched list prevents unrelated refactors.
</task>

<verification_loop>
Run these before finishing and fix anything they surface, do not just report it:
  <the project's real test command>
  <the project's real lint/format command>
  <the project's real build/typecheck command>
Confirm the working tree shows only the intended changes afterward.
</verification_loop>

<action_safety>
Keep changes scoped to the task. No unrelated refactors, renames, or cleanup unless required for
correctness. Do NOT run git add or git commit - the orchestrator commits after reviewing. Leave the
work uncommitted in the working tree.
</action_safety>

<structured_output_contract>
End with a report in this exact shape:
  1. What changed and why
  2. Files touched
  3. Gate outcomes (include test/lint counts)
  4. Anything you deviated on, left open, or want a decision on
</structured_output_contract>
```

Add extra blocks only when the task needs them:

- **Debugging or open-ended fixes** - add `<completeness_contract>` (resolve fully, not just the first
  plausible cause) and `<missing_context_gating>` (find missing repo facts or state what is unknown).
- **Research or recommendations** - add `<research_mode>` (separate observed facts, inferences, and
  open questions).

## Always ask for the report explicitly

The relay builds `finalMessage` from assistant text in Kimi's structured stream. Without a closing
summary, the edits may exist but the result is hard to review. The `<structured_output_contract>`
block makes the expected report explicit.

## Discover the real gates

Read the repo's `AGENTS.md`, `CLAUDE.md`, `Makefile`, `package.json`, or equivalent first and copy the
actual commands into `<verification_loop>`. A brief that says only "run the tests" makes the
implementer guess or skip them.

## Honor repo conventions

Restate the load-bearing house rules in the brief. Kimi can inspect the workspace, but the important
constraints should be directly in front of it.

## One task per brief

Keep each brief bounded. One brief -> one Kimi run -> one reviewed commit keeps the diff and rollback
clean. Split mixed implementation, review, documentation, and roadmap requests into separate
dispatches.

## Premises freeze at dispatch

The implementer starts from the brief's facts and there is no steering channel mid-run. Audit the
fact block before sending — ownership, target branch, constraints, anything a judgment call rests
on. If a premise turns out wrong while the run is live, stop the run and re-dispatch a corrected
brief rather than discounting the output afterward; for a write-capable run, inspect the working
tree and reconcile any partial or premise-contaminated edits — keep or revert them — before the
re-dispatch.

## A worked example

```xml
<task>
In the payments service at services/billing/, the refund path double-charges when a refund is retried
after a network timeout. Make refund submission idempotent: check for an existing refund by idempotency
key before creating a new one. Touch only services/billing/refund.py and its tests. Leave the charge
path, API routes, and data models untouched.
</task>

<verification_loop>
Run and make green before finishing:
  pytest tests/billing/ -q
  ruff check services/billing/
Confirm git status shows only refund.py and its test file changed.
</verification_loop>

<action_safety>
Scope strictly to the refund idempotency fix. No unrelated refactors. Do NOT git add or commit; leave
changes in the working tree for review.
</action_safety>

<structured_output_contract>
Report: (1) the root cause and fix, (2) files touched, (3) pytest and ruff outcomes with counts,
(4) anything left open or needing a decision.
</structured_output_contract>
```

## Argv delivery limits

Kimi headless mode requires the brief as a command-line argument. The relay reads a file or stdin for
convenience, then passes the text with `--prompt=<brief>`. The equals form binds a brief that starts
with `-` instead of treating it as another flag.

This has two consequences:

- The brief is visible in the host process list (`ps`, `/proc`). Keep secrets out of it on shared
  machines; reference workspace files or environment variables instead.
- A brief over 120 KB is rejected before launch because operating systems cap a single argv value.
  Put large context in the workspace and tell Kimi which file to read.

Dispatch with [dispatch-and-poll.md](dispatch-and-poll.md), then review and commit with
[review-and-land.md](review-and-land.md).