Pipelines skill: outcome-first output, aligned review and loop guidance, operator material moved to docs

Rewrite format.md around turn files, the output.md order (# outcome, edge word, # handoff, detail), checks, configs, human stages and the land stage delivery gate (sh -c in a fresh detached worktree, clean checkouts incl. untracked, 64 KB output cap, opencode only). Align review guidance across practices, verification, orchestration and the feedback-loop example. Fix loop-limit semantics in control.md against runner.go, budget_tokens sizing, read for large inputs, blocked-else-error and one stage naming set. Move dated verification logs to docs/verification-history.md and brokered chat, TUI keys and harness internals to docs/operator-reference.md; label operator-only references in SKILL.md.
This commit is contained in:
2026-11-04 17:27:01 +00:00
parent b5927505cc
commit 5090f1cf4e
13 changed files with 1243 additions and 1438 deletions
+291
View File
@@ -0,0 +1,291 @@
# Operator reference
Operator and developer material moved out of the packaged Pipelines skill
(`internal/author/skill/references/operations.md`) because authoring agents
never need it.
## TUI keys
In the TUI, Home advertises `/` omni search and `:` commands. Home `/` opens one
popup over pipelines, versions, runs, steps/visits, artifact names and stage
input/output/evidence text; each row shows a short type badge and a text match
shows a bracketed snippet, and a bare status word or date selects runs. The same
query is available as `pipelines search QUERY [--type KIND]`, where `--type`
narrows the kind. Run Tab switches only
Details ↔ Graph. `n/p` select recorded visits, including repeated stages; `d`
focuses/toggles file changes, `A` opens the run's grouped artifacts view (name,
content type, size and URL per entry, `PgUp`/`PgDn` scroll so a trailing visit
that recorded none stays reachable, `Enter`/`o` to open the selected URL and
`y` to copy it), `a` selects the active/latest retained
configured-harness agent session's bounded, redacted tool evidence, `D`/`:debug`
opens fresh investigation, and `P` opens the pinned pipeline version. `:quit`
exits; `q` does not. Results are retained reports, not independently confirmed
achievements. Distinguish partial output from full success.
## Brokered OpenCode chat
The protocol declares the brokered `chat_*` surface (`chat_sessions`,
`chat_create`, `chat_directories`, `chat_prompt`, `chat_messages`,
`chat_interrupt`, `chat_permission`, `chat_reply`). The server dispatches all of
them, and pushes `chat_event` frames derived from OpenCode's global SSE firehose
(`/event` on the native serve, `/api/event` on the V2 API), with retained
per-session/per-message state so a reconnecting client re-syncs instead of
replaying deltas.
At startup `cmd/pipelines-server` calls `opencode.OpenChat`, which detects the
installed backend and opens exactly one owned `opencode serve` endpoint for it:
the native wire for v1, the V2 API for the installed V2 CLI. Chat is enabled only
when that connection carries a URL-bearing, SSE-capable event endpoint; otherwise
chat stays disabled and every `chat_*` request is answered with a protocol error
naming the missing configuration rather than hanging. Stage generation still
reaches V2 through the `opencode api` CLI, so the owned serve process is chat's
single transport and starts no process for stages. The adapter skips firehose
events it does not surface before decoding their data, so an unrelated event
whose `delta` has a different shape (`session.instructions.updated` carries an
object) never fails the stream.
The operator can instead broker chat from their own OpenCode service with the
opt-in `-opencode-endpoint` flag or `PIPELINES_OPENCODE_ENDPOINT`, with precedence
flag > environment > the endpoint recorded on a previous run and the spawned
instance as the default. `opencode.OpenEndpoint` validates the reference once
(the established http(s)/host/no-credentials/no-query/no-path idiom), detects the
backend from the service's own `/api/info` (V2) or `/global/health` (native)
contract and requires a streamable `text/event-stream` event path; it returns a
connection with **no owned process** and never calls `startServe`. A malformed
reference, an unreachable host, a reachable non-OpenCode service or a
health-ok-but-no-SSE service each disable chat with an error naming the endpoint
and never fall back to the spawned instance. An authenticating endpoint accepts an
optional password only through the private file
`PIPELINES_OPENCODE_ENDPOINT_PASSWORD_FILE` (regular, 0600, single-owner), and
`PIPELINES_OPENCODE_ENDPOINT_USERNAME` overrides the detected default user. The
validated choice is recorded in the additive `server_settings` table so a restart
with no flag/environment reuses it; an unreachable recorded endpoint disables chat
with a clear message and no fallback. `pipelines service enable` preserves the
endpoint and the password-file reference in autostart.
`chat_sessions` lists the operator's own chat sessions, not the sessions pipeline
runs create. Operator sessions are recorded in the dedicated `operator_sessions`
table (`session_id` primary key, plus `directory`, `title`, `tag`, `created_at`,
`last_used_at`), separate from `run_steps`/`run_session_owners`, so an operator
chat is a first-class thing and a pipeline stage session — recorded as run
ownership, never in the operator registry — is never listed. The handler reads the
registry once (bounded to 128 rows, most-recently-used first), calls OpenCode's
session list once, and keeps only registry rows the endpoint still reports, so a
session with no recorded tag is never listed and a deleted upstream session does
not linger. It fills each session's `directory`, `tag` and `created_at`/
`updated_at` from the registry and marks `busy` when another client currently
holds the session (an in-server claim, released when the stream ends or the client
disconnects); a second client's `chat_prompt` for a held session is rejected
before any OpenCode call. It is fail-closed: with no registry configured it
returns an empty list, never the endpoint's whole session list. The OpenCode
session list is read unscoped by directory (the V2 `GET /api/session` otherwise
defaults to the caller's directory), because an operator session may live in any
directory.
`chat_create` creates one operator session and records it in the same registry
with the stored tag `operator` (the display label `Operator` is derived from it,
so there is no second tag vocabulary). It takes a `title` (default "New chat") and
a `directory` (default `~`): an omitted or empty value, `~`, and any `~/...` value
all resolve to `os.UserHomeDir`, never the server's working directory; a relative
path or a missing directory is rejected before any OpenCode call, and a session
created but not recordable is reported as an error naming its id. Create posts the
verified V2 shape `POST /api/session` `{"title":...,"location":{"directory":...}}`.
`chat_directories` returns the operator's home first, then the directories of
previous operator sessions most-recently-used first, deduplicated and bounded (8);
it is a dedicated request so the create dialog can load the choices without first
listing sessions and `chat_sessions` stays a pure, fail-closed session list. A
successful `chat_prompt` touches the session's `last_used_at` in one UPDATE, so it
moves to the front of the list; a non-operator session id touches no row.
`chat_adopt` records a session that already exists on the configured endpoint in
the same operator registry, using the endpoint's own directory and title
verbatim (never a guess, the server's working directory or the home directory).
It reads the endpoint once through the shared `Chat.Session` (which reuses
`Sessions`/`decodeChatSessions`), records through the existing
`RecordOperatorSession` with the `operator` tag, and echoes the adopted session
plus its registry row like `chat_create`, so `chat_sessions` lists it and
`chat_prompt` continues it. A nil payload, a blank or foreign-shaped id, a nil
broker or a nil registry is refused before any endpoint call; an id the endpoint
does not report is refused naming the id and records nothing; an endpoint record
with an empty directory is refused rather than substituting a directory. The CLI
equivalent is `pipelines chat-adopt <session-id>` (`--json` prints the full
response, otherwise a short `Adopted <id> · <directory>` line).
While a `chat_prompt` subscription is open the server also polls
`GET /api/permission/request` on a fixed small interval (first poll immediately) and
pushes one `chat_permission` frame per newly pending approval request, deduped by
request id so a repeated poll never re-pushes the same request. The app answers with
`chat_reply`, which the server forwards as
`POST /api/session/{id}/permission/{requestID}/reply` with
`{"decision":"once"|"always"|"reject"}`. A missing session/request id or an invalid
decision is rejected before any OpenCode call, and the poller stops when the stream
ends or the client disconnects.
The permission list and reply are implemented against the V2 HTTP API only: their
field names match the service's `Permission.Request`/`Permission.Reply` schemas
(verified against the installed service's `/openapi.json`). The native v1 serve
translation rejects them explicitly instead of guessing an endpoint, so on v1 the
permission poller stops quietly rather than reporting the documented limitation as
a per-prompt error.
### Verification evidence (2026-10-17)
Verified against the installed OpenCode 2.0.20 on 2026-10-17:
- `opencode --version` reports `2.0.20`; `opencode --help` advertises `api` and
`serve`. `GET /openapi.json` on an owned `opencode serve` lists `GET /api/event`
(SSE) and the session/prompt/interrupt/permission endpoints.
- A live turn streamed token-level `session.text.delta` and
`session.reasoning.delta` events (each with `assistantMessageID` and `ordinal`),
plus `session.step.*` and `session.usage.updated`; the V2 API server
authenticates the fixed `opencode` basic-auth user.
- The opt-in live end-to-end test (`PIPELINES_TEST_OPENCODE_CHAT_LIVE=1 go test
./internal/server -run TestChatLiveEndToEnd -v`) opened an owned V2 endpoint,
created an operator session through `chat_create` in a chosen directory, listed
exactly that session through `chat_sessions` (with its directory and tag
`operator`), recorded a genuine pipeline stage session in
`run_steps`/`run_session_owners` and showed it never appeared in the list, and
streamed a completed turn as `[step:started,text,step:streamed,step:ended]`
(first delta `"pong"`). The operator-session registry, the filter, directory
defaulting and the recents bound are also covered by the `pipeline`, `opencode`
and `server` unit tests, which run without the live gate.
- Not verified live: a genuine pending-approval round trip and any backend other
than the installed 2.0.20. The permission wire shapes are unit-tested over an
httptest fixture, not against a live pending request.
- Operator-supplied endpoint selection and `chat_adopt` (added 2026-10-17):
`opencode.OpenEndpoint` and the flag/env/recorded precedence, the URL-shape
validation failures (scheme, empty host, userinfo, query, fragment, non-empty
path), the unreachable/non-OpenCode/no-SSE/auth-mismatch failures, the
no-owned-process property (`conn.process == nil`) and the password-file rule
are unit-tested over httptest fixtures in `internal/opencode/endpoint_test.go`.
