Files
pipelines/internal/author/skill/references/format.md
T
alan c9b904186a Update templates and authoring skill to the current pipeline contract
Bring the packaged starters and the pipelines skill up to the guidelines the
project now works to.

Templates:
- task and three-stage now end in a committer stage that stages the union of the
  runner's captured input.server_changed_files and the producer's declared
  changed_files, runs the repository's checks, commits locally and never pushes;
  their producers no longer commit.
- Every model/agent prompt states the line-oriented result contract (outcome on the
  first non-empty line, "# output" JSON map, other "# <heading>" sections kept
  verbatim as evidence) and an "# evidence" section for exact commands and results,
  with proportionate verification and no fabricated checks.
- Stages that can write save their reports, logs and screenshots into the runtime
  artifacts directory.
- Remove the summary starter: a tool-free single-prompt text transform with no
  repository interaction, artifact or commit is a format demonstration, not a
  reusable workflow. No starter invents a pretend approval stage; a decision point
  is a type=human stage.

Skill:
- references/format.md gains a Result format section (line form, legacy JSON
  precedence, result_parse, raw-output.md, artifacts) and a Committer stages
  section with the pre-commit checklist; the role-split and envelope notes mention
  the line form and the committer.
- orchestration.md points at the checklist and records that a genuine gate is a
  human stage; operations.md and the SKILL.md index drop the removed starter and
  name the result format and committer. No new reference, so the managed inventory
  is unchanged.

Docs/tests: examples/README, README, docs/cli, docs/first-version-testing, the CLI
help example and the smoke script track the four starters; catalog, tool-role,
server, tui and pipeline tests are updated, with a new test pinning the committer
ending and server-captured change set.

Commands run: go build ./...; go vet ./...; go test ./...; python3 -m unittest
discover -s scripts -p 'test_*.py'; python3 scripts/smoke-first-install.py. All
passed. Templates inspected through an isolated CLI server (pipelines templates;
pipelines template KEY --source). No server, service or device was restarted, and
nothing was pushed.
2026-10-17 01:09:42 +01:00

14 KiB
Raw Blame History

Definition format

Definitions are Markdown made only of # stage KEY headings and fenced blocks. An optional # settings section precedes all stages. No unrelated prose outside blocks. The first stage receives input.prompt from the runtime user's task and input.pwd, the resolved run directory recorded by the server; later stages receive previous output unless memory explicitly selects fields from run-local context. There are no stage input blocks. Read references/control.md for selected memory and runner-enforced limits.

Each model stage requires nonempty output, prompt, configs, and edges blocks:

# stage worker

```output
{ summary, evidence, artifacts }
```

```prompt
Perform the task supplied in input.prompt. Return evidence, not invented success.
```

```configs
type=model
provider=opencode-go
model=deepseek-v4.1-flash
retries=2
timeout=1h
```

```tools
```

```edges
success -> #success
blocked -> #failure
error -> #failure
```

Stage/outcome keys begin with a letter and contain letters, digits, _, or -. Each outcome has exactly one target: another stage, #success, or #failure. An omitted error edge defaults to failure. Execution is sequential; forks choose one outcome, never execute parallel branches. Cycles are allowed; every stage must be reachable from entry and have a possible path to a terminal. Use bounded runner-owned limits for feedback loops, never revision counters in model prompts/outputs. Read references/control.md for the exact format.

Result format

A model or agent stage returns a line-oriented document: the first non-empty line is the declared outcome (one of the stage's non-error edges keys), sections begin with # <heading>, and the required # output section holds one JSON object — the output map that later stages and memory select from. Every other heading becomes an evidence field keyed by its normalised heading (lowercased, spaces to underscores) and is retained verbatim, so prose, code fences, quotes and embedded JSON need no escaping. Extra sections are best-effort and never fail the stage.

success

# output
{"task": "x", "changed_files": ["a.go"]}

# evidence
go test ./... — PASS (observed output)

The legacy single JSON envelope { "outcome": "...", "output": {...} } is still accepted unchanged. The parser chooses by precedence: a response whose first non-empty character is { (after an optional surrounding fence) uses the JSON path; a # heading that appears before any { uses the line path. A missing outcome, an undeclared outcome, or a missing/invalid # output fails the stage with FINAL RESULT VALIDATION; salvageable sections are retained and the parse status is recorded under the reserved key result_parse (parsed, partial, failed). The full raw response is saved as raw-output.md in the stage's artifacts directory. Use the line form when the evidence is prose, logs or code; never fabricate a result, never flatten the output fields alongside the outcome, and save any reports, logs or screenshots you produce into the artifacts directory the runtime names (references/delivery.md).

