subtask

First commit in good_ref..bad_ref that fails test_cmd, testing up to parallelism commits at once. auto_fix: start a fix job.

Remove a job's worktree, keep branch.

2-4 engines solve prompt blind in worktrees, then one job merges the best (verify, invariants). Returns a group id for wait().

Free quota and API spend.

Raw log lines of a job (last `tail`, filtered by `grep`). Only when the summary is not enough.

Bring worktree jobs back. diff first to review; apply = uncommitted, all or nothing, Python files of symbol_scope jobs merged by symbol; discard removes worktree and branch. auto_resolve: a reconcile job on conflict.

Show or change the shared Jev policy: status | auto | manual | off. Only the operator changes the policy: do not switch it to obtain or avoid a check. Auto checks every new final delivery once within the existing budget; read that outcome in wait()/result before any manual review. All advice is consultative. Credentials are never accepted here: add or replace a key in a terminal with `subtask jev setup` (hidden input), never in chat, argv or a tool argument. Changes apply to new submissions in every configured CLI; no server reload is needed.

The same edit over many files: one job per batch of files matching glob ({{files}} in prompt_template), at most `concurrency` at once, each in a worktree with verify_cmd. Returns a group id for wait().

Preview tasks before workers start. Read deterministic facts and advisory Jev contradictions, then launch=True with plan_id to start the unchanged plan once. Changed inputs require a new preview. This is a coordinator decision within the authorized task, not a new operator permission. Legacy start/start_many remain available. Read dependencies must be explicit in depends_on.

Jev auto adds advisory feedback checks; read the output. Continue a finished job.

Job summary; full=True for all; evidence=True for the JSON envelope.

Advisory Jev review of a terminal delivery against the parent's criteria (1-12). Read the automatic outcome in wait()/result first; do not resubmit the same delivery. Default prepares a local evidence packet without network; packets=True prepares separate claim packets and manifests offline (never submits). submit=True sends one request (unknown sends are never retried). Supply original_request from the coordinator to judge full scope; without it scope_assessment is unproven, which is neither a pass nor a contradiction. supported is advice, not acceptance. provider_choice is the raw answer; assessment includes local vetoes (missing, failed or mismatched evidence), which are not findings by the model. Jev never accepts, merges, deploys or retries the worker; local checks remain necessary. Key/budget errors are final for the call: keys only from `subtask jev setup`, never a tool argument.

Start one job; returns its id. kind: read|code|review|hard. Writes: repo= or isolation='worktree' (own branch). model: engine-specific model id (opencode, codex, kimi, API engines); omitted = the engine's default. verify: shell check run by subtask after the job; max_retries (0-5) resumes with the failure. invariants: default ['no_test_deletion','no_suppression'] fail verify on deleted/skipped tests or new noqa; [] = off. allowed_paths: files outside are reverted. symbol_scope: ['f.py::func'] only those defs may change; integrate merges by symbol. oracle_cmd: after verify passes, run on base and result; reports output_match and speedup_pct. adversarial: a Breaker job writes the tests first. context_refs: file:P[:A-B] | git:diff[:REF] | subtask:ID:summary|diff instead of pasting text; auto_repomap adds a symbol map. policy: worktree|sandbox|isolated|untrusted. tier: auto|fast|balanced|deep|free_only.

Start several jobs in one call. Items take start()'s arguments. With id + depends_on they form a group (grp-…) run as a DAG; subtask:<id>:summary in task/context_refs is replaced by the real job id. With Jev auto, the response includes advisory dependency checks; read them without treating them as permission. foreach=<parent id>: one copy per item of the JSON list the parent writes to .subtask/fanout.json ({{item}} in task), max 8; dependents wait for every copy. after='any': start when one parent succeeded.

One line per job.

Correct a job: hint (instruction sent when the attempt ends) | abort | retry (fresh job with the instruction).

Stop a job.

Block until jobs or groups end and return their summaries. mode: all | any (first to end) | first_success (first done and verified; the rest are stopped). Returns early on a stalled job. since: cursor for clients without progress; with it, timeout is capped at 60 s. For Codex: wait(ids, mode='any', timeout=60, since=''), drop ended ids and pass back cursor=. An idle Codex 0.164.0 is not woken by ordinary local MCP progress or log notifications. Includes the automatic Jev delivery/evidence/risk advice, raw provider choice, wrapper assessment and next action: read it before a manual review and do not resubmit the same work.