`chat_adopt` (endpoint directory/title recorded with the `operator` tag, echo,
missing id refused naming the id and recording nothing, nil payload/blank id/nil
broker/nil registry refused before any endpoint call, empty endpoint directory
refused) is unit-tested over the server fake broker in
`internal/server/chat_test.go`; the recorded-endpoint round-trip across a store
Close/Open is in `internal/pipeline/settings_test.go`; the protocol round-trip
and the CLI dispatch (`pipelines chat-adopt`) are covered in
`internal/protocol/chat_test.go` and `internal/cli/chat_adopt_test.go`. The
live scratch-server check against the operator's real endpoint (adopt, list,
prompt) was **not** run in this change; only the unit fixtures above were
executed.
Deployment state: not deployed. This is reviewed and committed locally only;
deploying it (and restarting the server) is the operator's step. Do not describe
brokered chat as already deployed.
Decide a waiting human stage in the TUI: open the run, press `c`, pick an option,
optionally type feedback, Enter.
## Docker release resolution
Docker setup resolves the current supported OpenCode V2 release from the single
documented complete `GET .../git/matching-refs/tags/v2` response (a bounded
complete array with no pagination parameters; never the moving `latest` tag or
the registry's insertion order) and the current Pi release from npm, resolves the
selected tag's immutable GHCR `sha256` digest, builds `FROM` that digest, and
verifies the built image reports exactly those executable versions plus a
Node-compatible Pi engine.
It fails closed, keeping the last verified Dockerfile fallback pins, when discovery,
digest resolution, completeness, build or compatibility cannot be established: never
a hardcoded fallback, never a silent stale-pin substitution. A full install skips a
rebuild only when the release receipt **and** the actual built image's release and
source identity labels already match; a dirty source always invokes the Docker
build and relies on layer caching. A model/login-only reconfiguration compares only
the verified release image identity, so a changed source alone does not rebuild.
`pipelines harness setup opencode|pi` reconfigures inside the existing container and
refuses an image that does not match; it does not rebuild or restart services (an
explicit ordinary `./install` does when the user asks).
## Harness internals
CLI `new/edit/debug` and TUI author/debug build one shared, Docker-aware CLI
prefix. A Docker-linked profile embeds the in-container `/usr/local/bin/pipelines`
(never the host binary: Linux can see but cannot execute a mounted macOS host
executable). Loopback is recognized only via `net.ParseIP(...).IsLoopback()` plus
an exact case-insensitive `localhost`, so a remote DNS name such as
`127.remote.example` stays remote and runs no probe. For a loopback logical
`--url`, a single bounded `docker compose port` probe parses each returned line
as a complete `host:port` binding (IPv4/IPv6/wildcard) and the prefix maps only
when a binding covers the requested loopback address and port; malformed or
non-matching bindings fail closed. A loopback `wss` endpoint is rejected as
having no supported local TLS mapping rather than downgraded to plaintext. On a
match it embeds scoped `PIPELINES_TRANSPORT_SOURCE`/`PIPELINES_TRANSPORT_TARGET`
aliases in the prefix string (not `cmd.Env`, so the pre-existing harness
server's tools inherit them). The client rewrites an endpoint only on an exact
source match; remote endpoints stay remote. Draft metadata (server, base
version, create-only guard) is preserved unchanged.
`provider-check` with a Docker-linked profile runs inside that profile's existing
Compose service with `-T`, the original cwd/model/timeout and exact stdout/exit
propagation; container profiles have no `DockerDirectory` and cannot recurse, and
explicit native profiles keep the host path. The picker uses a true `x/term` TTY
check, so `/dev/null` and pipes fail fast instead of hanging.
On an existing Docker setup, `pipelines harness setup opencode|pi` configures inside its container and link the host
launcher without restarting/deploying services. They resolve and verify the current
OpenCode V2 release from the single documented complete
`GET .../git/matching-refs/tags/v2` response (a bounded complete array with no
pagination parameters; never the moving `latest` tag or the registry's insertion
order) and the current Pi release from npm, resolve the selected tag's immutable
GHCR `sha256` digest, and require a rebuild only when the verified release image
identity no longer matches. A full install always invokes the Docker build for a
dirty source (relying on layer caching); a model/login-only reconfiguration does
not rebuild. Setup writes its generated release receipt to the machine-local root
file `.pipelines-releases.json` (with atomic `.pipelines-releases-*` temporary
files); both are git-ignored, so a fresh clean checkout stays clean and reinstall
still reuses the verified release/image identity. The actual built image's labels
stay authoritative and a dirty source still rebuilds. If discovery, digest
resolution or completeness cannot be established they stop with an error (keeping
the last verified Dockerfile fallback pins); they never guess, fall back to a host
runtime or install a stale pin.
(`./install --opencode`/`--pi` were removed and only point to that command.) The native installation reuses the host OpenCode
configuration, writes **host** (non-Docker) profiles for the harnesses it detects
into XDG config home's `pipelines/harnesses.json`, and clears a stale Docker link
so a Docker-era profile is not left Docker-linked. It never installs, upgrades or
downloads a harness. Container and host credentials and accounts remain independent and
are reused on reinstall/reconfigure. `./install` installs natively by default
(`--native` is equivalent); explicit `./install --docker` selects the Docker
server + ntfy installation.
Fresh setup accepts `./install --docker --harness pi` to skip OpenCode
login. Existing setup can configure either harness independently. Pi setup does
not run a generation check; `provider-check --harness pi --model PROVIDER/MODEL`
is a separate confirmed, potentially chargeable check.
Profiles live in XDG config home's `pipelines/harnesses.json`, store preferences
only, and preserve unrelated configuration. A profile launches a native host
harness unless it records a Docker checkout directory, in which case it launches
through that installation's Compose service. `harness setup <opencode|pi> --host`
configures or converts a host profile and clears any Docker link; without
`--host`, reconfiguring a Docker-linked profile re-verifies that the recorded
directory still has `compose.yaml` and fails naming it rather than saving a link
that cannot launch. Setup's summary and `harness list` report the resulting mode
(and, for Docker, the directory). Harness CLI setup/default commands
always configure the local execution user, not a remote `--url` server.
OpenCode interactive launch uses
`mini --model`: verified V2 full CLI lacks a model flag. Pi uses its CLI with the
packaged skill explicitly loaded. Pi has no standalone `auth login` command
(verified `pi auth --help`: only credential check/print): setup prints a
title-plus-three-lines Pi sign-in handoff and opens a fresh, no-context,
extension-free, no-prompt-templates, no-tools session with Pi's documented
`--tui-mode regular` flag, so the header and handoff stay visible above Pi's
interface at 80x30 instead of the default fullscreen clear. The user types
`/login`, chooses an authentication method ("Sign in with an API key" for
provider API credentials; account and Radius remain the user's choice), finishes
provider sign-in, then exits with `ctrl+c`/`ctrl+d` to return to Pipelines model
configuration. Existing sign-ins are reused by exiting when no new sign-in is
needed; completing a sign-in can update the credentials stored in the Docker
volume. No coding/task prompt or scripted keystrokes are injected.
OpenCode V2 model stages settle long sessions by polling `GET /api/session/active`
about once per second under the stage context, instead of the `.../wait` request
whose CLI-side request timeout failed long stages after roughly six minutes
(HTTP 499, dated 2026-10-10). V1 native settlement is unchanged. Final results
and debug session evidence use the same single bounded latest-assistant readback
(`order=desc&limit=1&type=assistant`), so a small final result is visible behind
large prior tool content; retained transcripts over 32 KiB are stored as valid
bounded preview envelopes that preserve stage limits and diagnostics, and exact
outputs remain authoritative. Pi evidence is JSONL and is not parsed as one JSON
object. Short-lived context-controlled CLI calls (`--help` detection, API calls
and the native export fallback) share one finite inherited-pipe drain grace
(`os/exec.Cmd.WaitDelay` ~250ms) so a canceled context or a descendant that still
holds stdout/stderr cannot block for the child's natural lifetime; the
`context.Canceled`/`DeadlineExceeded` and `exec.ErrWaitDelay` identities are
preserved and partial stdout after the grace is never accepted as success.
+612
View File
@@ -0,0 +1,612 @@
# Verification history
Dated verification logs and backend caveats moved out of the packaged
Pipelines skill (`internal/author/skill/references/verification.md` and
`harnesses.md`) so authoring agents do not load them. They are a historical
record: the JSON/line-format result envelope and the format-repair ladder they
describe are retired. Model stages now write `output.md` and only its
`# outcome` section is parsed (`internal/author/skill/references/format.md`,
`docs/model-results.md`).
## From the skill verification reference
### Budgets and backend caveats
Defaults remain two retries and one hour per stage attempt; a run-level wall-clock
deadline is not added. Budgets are optional, positive and independent USD/token
reported-usage limits shared across attempts and repeat visits.
Accounting failures stop budget-limited stages. In-flight calls can overshoot;
these are **not provider-side hard caps or a guaranteed bill ceiling**. Reported
USD may validly be zero; do not fabricate prices/accounting from output length.
Per-run usage is recorded as typed step evidence from the usage the stage already
measured for its budget (no second harness read and no transcript parse), and
totalled for the run and over all history. A stage revisited within a run shares
one budget, so each step records only that visit's increment of it and the run
total is not the cumulative stage budget counted again; a revisit that reports
nothing new (a failure or timeout before any usage poll, or a Pi visit that never
reaches a usage stat) records no usage for that visit rather than a known zero.
`CLI_PREFIX inspect RUN_ID --json`
exposes each model step's `tokens_total`, `tokens_in`/`tokens_out` (only when
`split_known`), `cost_usd` (only when `cost_known`) and the model it ran with,
plus the totalled `usage`; `CLI_PREFIX stats --json` adds the history-wide totals,
which equal the sum of the per-run totals. A stage that reported no cost exposes
its tokens and marks the cost unavailable rather than showing zero; a harness that
reports only a total (Pi) exposes the total and marks the in/out split
unavailable rather than presenting the total as input tokens. An upgraded or
historical database gains an empty usage table with no backfill, so old runs omit
`usage` instead of showing zero. This is current source, not deployment evidence.