Model configs may set harness=opencode or harness=pi; omission preserves historical OpenCode execution. Read references/harnesses.md for setup/limits. Use the exact provider/model IDs validated during server setup. New drafts/templates inherit that selection; do not assume the host's login matches the container's. Other OpenCode provider/model IDs are accepted syntactically; actual availability, authentication and inference require pipelines provider-check on the execution computer/container. Optional retries defaults to 2 (three total attempts), and accepts integers 0–100; explicit 0 disables execution retries. Optional timeout defaults to 1h per attempt and accepts positive durations such as 30m or 90s. Automatic retries cover retryable transport failures and timeouts; an explicit read-only stage may additionally retry a post-admission deadline or transport failure, while a stage with edit/shell (or no tools block) never replays admitted work. Optional budget_usd=1.50 and budget_tokens=50000 independently cap reported usage. They accumulate across attempts, format repair sessions, and repeated visits to this stage in the same run. Omit either budget to leave that resource unlimited. Both budgets must be positive; tokens include input, output, reasoning and cache reads/writes. Accounting failures stop budget-limited stages. In-flight requests may exceed limits before usage is reported; these are not provider-side hard caps. In current source, budgeted OpenCode V2 text-only calls use tracked prompting with all tools denied, rather than the usage-less /generate path. Completed token-budgeted responses reporting zero tokens fail closed. This is an execution implementation detail, not a new Markdown field: never add backend/format/API settings to definitions. Read references/verification.md for the dated live accounting result and its provider/deployment limitations when relevant. The run has no additional wall-clock deadline; step/visit caps and cancellation still apply. A native ntfy stage accepts timeout but never automatically retries delivery and has no model budget.

Explicit empty tools denies all; allowed tools are read, glob, grep, webfetch, websearch, edit, shell, one per line. No wildcards, delegation, or browser tools. Tools are per-stage and automatically enabled by starting a run. edit supports any file type and creating files/directories in the run directory; no file list is required. shell supports commands appropriate to the repository's language and tooling, not a language-specific allowlist. A missing tools block uses local read/glob/grep/edit/shell tools; prefer explicit stage roles. Planning stages must not label a task blocked simply because they defer edits to an implementer stage. Bundled starters show the intended role split: a task stage may read/edit/shell and conditionally use websearch/webfetch; a planner may read plus conditional web search/fetch; a three-stage implementer has no web tools and works from the planner's research with local read/glob/grep/edit/shell; a reviewer may read plus conditional web; a source-only review stage has no edit/shell; a research stage uses web search/fetch; a committer has read/glob/grep and shell but no edit. Never force web access for trivial, fully understood local edits, and return blocked only when required reliable evidence cannot be obtained rather than whenever one search tool fails. Keep examples and prompts language-neutral unless the task itself asks for a specific language.

Optional permissions is a JSON object with edit (run-directory-relative patterns) and shell (exact commands) arrays. It narrows declared tools and any run-level file scope; it never enables a missing tool. Empty arrays deny actions. Nulls, duplicate/unknown keys, traversal and shell wildcards/chaining/redirects or expansion are rejected. If edits are restricted and shell is enabled, provide an explicit shell list too. Example: {"edit":["README.md","plugin/*.qml"],"shell":["bash -n install.sh"]}. Use this block for intentional file/command restrictions; prose is not a runtime permission policy. Keep ordinary workflows language-neutral and unrestricted within their run directory unless the user asks for a narrower scope.

Human (decision) stages

A type=human stage pauses its run until a person chooses one of its outgoing options. It has no model, agent, tools or configs: it needs a nonempty prompt block (the operator instructions) and at least one non-error edges outcome. Its outcomes are exactly its non-error edges, so a draft can express choices such as deploy, revise or abort; the mandatory error edge is a failure route, not a choice. It validates, renders, exports and imports like every other type.