Dated current-source evidence (2026-10-17, this machine). A throwaway read-only
reader (`internal` store API) over a scratch copy of
`~/.local/share/pipelines/data/pipelines.db`, taken with
`sqlite3 "file:$HOME/.local/share/pipelines/data/pipelines.db?mode=ro" ".backup <scratch>"`
so the live DB is never mutated, opened 228 runs and found **no** `step_usage`
rows: every stored run predates this change, so per-run figures are unavailable
rather than zero. Run 314 (this item's own run) and run 239 (whose implementer
step ran `opencode-go/kimi-k2.7-code`, a stage model different from the pinned
`opencode-go/deepseek-v4.1-flash`) both report `usage=(none recorded)`, and
`stats` omits the history-wide totals. The recorded figures themselves are
covered by the passing current-source round trips — `internal/pipeline/usage_test.go`,
`internal/server/usage_test.go` (including `inspect --json` over a websocket) and
the pre-upgrade/read-bounded/stats-sum cases — not by a live run, because the
deployed server predates this change and was not restarted. No live model call,
deploy or rebuild produced this evidence.
A live V2 trial found `/generate` returned text while its retained session had no
messages and zero counters. Current source uses tracked `/prompt` → bounded
active-session polling → message readback for **budgeted V2 text-only calls, with
all tools denied**. Completed token-budgeted responses reporting zero tokens fail
closed. No new definition flags or agent tools are required for this fix.
Unbudgeted tool-free V2 generation can still have empty backend message history;
pipeline inputs, results and command audit remain retained. An unbudgeted V2
audited agent stage makes exactly one extra bounded final session-aggregate read
to record any reported USD/token usage best-effort: missing or invalid usage stays
unknown and never turns a valid run into a failure, cumulative sessions/retries
are keyed per session so they cannot double count, and totals are never inferred
from final-assistant-only or native-partial data. Budgeted settlement and native
V1 enforcement are unchanged. Native V1 uses its existing path.
The V2 `.../experimental/session/{id}/wait` request is **no longer used**: a dated
Docker log shows it timing out at the CLI's own request timeout after about six
minutes (run started 2026-10-10T23:07:16.547Z, `TimeoutError` logged at
2026-10-10T23:13:17.262Z, server `http.status=499`), which aborted a long
implementation stage. Instead current source polls `GET /api/session/active`
about once per second with a context-aware delay and no busy loop, until the
admitted session is absent (inactive). Missing/null/non-object `data`, or a state
other than the documented `running` type, fails closed and is never treated as
inactive. This is **mocked regression coverage** in `internal/stage` (fake CLI),
not live-provider evidence; V1 native settlement is unchanged.
Current source reads the V2 final result with a single bounded descending
final-assistant readback (`order=desc&limit=1&type=assistant`) after the settled
poll, for both audited agent stages and budgeted V2 text-only calls, so large
retained history (including prior tool-read contents) is no longer fetched just
to select the completed result. A truncated/incomplete readback, an empty data
list, or a latest message that is neither completed `stop` nor a completed
structured tool-call fails closed with a sanitized diagnostic that omits
provider content; retained audit previews are **not** executable final results.
Session/debug evidence now reuses the same single latest-assistant readback
instead of a recent-20 all-message fetch, and returns each payload as a labelled
bounded, credential-redacted envelope with explicit preview/truncation/missing
diagnostics; a small final assistant result is therefore selected even when large
prior tool content exists. Pi evidence remains documented JSONL and is never
parsed as one JSON object. This describes current source behavior, not a guarantee
that a user's installed server includes the fix. An updated skill/client is not
deployment evidence; never rebuild/restart services or log into providers without
specific authorization.
Retained model-stage failures now carry a fixed sanitized category. A strictly
invalid final result (a duplicate nested field, or malformed/ambiguous JSON with a
byte offset) is labeled `FINAL RESULT VALIDATION`; request, V2 active-session poll
and final-readback failures are labeled `HARNESS TRANSPORT`. A pre-admission
request failure replays nothing and is retried for any stage; a post-admission
failure is retried only on an explicit read-only stage (see the 2026-10-17 section
below). A validation failure
preserves the admitted session, transcript and evidence and performs no second tool
execution. Confirmed ordinary-endpoint failures on 2026-10-11: an all-history
readback of exactly 262144 bytes of incomplete JSON (`invalid agent messages`), a
reviewer result with a duplicate nested `performance_review` field, and an
onboarding visual-review result with `invalid character 'z' after object key:value
pair at byte 3968` where unsafe lossless repair was rejected. These are **mocked
`internal/stage` fixtures**: executable source-level evidence, not live-provider
evidence and not a deployment. OpenCode V2 prose `output_contract` does not enforce
structured output; V2 results are validated locally and no unsupported V2 format
field is sent. A review-only fresh execution is a future recovery idea, **not
implemented**. Onboarding UI visual approval remains unresolved and must not be
reported complete.
### Bounded malformed-result recovery: 2026-10-16
Source-level, mocked `internal/stage` regression coverage (not live-provider
evidence and not a deployment): malformed final-result recovery now tries a
deterministic local pass first (append missing closers, 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, the stage
timeout and the attempt's remaining budget rather than a fixed 30-second
constant. Every path
records `repaired`, `partial` or `unrecoverable` in `format_repairs`; a `partial`
or `unrecoverable` payload is never returned as a completed result, and an
ambiguous payload (an unescaped quote/colon inside a string value) is never
guessed at. A shell-enabled stage's malformed but deterministically recoverable
result now completes without replaying admitted tool work; `safeToReplay` is
unchanged. The run-55 `ui_reviewer` payload was retrieved read-only with
`pipelines inspect 55 --json` and reproduced its exact byte offset 7837; it is the
ambiguous error class, so it is reported unrecoverable rather than repaired. This
does not update or restart any running server.
### Harness transport reach retry and repair deadline: 2026-10-17
Source-level, mocked `internal/stage`, `internal/opencode` and `internal/server`
regression coverage (not live-provider evidence and not a deployment): the
harness transport path now distinguishes a pre-admission reach failure
(connecting or creating the session) from a post-admission readback/poll/agent
failure under the one `HARNESS TRANSPORT` category. A pre-admission reach failure
replays nothing, so it is retried within `retries` for any stage with a fresh
session and no replayed prompt; a post-admission failure is retried only on an
explicit read-only stage, and an `edit`/`shell`/legacy stage still never replays
admitted work. A context that expires during a request keeps both the sanitized
transport detail (operation/status/exit) and
`errors.Is(err, context.DeadlineExceeded)`; a bare attempt-boundary deadline is
not treated as a reach failure and stays terminal for a mutating stage. An
unrecognized provider execution-error name is reported as a bounded, sanitized
identifier plus any HTTP status. The isolated formatter deadline is now
proportional to the stage timeout (floored, capped, and clamped to
`remaining - margin` so it can never extend the stage/attempt deadline). These are
mocked fixtures; a deployed server is not updated by this change.
### Failure-handling source changes: 2026-10-15
Source-level, mocked `internal/stage` and `internal/server` regression coverage
(not live-provider evidence): an explicit read-only tools stage now actually
retries a post-admission stage deadline or harness transport failure, creating a
fresh bounded session per attempt, while a stage with `edit`/`shell` or no tools
block still never replays admitted work; a malformed final result is re-emitted
up to `retries` only on such a read-only stage with its `format_repairs` evidence
retained. A timed-out agent stage settles knowable V2 usage and retains one
bounded, redacted latest-assistant readback plus a `retained_session` pointer in
its stored transcript. A declared outcome routed to `#failure` with no step
diagnostic now yields a run diagnostic like `stage <key> returned outcome
"blocked"`; an existing step diagnostic is still used verbatim.
### Dated source-level coverage: 2026-10-11
Source-level/mocked regression coverage (not live-provider evidence):
`resolve-releases` now uses a single bounded
`GET .../git/matching-refs/tags/v2` response that the GitHub REST docs describe as
complete with no pagination; offline fixtures cover a 100+ ref array,
`MAX_REFS`/`MAX_BODY` caps, ignored prerelease/build tags, malformed refs and a
missing newest-tag digest failing closed with no older fallback, with no
`tags/list` cross-check. Picker tests cover blink/index preservation,
ANSI-readable selection without a colliding background, and
40x16/80x24/120x36 height budgets. The compiled picker PTY check (opt-in via
`PIPELINES_HARNESS_PTY_DIR`) waits through blink intervals and asserts exact
saved/arrow-scrolled models. `setup-docker.py` accepts the actual
`opencode v2.0.26` probe token and compares source identity only on a full
install; model/login-only reconfiguration compares the verified release image
identity. Python fixtures bind temporary HOME directories so the suite passes
under the container default `/home/pipelines` without weakening mount guards.
The Docker authoring transport is also covered at source level: the shared
prefix picks `/usr/local/bin/pipelines` for a Docker-linked profile. Loopback is
recognized only via `net.ParseIP(...).IsLoopback()` and an exact case-insensitive
`localhost`, so a remote DNS name such as `127.remote.example` stays remote with
no probe. A single bounded `docker compose port` probe parses complete
`host:port` bindings, and scoped source/target aliases are embedded only when a
binding covers the requested loopback address and port; malformed or non-matching
bindings and a loopback `wss` endpoint fail closed, and `client.Dial` rewrites
only an exact source match. `provider-check` dispatches through a Docker-linked
profile's existing service with `-T`, the original cwd/model/timeout, exact
stdout/exit propagation and `--json` passed only in JSON mode (fixture tests, no
real provider), while explicit native profiles keep the host generator. The
picker uses a true `x/term` TTY check so `/dev/null` and pipes fail fast, with a
short context deadline so a regression fails rather than hangs. Real Docker
rebuild/reconfigure against live registries, a real
40x16/80x24/120x36 terminal capture, and real model inference remain **not tested**
in this change.
#### 2026-10-11 Pi sign-in handoff (source + Root PTY observation)
Root separately exercised current-source `pipelines harness setup pi --login`
under a real Docker PTY with copied harness preferences. Root observed that
Pi 1.1.0 defaults to fullscreen and clears the Pipelines login instructions, so
the user sees a coding interface without the `/login` guidance, and that
`/login` first shows "Select authentication method" (account / API key / Radius)
rather than a provider picker. The same handler run with a temporary executable
wrapper passing `pi --tui-mode regular` retained the Pipelines header and
instructions above Pi's interface. Installed `pi --help` documents the supported
`--tui-mode regular` flag and the fullscreen default; `pi auth --help` confirms
there is no standalone login (only print/check, never run). These are source/root
observations with copied preferences: **no provider was selected, no key was
entered and no inference occurred**, and this source is **not deployed** and is
not live-provider evidence. A first reviewer capture at 80x30 found the longer
handoff plus Pi's own banner scrolled the Pipelines header off the top, so the
copy was shortened to a title plus three short lines (existing-credential reuse
folded into the `/login` line, with the account/API key/Radius method choice and
`ctrl+c`/`ctrl+d` exit keys kept) and the redundant trailing blank removed.
Independent PTY re-capture at 80x30/100x36 after this shortening is **not
tested** in this change. The matching exact login-argv and copy assertions are
covered by fixture tests in `internal/cli`/`internal/harness`.
#### 2026-10-11 server CLI fixture isolation (source-level + Root-reported run)
Root-reported runtime evidence supplied for this change (not re-executed by the
authoring stages): the deterministic seeded-profile regression
`go test ./tmp/preview-verification -run TestServerCLIFixtureDoesNotInheritUserDockerProfile -count=1`
seeds a synthetic Docker-linked harness profile in a child
`go test ./internal/server -run '^TestCLIHeadlessRunInspectionCancellationAndRPC$'`.
It previously failed because the child inherited the caller's real
`PIPELINES_HARNESS_CONFIG`, so the CLI `debug` prefix failed closed
("refusing to redirect") against the test's ephemeral httptest endpoint. Root's
four independent preview tests for the bounded transcript helpers pass; Root's
full host race run produced no race warning and only this fixture failure, and
`go vet ./...` passed. Current source therefore isolates the server CLI fixture
with the same missing-temp-file
`t.Setenv("PIPELINES_HARNESS_CONFIG", filepath.Join(t.TempDir(), "harnesses.json"))`
pattern already used by `internal/cli`'s setup, so the host executable stays
authoritative and no Docker probe runs for an ephemeral test endpoint. The
production fail-closed redirect guard in `internal/harness/prefix.go` and its
`refusing to redirect` / loopback-wss regressions are unchanged; the failing
verification was fixed rather than removed.
This is a current-source and Root-reported observation. At the time of that
observation, independent re-execution of the full `go build`/`go vet`/`go test`
matrix (including Docker-only race results) and the final installed-host Docker
verification were **pending**; they are now recorded in the 2026-10-11 FINAL
INSTALLED section below, so this phase-specific wording is superseded by that dated
install. The packaged reference describes source behavior; a source fix or updated
skill is not deployment evidence.
#### 2026-10-11 retained run11 reviewer re-capture (source-level, not a final install)
Independently reading the retained run11 verification at
`tmp/maintenance-run11-verification.json` records the source-level review
sequence: an earlier reviewer PTY capture rejected the longer handoff because at
80x30 it scrolled the Pipelines header off the top; the implementer then
shortened `AuthHandoff` to a title plus three short lines; and the re-run
`reviewer` and `ui_reviewer` stages approved from real current-source Pipelines
PTY captures at 80x30 and 100x36 that showed the header and handoff visible above
installed Pi 1.1.0's regular interface. A labelled controlled fixture that
stripped `--tui-mode regular` reproduced the pre-fix fullscreen clear, and the
review stages report no provider selected, no key entered and no inference. This
is source-level reviewer evidence, read from retained output; it was not a
deployed/installed state at that time, and the final full Docker install
verification was then **pending** — it is now recorded in the 2026-10-11 FINAL
INSTALLED section below, so this phase-specific wording is superseded by that dated
install.
Root-reported actual runs (source-level observations supplied by Root for this
change and not re-verified here): run7 showed both configured providers' exact
handoff markers; runs6/9/10 exercised live maintenance with final-assistant
polling/readback succeeding. These are Root observations, not mocked-regression
coverage and not a completed installation; no final deployed/installed state is
claimed.
#### 2026-10-11 run13 interruption, Docker race limitation and state separation
Four states are kept explicitly separate and must not be conflated:
1. **Current source** (this checkout, not deployed): bounded 32 KiB
(`transcriptBound = 32<<10`) redacted transcript previews produce a valid JSON
envelope with redaction applied before truncation and a rune-safe 8 KiB preview;
session/debug evidence is scoped `latest_bounded_evidence` with the single
bounded latest-assistant readback and at most the 3 most recent session-bearing
steps; an unbudgeted V2 audited agent stage records reported usage best-effort
through exactly one 2s-bounded final session-aggregate read, leaving
missing/invalid usage unknown; and the isolated server CLI fixture uses the
missing-temp-file `PIPELINES_HARNESS_CONFIG` pattern while the production
fail-closed redirect guard in `internal/harness/prefix.go` is unchanged. Pi JSONL
is never parsed as one JSON object; native V1 keeps its existing path.
2. **Host verification evidence independently recorded by Root**: after the fixture
fix, Root ran the full `go test -race -count=1 ./...` and `go vet ./...`; after
three harness-neutral evidence labels and Step wording changes Root re-ran the
affected `tui`/`author`/`cli` race and vet checks, the Python suite (80) and the
opt-in compiled picker PTY check (4). These are Root-recorded host results, not
re-executed by the authoring stages.
3. **Deployed old image**: the running Docker image predates these source changes
and does not include them.
4. **Final install (completed 2026-10-11)**: the final install and installed
authoring/provider verification were **pending** when this separation was
written and are now recorded in the 2026-10-11 FINAL INSTALLED section below; an
updated skill/client or source checkout is still not deployment evidence on its
own.
Docker race limitation (confirmed): the Docker runtime is built with
`CGO_ENABLED=0` and has **no C compiler** (the Alpine runtime stage installs no
GCC/musl-dev), so `go test -race` cannot run there. In-Docker reviewers must use
ordinary `go build`/`go test`/`go vet` and rely on independently executed host
`-race` runs. Race checks must not be attempted in Docker and no compiler may be
installed or searched for.
Run13 interruption (dated evidence, not a fix): the previous reviewer ran `find /`
looking for GCC; the tool timeout left a process in disk sleep, Docker could not
stop the container, and an approved Desktop restart recovered run13 as interrupted
(`executing=false`, every step `agent_active=false`) with **no automatic replay**.
This is an environment/interruption observation only: no general cancellation fix
is inferred and process termination is unchanged. Docker startup recovery already
sets running steps to `interrupted` with `agent_active=0`.
#### 2026-10-11 short-lived CLI inherited-pipe cancellation (current source)
Current source (not deployed) adds one shared, dependency-free constructor in
`internal/opencode`: `CommandContext(ctx, executable, args...)` sets the single
finite `os/exec.Cmd.WaitDelay` constant `ShortLivedWaitDelay = 250ms` and is the
only place that value is defined. It is reused by the `internal/stage`
`OpenCodeClient.call()` API/agent path (including `Interrupt`), `opencode.Detect()`
`--help` and the native `Connection.Messages()` export fallback. It bounds
**draining of inherited output pipes only**: after the child exits os/exec waits at
most the grace for descendants holding the inherited stdout/stderr pipes, then
closes them and reports `exec.ErrWaitDelay`; it does not terminate or confirm
cleanup of descendants.
`context.Canceled`/`context.DeadlineExceeded` identities, `exec.ErrWaitDelay` on
the sanitized errors, the ≤64 KiB request / ≤1 MiB response / 8 KiB stderr bounds,
`boundedBuffer`/`boundedOutput` drain-with-overflow behavior, redaction, strict
result validation and cleanup-unconfirmed active ownership (`ErrStageCleanup`, no
replay) are unchanged; no new module dependency is added and a parent that exits
successfully while a descendant still holds partial stdout is never treated as
success.
Dated synthetic reproduction (`tmp/interrupt-verification`, synthetic
real-subprocess diagnostics, **not provider evidence**): with Root waiting for the
descendant itself to start before cancelling public
`OpenCodeClient{Backend:"v2"}.Interrupt`, two Docker/Linux returns took
3996/3995ms despite `context.Canceled` (`descendant-started.jsonl`); the stronger
host reproduction took 4003/4000ms (`reproduction.log`). Added source-level
regressions use real `os/exec` fixtures with start-marker barriers, bounded
watchdogs and naturally terminating children for cancel-after-descendant,
deadline identity, descendant-held pipes → `ErrWaitDelay`, ordinary
output/exit/redaction, failed-interrupt ownership/no replay, plus `Detect`/export
wait-delay and cancellation cases. This is **current source, not deployed**:
descendant termination, confirmed remote interruption and any run13 Docker disk
sleep fix are **not claimed**, and Docker race remains unavailable (no C
compiler).
#### 2026-10-11 FINAL INSTALLED verification (friend-ready preview)
This is the dated receipt for the installed runtime, recorded by Root from
`tmp/friend-final-verification/summary.json`; it supersedes the earlier
"pending final install" statements above, which stay as phase-specific history.
A normal interactive `./install --model opencode-go/deepseek-v4.1-flash
--harness-model opencode-go/deepseek-v4.1-flash` exited **0**, resolving the current
releases live and building fresh dirty source into actual image
`sha256:1810ab50f3ea3991e7f3548c79250e65a114bb1821eac52efd872b91cf7c3136`
(OpenCode 2.0.26 / Pi 1.1.0 / Node 24.18.1) with real tool-free provider
validation, ntfy authenticated publish, server + host health, home/workspace entry,
preserved authoritative endpoint and `ok` pre-install database/home backup
integrity. Post-install preservation all passed (original definitions 1–4, history
1–16, host/container default Pi and both models/profiles, logical endpoint,
service URLs/timezone/ports/models, Pi credential hash, OpenCode connected accounts,
ntfy token); neither original-repo commit/push nor credential/data cleanup ran.