# stage gate

```output
The operator's decision evidence.
```

```prompt
Review the screenshots and artifacts above, then choose where the run goes.
```

```edges
deploy -> publish
revise -> worker
abort -> #failure
error -> #failure
```

When a run reaches a human stage its step becomes waiting, the run reports it is waiting on a person, and nothing later runs. Decide from the TUI (open the run, press c, pick an option, optionally type feedback, Enter) or the CLI: pipelines decide <run-id> [stage] --option KEY [--feedback TEXT]. The decision and feedback are recorded as the step's evidence (the feedback stays in the step output, never an error diagnostic) and the run resumes along that edge. The wait is persisted, so it survives a server restart. An unknown option is refused with the valid list; a decision to a stage that is not waiting is refused; a repeated decision for an already-decided visit does not double-apply. Cancel and retry keep working while waiting and after a decision, and a human stage is never killed by a stage timeout or max_visits (the shared run budget still applies).

Committer stages

A workflow that changes the repository ends in a committer: a normal model stage whose prompt commits the run's change locally and never pushes, tags, deploys or rewrites history. It is not a native type. Declare shell (and read/glob/grep when it inspects content) and no edit, so a failed check is reported rather than patched, and select the runner's captured change set alongside the producer's declared list:

# stage committer

```prompt
Commit this run's change locally; never push.
```

```memory
{"changed_files":"implementer.changed_files","server_changed_files":"input.server_changed_files"}
```

```tools
read
glob
grep
shell
```

```edges
success -> #success
blocked -> #failure
error -> #failure
```

State this pre-commit checklist in the prompt:

  1. Stage the union of input.server_changed_files (the authoritative, server-captured set) and the declared changed_files, restricted to paths that still exist, keeping every exclusion. A declared list can be incomplete, and a captured path it omitted is still this run's change (references/control.md).
  2. Inspect the staged diff before committing; never commit unrelated work, secrets or generated artifacts.
  3. Run the repository's required checks and record the exact commands and observed results as evidence. Do not commit when a required check fails; return blocked with the failing output instead.
  4. Create no empty commit: when nothing is staged, return success with a clear note.
  5. Commit with a concise message naming the run's change and report the commit hash; never push, tag, rebase or amend.

Merging is the operator's or a lane's job, not the committer's: it commits locally and stops (references/orchestration.md, references/lanes.md). The server does not create the commit and cannot enforce the message; a reviewer checks the rules.

Malformed final JSON has bounded recovery even with retries=0; it never changes verdict/evidence. Recovery tries a deterministic local pass first (append missing closing delimiters, drop one trailing comma, or insert the single comma/colon the parser expected), then at most one deny-all formatter request whose deadline is derived from the payload size and the attempt's remaining budget rather than a fixed short constant. Every path records repaired, partial or unrecoverable in format_repairs; a partial or unrecoverable result is never returned as complete, and an ambiguous payload (an unescaped quote/colon inside a string value) is never guessed at. On an explicit read-only stage a rejected malformed result may be re-emitted up to retries; a stage with edit/shell or no tools block never replays stage tools or re-emits the result, though the deterministic pass and the fresh deny-all, tool-free formatter session still apply. Compatible native stable backends request schema output with schema retries disabled; a retained deny-all, no-inference compatibility probe identifies known format incompatibility. Incompatible native backends and V2 require strict local envelope validation. Do not promise recovery of truncated strings, missing evidence or invalid outcomes. Return the line-oriented result format above, or the strict { "outcome": "declared-edge-key", "output": { ... } } envelope. Do not treat tool-call/DSML markup, plain prose or flattened output as success, or rerun tool work to fix a response's formatting.

Scheduling

Manual-only is the default. To schedule, put # settings before all stages with a nonempty fenced prompt and one or more fenced schedule blocks. Each schedule uses exactly one of times=09:00,17:30 or every=15m, optionally days=mon,tue,wed,thu,fri and timezone=Europe/London. Intervals are at least one minute. Submission activates the latest version's schedules immediately. Removing settings disables schedules on the new version. Scheduled shell/edit are not approved. Warn explicitly before adding/changing schedules.

Notifications

Stage hooks use the global phone connection, never store credentials. Optional fenced notify block: on=success,failure (add waiting to fire when a human stage parks the run), artifacts=markdown. Read this skill's references/notifications.md for the minimal terminal-path recipe and optional native publisher format. Prefer hooks for ordinary success/error alerts; a request to notify is not a request for a new delivery stage. Do not scan the user's repository for Pipelines docs. Bundled starters are generic and manual-only. Notification attachment/report support and model availability need real runtime tests; structural validation alone cannot confirm delivery.