Installed host-CLI authoring with **both** Docker harnesses (separate retained
drafts, each changing only the worker prompt) performed real `ping` → `pong` and
`validate` → `validated` through the generated Linux `/usr/local/bin/pipelines` and
scoped transport aliases preserving the logical `8081` endpoint and draft metadata,
independently inspected from native OpenCode tool outputs and retained Pi JSONL
`toolResults`, with no draft submit/run/publication. Docker-proxy submit on
verification-only definition 5 published v2, a second stale v1 draft was rejected as
conflict, and **Run17** succeeded in 7 seconds with the exact
`pipelines-docker-verified` markers in OpenCode then Pi, both inactive and exactly
one completed marker read verified from retained native history (not the
latest-assistant preview); best-effort unbudgeted usage was OpenCode 4011
tokens/$0.00029769599999999996 and Pi 1071 tokens/$0.000142002, and
`/api/session/active` was empty after exit. Installed-UI captures
(`installed-pi-*`, `pi-signin-*`, `installed-pi-models-*`) cover the actual run17
80x30/120x36 neutral-Pi/green-both-stage renders, the Pi auth handoff/method menu
viewed/canceled/exit0 with no sign-in, and the model wizard using copied
preferences only while production preferences stayed preserved. Root's independent
checks passed: full host `go test -race -count=1 ./...` and `go vet ./...`,
Python 80 tests (1 optional PTY skipped), Node policy, isolated developer lifecycle
fixture (no inference/deploy) and author package tests; earlier independent
reviewers ran ordinary Docker build/vet/tests and focused subprocess regressions
(no Docker race, no GCC search, no global `find`). **UNVERIFIED** here: fresh
OAuth/provider login completion, phone delivery, other real providers, the
D-disk-sleep fix and active lease expiry; authentication menus and
existing-credential inference are not fresh sign-in proof. The stronger synthetic
PUBLIC `Interrupt` child-start barrier (host 252/252 ms, Docker 250/251 ms, context
canceled true, bounded true vs ~4 s before) is not proof of descendant termination,
remote cleanup or a Docker VM disk fix. Archive extraction, build-identity and
compile verification remain pending until Root executes them.
#### 2026-10-11 generated release receipt ignore (source-hygiene regression)
Current source adds two root-anchored `.gitignore` rules for the installer's
machine-local generated artifacts: `/.pipelines-releases.json` (the receipt path
from `setup-docker.py` `release_receipt_path()`) and `/.pipelines-releases-*` (the
`tempfile.mkstemp` `prefix=".pipelines-releases-"` in `record_release_receipt()`);
no installer/runtime code changed and the pre-existing receipt and other files are
retained. A new `scripts/test_build_metadata.py` case is a controlled, isolated Git
fixture using the repository's actual `.gitignore`: a clean tracked source plus a
representative generated receipt/`.pipelines-releases-*` temporary file leave `git
status --porcelain` empty and `build_metadata.docker_args` at
`PIPELINES_DIRTY=false` with no `-dirty` version; editing the tracked source then
makes the status non-empty and `docker_args` report `PIPELINES_DIRTY=true` with a
`-dirty` version. This is **offline source-level regression coverage**, not the
recorded actual new-account install/provider login above and not live-provider or
deployment evidence; this docs-and-ignore change has no rendered UI.
### Dated live reference validation: 2026-10-10
Environment: Docker Linux aarch64, OpenCode v2.0.20,
**opencode-go/deepseek-v4.1-flash**. Isolated databases/fixtures and local HTTP
notification endpoints; normal published pipelines/repositories were not changed.
- Incident extraction → report: exact IDs/severities/counts, unchanged handoff,
retained session readback and one local success receipt passed (6.63s).
- File edit → verification: exact final release-file bytes, unchanged fixtures,
independently executed `cmp`, completed read/edit/shell evidence, retained edit
diff and no verifier edits passed (14.60s).
- Missing required input: blocked route ended failed; missing file was not invented;
retained read attempt and one local failure receipt passed (4.21s).
- Accounting/one-token budget initially failed its acceptance check because session
zeros let the run succeed. After the tracked-prompt fix, a focused live rerun
passed: **952 reported tokens, $0.00016440**, budget-exceeded failure, stopped
owned session (2.43s). This is not an independently reconciled provider bill.
The earlier three workflows were rechecked from retained artifacts with current
assertions, without more inference. There was **no fresh full-suite live run of
all four workflows after the fix**. Do not generalize these results to all five
starter templates, other models/providers, or compatible native schema/tool usage.
Real ntfy authentication/storage, phone reception, provider outages/timeouts,
long-stream interruption and promptness of cleanup were **not tested** by this trial.
The trial ran rebuilt test binaries; it did not deploy the fix to the ordinary server.
### Dated live reference validation: 2026-10-11 (run7)
One existing real run7 (2026-10-11) is the retained live evidence dated for this
change: it executed both configured harnesses, OpenCode 2.0.26 and Pi 1.1.0, with
`opencode-go/deepseek-v4.1-flash` stages on the Docker server, and both steps
succeeded (6s; the retained Pi evidence panel reports 1054/10000 tokens). The
captures are retained at `tmp/friend-ui-verification/source-pi-80-*` and
`source-pi-120-*`, and a current-source TUI inspection of that run recorded actual
80x30 and 120x36 renderings, including the run graph and the bounded evidence
panel.
This is a single real run, **not** a fresh full reference suite. Other providers,
real outages/long-stream interruption, fresh OAuth and phone delivery remain
**not tested**; the new-source installer and installed-authoring verification were
separately completed by the dated 2026-10-11 FINAL INSTALLED section above. The
[2026-10-10 OpenCode v2.0.20 trial](#dated-live-reference-validation-2026-10-10)
above remains dated history.
### Reference suite when explicitly requested
The source checkout's `TestReferenceWorkflowsLive` uses six model stage attempts
plus possible compatibility/format-repair calls. Retries are disabled and stages
have two-minute timeouts. It uses real existing credentials and retains private
`runs.db`, pinned definitions, fixture directories, run/session JSON and report.
The accounting case has a one-token/$0.25 budget; other cases have no spending
limit. Test notifications use a local endpoint, not the configured phone topic.
Live inference requires explicit `PIPELINES_REFERENCE_LIVE=1`, a chosen
`PIPELINES_REFERENCE_MODEL=PROVIDER/MODEL`, and an existing private
`PIPELINES_REFERENCE_DIR`. Get consent for chargeable inference and confirm which
execution computer/account to use. Ordinary tests skip live inference. Do not
search the repository or run the suite during normal draft authoring.
If the user explicitly asks to run the suite and provides a source checkout:
```sh
PIPELINES_REFERENCE_LIVE=1 \
PIPELINES_REFERENCE_MODEL=PROVIDER/MODEL \
PIPELINES_REFERENCE_DIR=/private/approved/artifacts \
go test ./internal/server -run '^TestReferenceWorkflowsLive$' -count=1 -v -timeout 15m
```
Docker credentials require running the correctly compiled test binary in that
container; do not copy host credentials or publish tests to the normal database.
`TestReferenceDefinitions` checks definitions without inference.
`TestReferenceArtifactsReview` rechecks copied run/fixture evidence without
inference using `PIPELINES_REFERENCE_REVIEW_DIR`; select only cases present in
that artifact directory. Missing cases skip and must not be reported as passed.
### 2026-10-12 run22 success, run23 live CSV fixture and run24 interruption
Source/structural and live-fixture evidence stays separate from runtime
deployment; nothing here is a deployment claim.
- **run22 (structural/source checks, success):** the retained run22 verification
passed its structural/source checks of the scoped template and prompt changes.
- **run23 (live Pi CSV fixture):** a real exact-template Pi CSV run fetched the
official Python `csv` documentation through the conditional official-source
webfetch and implemented CSV parsing with the standard library's `csv.reader`
through an existing shared helper, adding no duplicate preview parser; both the
implementer and reviewer checks actually passed. Root independently verified the
full retained native tool results and protected-file hashes against its saved
baseline, rather than relying on model-written reports.
- **run24 (interrupted, not a pass):** the run24 implementation completed, but its
reviewer ignored the scope instruction and ran a prohibited filesystem-root scan
(`find /`), leaving a process in uninterruptible D-state and stalling Docker
mount/snapshot reads. Root canceled the run, made a consistent SQLite backup
(`integrity ok`), recovered Docker with the supported stop/start path, and
restored the existing ntfy/Pipelines services with the original definitions, run
history, credentials and settings verified unchanged. run24 is retained as
**interrupted**, not a success.
- **run25 (live Pi source-only review):** the reviewer identified duplicated
implementation, a hardcoded special case, suppressed errors and test gaps.
Root inspected retained native calls: only local read/search tools ran, with no
shell/edit/network calls. Original fixture hashes were unchanged; runtime
behavior was explicitly marked untested.
- **run26 (final maintenance review, success):** the scoped plan/implement/review
workflow passed package tests, vet, build and formatting checks. Root inspected
the actual retained outputs and changes. No rendered UI change was claimed.
The scoped prompt guidance asks stages to keep inspection/verification to relevant
repository paths and supported commands; it is a working instruction, **not** an OS
sandbox, and neither fixes Docker VM/disk bugs nor universally enforces tool
boundaries. At these recorded checkpoints the source changes had not been deployed.
Catalog deployment requires a separate check of the running server and its actual
template contents; these observations do not establish publication or deployment.
Other providers and phone delivery remain **not tested** by this record.
### 2026-10-12 final template verification and Docker catalog deployment
The final three-stage template ran as live Pi run27 (verification definition7,
version2) in a fresh disposable CSV fixture. Root inspected full retained native
results: the planner fetched official Python CSV documentation, the implementer
used the standard library through the existing shared parser, and implementer and
reviewer independently ran `python3 checks.py` successfully. Root reran those
checks, verified the protected fixture hashes and planner-owned review criteria,
and confirmed the preview reused the shared parser.
The Docker server was then refreshed from clean source commit
`143f237268dbde2efd6c5ce5722a3e1fd7e08c9c`, retaining OpenCode 2.0.26, Pi 1.1.0
and Node 24.18.1. The running server reported that exact commit and `dirty=false`;
all five served templates matched current source with the saved Pi/model defaults.
A consistent pre-deployment database backup passed integrity checks. Every stored
definition version/source, retained run ID, saved setting, endpoint and provider
credential/account checked by Root was preserved. This record is a documentation
follow-up to that deployed build; it changes no runtime code or template source.
These bounded fixtures establish the observed behavior on this instance, not a
guarantee of every future model review, provider, task or platform. They do not
establish fresh account sign-in or phone notification reception.
## From the skill harness reference
2026-10-10 verification: `scripts/check-pi-rpc.py` checked installed Pi 0.87.1
readiness, metadata/config RPC and **idle** lease cleanup without inference.
Go RPC fixtures cover result/budget/missing-accounting/timeout/format-repair paths;
Node tests cover permission checks. `PIPELINES_PI_LOCAL=1 go test ./internal/stage
-run TestPiInstalledLocalIntegration` also exercised the **installed Pi** against
scripted loopback responses: actual allowed/denied writes, budget exhaustion,
and active-shell cancellation (including no delayed write after cleanup).
The installed-Pi loopback suite also covers isolated deny-all syntax repair with
retained ownership and cumulative usage. The compiled fuzzy picker passed PTY
selection/cancellation; installed Pi catalog discovery/configuration passed with
an unreachable local endpoint and no prompt.
This is integration evidence, not real-provider/model evidence. Active lease-expiry
recovery, web search delivery and fresh interactive Docker Pi setup remain
**not tested**. Pi catalogs exclude ambient provider extensions for parity with
audited stages; compatible custom endpoints can use Pi's private `models.json`.
An isolated built Docker image also passed non-root, network-disabled policy/RPC
readiness and idle lease cleanup, without credentials/mounts or inference.
Codex/Claude
adapters and AI-assisted server guidelines validation remain future work.
2026-10-11 source-level coverage (source-level regressions; the separate dated
2026-10-11 final install is live evidence): the
shared Docker-aware CLI prefix, exact-match client transport rewriting,
Docker-linked `provider-check` dispatch and the `x/term` TTY check have
source-level regression tests (`internal/harness`, `internal/client`,
`internal/cli`). The prefix tests cover the remote-DNS negative
(`127.remote.example` stays unmapped with no probe), IPv4/IPv6/`localhost`
positives, complete `host:port` binding matching (a different service on the same
port, or a family mismatch, does not match), malformed/empty output failing
clearly, multiple bindings under a single probe, and loopback `wss` rejection.
Terminal Pick regression tests use a short deadline so a TTY regression fails
fast rather than hanging. Docker dispatch tests assert `--json` is passed only in
JSON mode while plain text stays readable. Python fixtures cover arbitrary-digit
OpenCode patches (a parsed `2.0.260` is still rejected against an expected
`2.0.26` by exact equality; 260/100 are illustrative valid/future examples, not
verified releases) and reject both raw and canonical reserved homes. Real
in-container `provider-check`/ping confirmation, a compiled PTY run and a real
Docker reconfigure remain **not tested** in this change. These source-level
regressions are not a claim about the deployed image; the separate dated 2026-10-11
FINAL INSTALLED verification recorded that the runtime was actually installed and
used (OpenCode 2.0.26 / Pi 1.1.0 / Node 24.18.1, image
`sha256:1810ab50f3ea3991e7f3548c79250e65a114bb1821eac52efd872b91cf7c3136`, with
both real stages executed in run17 and passed in Root's full host race/vet runs).
Active lease-expiry recovery, web search delivery and fresh interactive Docker Pi
sign-in remain **not tested**.
+5 -3
View File
@@ -37,9 +37,11 @@ error -> #failure
# stage review # stage review
```prompt ```prompt
Independently review the actual change against the original request in Review the actual change against the original request in memory.md, not just
memory.md, not just the implementer's summary: `git diff --stat` first, then the the implementer's summary: start from the server-captured changed files and
changed hunks and only the code around them. Run no test suites. Return `git diff --stat`, then read the per-file diffs and only the code around them.
Judge the checks the implementer reported and name missing coverage; run no
test suites. Return
rejected only for a must-fix problem, giving its location, evidence and fix. rejected only for a must-fix problem, giving its location, evidence and fix.
Otherwise return approved, with any non-blocking notes in the body. Do not edit, Otherwise return approved, with any non-blocking notes in the body. Do not edit,
commit or push. commit or push.
+1 -1
View File
@@ -29,7 +29,7 @@ error -> #failure
# stage check # stage check
```prompt ```prompt
input.md is the previous stage's draft; memory.md holds the original request. input.md holds the original request and the previous stage's draft.
Check the draft against its sources and the request, correct mistakes and gaps, Check the draft against its sources and the request, correct mistakes and gaps,
and return the final text under `# Final` with a short list of corrections. and return the final text under `# Final` with a short list of corrections.
Change nothing. Return blocked if the draft cannot be checked. Change nothing. Return blocked if the draft cannot be checked.
+22 -41
View File
@@ -1,6 +1,6 @@
--- ---
name: Pipelines name: Pipelines
description: Use existing Pipelines workflows to run, inspect, wait, recover and deliver project work. Use only when the work belongs in an existing pipeline; authoring is a separate, explicit task. description: Use existing Pipelines workflows to run, inspect, wait, recover and deliver work, and author definitions when the user explicitly asks.
--- ---
# Pipelines # Pipelines
@@ -34,63 +34,44 @@ explain the gap; ask before authoring. Do not add a task-specific pipeline as a
## Authoring ## Authoring
A definition is Markdown: `# stage <Name>` sections with `prompt`, `configs`, Start from `pipelines templates` and `pipelines new NAME --template KEY`
`tools`, `edges`, and `limits`/`checks` where required: every stage that can (`one-stage`, `two-stages`, `feedback-loop`, `human-decision`); these fill in
modify the workspace declares `checks` (commands on the `delivery=true` stage, the server's provider/model. Read `references/format.md` and
otherwise `none: <reason>`), and every loop has `limits`. Start from `references/practices.md` before writing prompts. Stage names: `plan` ·
`examples/` and read `references/practices.md` before writing prompts. Use stage `implement` · `review` · `ui-review` · `decide` (human) · `land`.
names that describe the work:
`Plan` · `Code` · `Review` · `UIReview` · `Land` (`Prepare` and `Survey` are
useful variants).
Keep prompts short and objective: what the stage should produce and any real Keep prompts short and objective: what the stage should produce and any real
constraints. The runner enforces turns, tools and limits; prompts do not need to constraints. The runner enforces turns, tools and limits and explains the output
repeat them. Only `# outcome` is parsed from `output.md`; everything else is format; prompts do not repeat them. Only `# outcome` is parsed from `output.md`;
free markdown. Use `links` and `memory` only when they clarify a handoff. everything else is free markdown. There are no memory, links, input or output
blocks; stages communicate through `output.md` (`# handoff`) and `public/`.
`pipelines validate DRAFT` checks a draft, including the authoring rules in `pipelines validate DRAFT` checks a draft, including the authoring rules
`references/practices.md` (errors block submit; `warning:` lines do not but should (errors block submit; `warning:` lines do not but should be fixed);
be fixed); `pipelines submit DRAFT` publishes a new immutable version. `pipelines submit DRAFT` publishes a new immutable version.
`pipelines help <command>` has flags. `pipelines help <command>` has flags.
Schedules are separate saved run configurations: pipeline/version, prompt,
workspace and other run options, plus timing. Never add `# settings` or schedule
blocks to a workflow to arrange recurring work. One generic pipeline can have
many independent topics and timers. Read `references/schedules.md` when the user
explicitly asks to manage a schedule; scheduling alone is not workflow authoring.
## Turns and artifacts
Each visit has `input.md` (the run prompt; later visits add the previous body), `memory.md`
(short essential memory inlined in the prompt: task, previous stage's `# handoff`,
outcome ledger, changed files; 4 KB cap), `history.md` (completed turns in full,
read on demand), `output.md`, and `private/`. Every run also has one shared
`public/` directory, addressed by its absolute path; files there are visible to
later stages and are the stage's real artifacts. `input.md`, `memory.md`,
`history.md`, `output.md` and `session.html` are system evidence for auditing, not stage
output.
## References ## References
Read only what the task needs: Read only what the task needs. Rows marked operator only are for setting up or
debugging the server; skip them when authoring.
| Need | Reference | | Need | Reference |
| --- | --- | | --- | --- |
| Definition syntax and turn files | `references/format.md` | | Definition syntax, turn files, output.md, checks, landing | `references/format.md` |
| Good practices (tokens, checks, prompts, loops) | `references/practices.md` | | Good practices (tokens, checks, prompts, loops) | `references/practices.md` |
| Limits, tools and permissions | `references/control.md` | | Loop limits | `references/control.md` |
| Stages, parallel work, recovery | `references/orchestration.md` | | Stages, parallel work, recovery | `references/orchestration.md` |
| CLI, storage and evidence | `references/operations.md` | | Verification and evidence | `references/verification.md` |
| Verification and accounting | `references/verification.md` |
| Failures | `references/debugging.md` | | Failures | `references/debugging.md` |
| Delivery and installation | `references/delivery.md` | | Delivery and installation | `references/delivery.md` |
| Harnesses and models | `references/harnesses.md` |
| Notifications | `references/notifications.md` | | Notifications | `references/notifications.md` |
| Independent saved run schedules | `references/schedules.md` | | Saved run schedules (never in a definition) | `references/schedules.md` |
| Transfer and versions | `references/transfer.md` | | Transfer and versions | `references/transfer.md` |
| Hosting, auth and deployment | `references/access.md` |
| Queue and work items | `references/work.md`, `references/queue.md` | | Queue and work items | `references/work.md`, `references/queue.md` |
| CLI, storage and run evidence (operator only; not needed for authoring) | `references/operations.md` |
| Harnesses and models (operator only) | `references/harnesses.md` |
| Hosting, auth and deployment (operator only) | `references/access.md` |
Ask about real ambiguity, destructive actions or changes outside the request; Ask about real ambiguity, destructive actions or changes outside the request;
routine steps of an authorized task do not need another confirmation. routine steps of an authorized task do not need another confirmation.
+36 -47
View File
@@ -1,11 +1,16 @@
# Runner-owned limits and stage memory # Runner-owned limits and loops
Use these blocks for bounded feedback loops. Never ask a model to count visits, Use `limits` for bounded feedback loops. Never ask a model to count visits,
increment revision counters, or enforce retry caps. Model verdicts concern current increment revision counters or enforce retry caps; the runner counts actual
work only. Counters are runner audit data, not model input. A fresh session alone visits. Model verdicts concern the current work only.
does not guarantee independent review: explicitly select its input fields.
Put the cap on the reviewer, and leave the loop target without `limits` (it then
has the runner's default of five visits) or give it a cap at least as large as the
reviewer's:
````markdown ````markdown
# stage review
```limits ```limits
{"max_visits":3,"on":["rejected"]} {"max_visits":3,"on":["rejected"]}
``` ```
@@ -18,48 +23,32 @@ error -> #failure
``` ```
```` ````
These blocks accompany a normal review stage's prompt/tools/configs. These blocks accompany the stage's normal prompt, tools, checks and configs.
Pipelines counts actual visits, ignoring model-generated counters. On visit three, Semantics (`internal/server/runner.go`):
`approved` can succeed; `rejected` retains its verdict but routes to `#failure`.
`rejected` is for a must-fix finding with a concrete location, evidence and remedy;
`advisory` carries non-blocking notes and continues the run without another
implementer visit, so an advisory-only review never buys a full re-implementation.
An implementer may likewise declare `blocked_retryable -> implementer` for a
transient environment, tooling or device problem a fresh attempt could survive,
keeping `blocked -> #failure` for an acceptance criterion that genuinely cannot be
met. `max_visits` caps every visit of that stage, including re-entries from the
reviewer's `rejected` edge, so an implementer that is also the rejection target must
use a cap at least as large as the reviewer's budget; the published pipelines use
`{"max_visits":5,"on":["blocked_retryable"]}`. A lower implementer cap stops the loop
before the reviewer's own cap fires, making the reviewer's `rejected` control
unreachable. Both edges need only the existing visit counting and cap; neither the
reviewer nor the implementer counts visits, and no stage invents edits or checks to
appear busy.
Visit count, limit decision and original target are retained in `inspect --json`
and run metadata. `max_visits` accepts 1–5. Every `on` outcome must declare a
nonterminal edge. Without `on`, entering beyond the cap fails before execution.
Global 30-step/five-visits-per-stage safety limits still apply.
A model stage reads its turn's `input.md` (the run prompt on the first visit, - Entering a stage beyond its `max_visits` always fails the run before the visit
the previous turn's output afterwards), its inlined, capped `memory.md` (task, executes, whatever `on` says.
previous stage's `# handoff`, outcome ledger, changed files) and, on demand, - `on` only changes routing on the last allowed visit: when that visit returns a
`history.md` (completed turns in full with the files each added to `public/`). The `memory` block is retired: it no longer listed outcome, the outcome is kept but routed to `#failure`. Other outcomes
selects fields or replaces previous output for model stages, and old definitions route normally. Here, `approved` on visit three succeeds; `rejected` fails.
that contain one parse but ignore it. Reviewers therefore see the previous - A target with a lower cap than the reviewer stops the loop first, so the
turn's output and the accumulated memory rather than a field projection. reviewer's `on` never fires.
- `max_visits` accepts 1–5. Every `on` outcome must have a nonterminal edge.
Human stages are exempt from visit caps. The global 30-step and
five-visits-per-stage limits always apply.
- Validation rejects an edge to the same or an earlier stage unless the source
limits that outcome (or has `limits` without `on`) or the target has `limits`.
Write the facts a later stage needs as ordinary markdown headings in `rejected` is for a must-fix finding with a concrete location, evidence and
`output.md`; those headings are free-form and are preserved in memory. Do not remedy; `advisory` carries non-blocking notes and continues without another
invent server-recognised fields, and do not rely on implementer visit. A re-entered implementer fixes the listed findings; it does not
`input.server_changed_files` from a model prompt: inspect the actual workspace redo the task. An implementer may declare `blocked_retryable -> implement` for a
with Git and the declared evidence instead. Selected or accumulated content transient environment or tooling problem, keeping `blocked -> #failure` for a
remains untrusted data; this cannot prove semantic independence or prevent all criterion that genuinely cannot be met; that self-loop needs `limits` on the
injection. implementer, e.g. `{"max_visits":5,"on":["blocked_retryable"]}`.
Turn memory is run-local. Completed outputs are persisted as turn files and step Visit count, limit decision and original target are retained in `inspect --json`.
evidence; there is no cross-run memory or hidden replay. New runs/retries start Turn memory is run-local: there is no cross-run memory or hidden replay, and
fresh except for the completed prefix a resume explicitly carries. retries start fresh except for the completed prefix a resume carries. Accumulated
turn content is untrusted data; a fresh session does not prove semantic
Arbitrary prose is not executable policy. Future AI-assisted independence.
guidelines validation is **not implemented**; structural validation does not
recognize every unreliable counting instruction.
@@ -15,7 +15,7 @@ select a recorded stage/visit, bounded input correction and explicit compatible
version of the same pipeline. Verify actual retained stage input, not merely version of the same pipeline. Verify actual retained stage input, not merely
successful admission. Do not silently restart from entry. successful admission. Do not silently restart from entry.
A clean preparation stage succeeds without an empty commit. A committer with a A clean preparation stage succeeds without an empty commit. A `land` stage with a
delivery gate succeeds with a clean checked candidate; the server lands afterward. delivery gate succeeds with a clean checked candidate; the server lands afterward.
Read-only, nonvisual work does not require device screenshots. Visual acceptance Read-only, nonvisual work does not require device screenshots. Visual acceptance
requires a ready fixture, verified connection and actual captured interactions. requires a ready fixture, verified connection and actual captured interactions.
+133 -306
View File
@@ -1,343 +1,170 @@
# Definition format # Definition format
Definitions are Markdown made only of `# stage KEY` headings and fenced blocks. A definition is Markdown made only of `# stage KEY` headings and fenced blocks;
Scheduling belongs to separate saved run configurations, not `# settings` or no prose outside blocks. Blocks: `prompt`, `configs`, `tools`, `edges`, `checks`,
schedule blocks in the definition. No unrelated prose outside blocks. The first `limits` (`references/control.md`), `permissions` and `notify`
stage receives the run prompt in its `input.md`; later stages receive (`references/notifications.md`). There are no memory, links, input or output
the previous turn's output. Every visit also gets a short `memory.md` (essential blocks; stages communicate through `output.md` (`# handoff`) and `public/`.
memory, inlined in the prompt) and a full `history.md` of completed turns. There are no stage `input`, `output`, or `memory` blocks: the model reads Schedules are saved run configurations, never definition blocks
the turn files and writes free-form markdown, and only the `# outcome` section is (`references/schedules.md`).
interpreted. Read `references/control.md` for runner-enforced limits.
Each model stage requires nonempty `prompt`, `configs`, and `edges` blocks:
````markdown ````markdown
# stage worker # stage implement
```prompt ```prompt
Perform the task. Make the change requested in the run task. Run focused checks for the touched
code only. Return blocked if the request cannot be met.
``` ```
```configs ```configs
type=model provider=default
provider=opencode-go model=default
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: publishing rejects an edge to the same or an earlier stage
(definition order) unless the source stage limits that outcome or the target
stage has `limits` (a human stage's choices are exempt). Read
`references/control.md` for the exact format.
## Checks
Every model stage that can modify the workspace (it declares `edit` or `shell`,
has no `tools` block, or sets `delivery=true`) must declare a `checks` block, so
the author decides where verification happens. Read-only stages need none.
- A `delivery=true` stage lists 1–20 commands, one per line. The server runs them
on the committed candidate (and again on a merged tree) before landing; a
failing command blocks landing. These are the run's deterministic checks.
- Every other stage writes exactly one line, `none: <reason>`, naming where
verification happens instead, for example
`none: focused tests only; the Land delivery gate runs the suite` or
`none: read-only review; shell is used only for git diff`. Commands on a
non-delivery stage are rejected because nothing would run them.
A check must fail when it cannot run. Validation rejects guards that pass
without running anything: `|| true`, `|| :`, `|| exit 0`, `|| echo`,
`[ ! -x tool ] || ...`, `test ! -f ... || ...`, `! command -v tool || ...`,
an `if ...; then ...; fi` with no failing else, and `set +e`. Cover every
language the run can change (a Go-only check list does not verify Flutter work).
`pipelines validate` reports these with the remaining authoring rules
(`references/practices.md`).
## Result format
Each visit gets `input.md`, `memory.md`, `history.md`, `output.md` and
`private/` in `<run>/stages/<seq>-<stage>/`, plus the run-level shared
`public/`. What a stage receives:
- `memory.md` (essential, hard cap 4 KB, always inlined in the prompt): the run
task, the previous stage's handoff with its outcome and public/ additions, a
one-line-per-stage outcome ledger (latest visit; a revisit is marked) and the
server-captured changed files. A stage must be able to work from this alone.
- `input.md` (on demand): the full run task and the previous turn's full output.
- `history.md` (on demand, never inlined): every completed turn in full, the
format `memory.md` had before essential memory existed.
Stages with `read` are told the two on-demand paths; stages without it get
`input.md` inlined too (capped at 32 KB) but never `history.md`.
The previous stage's handoff is its `# handoff` section (any level, up to the
next heading of the same or higher level); without one the server uses the head
of its output, marked as such. Either is truncated to fit with a pointer to
`input.md`, so nothing depends on the model following the convention. The
prompt asks every stage to start its output with a short handoff: what it did,
files changed, open issues or findings. The only required section is the
outcome heading, followed by one of the stage's declared edge words:
````markdown
# handoff
Fixed both review findings in cache.go; tests pass. No open issues.
# outcome
success
# Result
Free-form markdown for the next stage and the operator.
````
`internal/turn.ParseOutput` matches the heading case-insensitively at any ATX
level and ignores headings or words inside fenced code blocks. A missing,
duplicate, empty or undeclared outcome fails the stage with
`FINAL RESULT VALIDATION`. Every other heading is uninterpreted and preserved
verbatim in the body. There is no JSON envelope, output schema, field selection
or format-repair pass: do not ask for JSON fields or invent server sections.
Keep turn-local files in `private/`; put reports, logs and screenshots for later
stages in `public/`. Never fabricate a result.
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`.
A stage that declares a `skipped` edge (for example a UI reviewer) is eligible
for the server skip fallback: when every earlier visit's file-change capture was
complete and recorded no changed files or screenshots, the server completes the
stage as `skipped` without a model call (`reason_source: fallback`). Any recorded
change or incomplete capture runs the model. Optional `auto_skip=false` (values
`true`/`false`, default `true`) always runs the model. Read
`references/operations.md` ("Server skip fallback") for the exact rule.
Optional `reasoning_effort=high` selects a model's reasoning/thinking level for
this stage. Values are `default`, `none` (alias `off`), `minimal`, `low`, `medium`,
`high`, `xhigh`, or `max`. Omission or `default` preserves the harness/model
default; never add a level automatically to existing workflows. Availability is
model-specific: OpenCode V2 selects the corresponding named model variant and
rejects unavailable variants; Pi uses its native thinking level (`none` becomes
`off`) and verifies the effective level before prompting, rejecting unsupported
or silently clamped levels. Explicit effort on OpenCode V1 is unsupported.
Do not instruct the agent to “think harder” as a substitute for this native
setting. Effort is not a token budget or a guaranteed quality improvement; keep
usage budgets/provider spending limits separate. Both text-only and tool-using
model stages honor the setting, without changing their tools or permissions.
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 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, all 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. The intended role split: an implementer may
read/glob/grep/edit/shell; a planner reads, plus conditional web search/fetch only
when external knowledge is needed; a reviewer reads and may run read-only checks
with shell but never edits; 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. The bundled examples (`one-stage`, `two-stages`, `feedback-loop`,
`human-decision`) follow it without web tools. 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.
````markdown
# stage gate
```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:
````markdown
# stage committer
```prompt
Commit this run's change locally; never push.
``` ```
```tools ```tools
read read
glob glob
grep grep
edit
shell shell
``` ```
```checks ```checks
none: commits locally; the manager lands and runs the suite none: focused tests only; the land delivery gate runs the suite
``` ```
```edges ```edges
success -> #success success -> review
blocked -> #failure blocked -> #failure
error -> #failure error -> #failure
``` ```
```` ````
A landing committer instead sets `delivery=true` in `configs` and lists the Stage and outcome keys begin with a letter and contain letters, digits, `_` or
repository's required check commands in `checks`; the server runs them, so its `-`. Name roles `plan`, `implement`, `review`, `ui-review`, `decide` (human) and
prompt does not run the suite again. `land`; other jobs take a plain verb (`draft`, `check`, `act`). Each outcome has exactly one target: another
stage, `#success` or `#failure`. An omitted `error` edge defaults to `#failure`
for every stage type, human included. Execution is sequential; an outcome picks
one edge, never parallel branches. Every stage must be reachable from the entry
and have a path to a terminal; loops need runner-owned `limits`.
State this pre-commit checklist in the prompt: ## Turn files
1. Inspect `git status` and the full diff. Stage this run's change, including Each visit gets `input.md`, `memory.md`, `history.md`, `output.md` and `private/`
inherited work, restricted to paths that still exist, and keep every in `<run>/stages/<seq>-<stage>/`, plus the run-level shared `public/` addressed by
exclusion. Do not rely on a model-declared file list. its absolute path.
2. Inspect the staged diff before committing; never commit unrelated work, secrets
or generated artifacts.
3. Without a delivery gate, run the repository's required checks once (summary
output) 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. With `delivery=true` the server runs the `checks` block; skip this step.
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.
6. Ensure the item's per-item documentation note (`docs/notes/<slug>.md`, written when
the change makes a shared document stale) is staged with the change. Never edit a
shared document (a README or topic doc, or a packaged skill reference) here: a single
documentation writer folds notes later (`references/orchestration.md`). An item that
staled no shared document has no note and needs no step 6.
This list is the canonical checklist. Repeat it in each committer prompt, because a - `memory.md` (capped at 4 KB, always inlined in the prompt): the run task, the
definition is published on its own; keep those copies in sync with this list. The previous stage's `# handoff` with its outcome and `public/` additions, a
bundled examples leave changes uncommitted and have no committer. one-line-per-stage outcome ledger and the server-captured changed files.
- `input.md`: the run task, plus on later turns the previous turn's full output
(`internal/turn/render.go`). A stage with `read` reads it on demand; a stage
without `read` gets it inlined (up to 32 KB) on every call, so give `read` to
stages that follow a large output.
- `history.md`: every completed turn in full; on demand for stages with `read`,
never inlined.
The committer prepares the complete clean candidate and resolves integration conflicts. Keep turn-local files in `private/`; put reports, logs and screenshots for later
When `delivery=true`, the server executes the declared checks and lands after the stages in `public/`. `input.md`, `memory.md`, `history.md`, `output.md` and
stage returns success; do not run the post-landing ancestry check beforehand. `session.html` are server-written evidence, not stage output.
If canonical `main` moved meanwhile, the server merges it into the item (a normal
merge commit), re-runs the checks on the merged tree and lands that; a conflicting
catch-up is aborted with the workspace unchanged and the conflicting files named.
Without a delivery gate, the original workflow or manager completes the merge
and verifies ancestry. No separate merger pipeline is required (`references/queue.md`).
A stage returns the markdown above, never the retired ## output.md
`{ "outcome": ..., "output": ... }` envelope. Do not treat tool-call/DSML markup,
plain prose, or a missing outcome as success, and never rerun tool work merely to
fix a response's formatting.
## Scheduling The stage returns the complete `output.md` in this order: `# outcome`, the edge
word alone on the next non-blank line, then `# handoff` (a few lines: what it did,
files changed, open findings), then any detail:
Publishing a workflow does not schedule it. Create a separate saved schedule ````markdown
with an explicit pipeline/version and complete run information (prompt, server # outcome
workspace, model overrides, notifications, output format and write restrictions
when used). Multiple saved schedules can reuse one workflow with different
research items or timers; updates and deletion do not rewrite the definition.
Use exactly one timing rule: `times` (24-hour clock values) or `every` (a duration
of at least one minute), with optional weekdays and timezone.
New definitions with embedded schedules are rejected. Historical immutable success
versions remain readable; their latest legacy slots migrate into separate saved
schedules without changing source/history or replaying old occurrences. Never
reintroduce legacy scheduling blocks or make a new workflow just to set another
topic/timer. Warn explicitly before enabling unattended runs. See
`references/schedules.md` for the API and retry/concurrency guards.
## Notifications # handoff
Stage hooks use the global phone connection, never store credentials. Optional Fixed both review findings in cache.go; focused tests pass. No open issues.
fenced `notify` block: `on=success,failure` (add `waiting` to fire when a human
stage parks the run), `artifacts=markdown`. Free-form detail for the operator and later stages.
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 outcome heading matches case-insensitively at any ATX level, outside fenced
the user's repository for Pipelines docs. Bundled examples are generic and manual-only. code. Never add a second heading named Outcome. If the outcome is missing, the
Notification attachment/report support and model availability need real runtime runner sends one repair follow-up asking only for it; a still-missing, duplicate,
tests; structural validation alone cannot confirm delivery. empty or undeclared outcome fails with `FINAL RESULT VALIDATION`. Every other
heading is free-form and preserved. The handoff is the `# handoff` section (or,
without one, the head of the output, marked as such), truncated to fit memory.
The `{ "outcome": ..., "output": ... }` JSON envelope and its format-repair ladder
are retired: never ask for JSON fields or invent server sections. Missing tools or
evidence route to `blocked` when declared, else `error`; never fabricate a result.
## Configs
- `provider`/`model`: exact IDs validated during server setup. Templates
(`pipelines new NAME --template KEY`) fill them in; copy those IDs into a
hand-written draft. Availability needs `pipelines provider-check`.
- `harness=opencode|pi`; omission means OpenCode (`references/harnesses.md`).
- `retries` 0–100, default 2 (three attempts). Retries cover transport failures
and timeouts; a stage with `edit`/`shell` (or no tools block) never replays
admitted work.
- `timeout` per attempt, default `1h` (e.g. `30m`, `90s`).
- `reasoning_effort`: `default`, `none` (`off`), `minimal`, `low`, `medium`,
`high`, `xhigh`, `max`. Omit unless asked; unsupported levels are rejected.
Do not prompt "think harder" instead.
- `budget_usd`, `budget_tokens`: positive caps on reported usage, shared across
attempts and visits of this stage; totals include cache reads and writes. Set
only when the user asks or a measured visit exists (`references/practices.md`).
- `delivery=true`: the landing stage's gate (below). OpenCode harness only.
- `auto_skip=false`: disable the server skip fallback for a stage that declares a
`skipped` edge (`references/operations.md`, Server skip fallback).
## Tools and permissions
`tools` lists `read`, `glob`, `grep`, `webfetch`, `websearch`, `edit`, `shell`,
one per line; an empty block denies all and a missing block grants local
read/glob/grep/edit/shell (prefer explicit). Roles: `plan` reads (web only when
external knowledge is needed); `implement` reads, edits and runs shell; `review`
reads and may use shell for `git diff`, never edits; `land` has read/glob/grep and
shell, no edit. Planning stages do not return `blocked` merely because edits come
later. Keep prompts language-neutral unless the task names a language.
Optional `permissions` is a JSON object with `edit` (run-directory-relative
patterns) and `shell` (exact commands) arrays. It narrows declared tools; it never
enables a missing one. Empty arrays deny; wildcards, chaining, redirects and
traversal are rejected. With restricted edits and shell enabled, list shell too:
`{"edit":["README.md","plugin/*.qml"],"shell":["bash -n install.sh"]}`.
## Checks
Every model stage that can modify the workspace (`edit` or `shell`, no `tools`
block, or `delivery=true`) declares `checks`. A `delivery=true` stage lists 1–20
commands, one per line. Every other stage writes exactly one line,
`none: <reason>`, e.g. `none: read-only review; shell is used only for git diff`.
A check must fail when it cannot run: validation rejects `|| true`, `|| :`,
`|| exit 0`, `|| echo`, negated file tests, `! command -v tool ||`, an `if` with no
failing else, and `set +e`. Cover every language the run can change.
## Human stages
`type=human` pauses the run until a person picks one of its non-`error` edges
(e.g. `approve -> act`, `revise -> plan`, `abort -> #failure`; see the
`human-decision` template). It needs only `prompt` (operator instructions),
`configs` with `type=human` and `edges`; no model or tools. Decide with
`pipelines decide RUN_ID [STAGE] --option KEY [--feedback TEXT]` or the apps. The
wait survives restarts and is never killed by a stage timeout or `max_visits`.
## Land stage and delivery gate
A workflow that commits its change ends in `land`: a model stage with
`read`/`glob`/`grep`/`shell`, no `edit`, that commits locally. Its prompt states:
1. Commit only this run's changes (server list + git status).
2. Check the staged diff for unrelated work and secrets.
3. No empty commit, push, amend or rebase. Report the hash.
With `delivery=true` and `checks` commands, after `land` succeeds the server:
requires the item and main checkouts to be clean, untracked files included; merges
a moved `main` into the item (a conflict aborts with the workspace unchanged);
runs each check with `sh -c` from the root of a fresh detached worktree of the
commit, so include dependency bootstrap (`npm ci && npm test`); caps each check's
output at 64 KB; and fast-forwards `main`. A failing check blocks landing. Do not
check ancestry before the gate runs. Without a gate, the manager merges and
verifies ancestry; no separate merger pipeline is needed (`references/queue.md`).
+34 -180
View File
@@ -1,191 +1,45 @@
# Configured harnesses # Configured harnesses (operator only)
Current source supports OpenCode and Pi interactive authoring, debugging and Authoring needs only the `harness=` config (`references/format.md`). The rest is
model stages. nvim remains a file editor/read-only debug packet viewer, not a for an operator setting up or debugging the execution computer.
stage backend. Only configured harnesses appear in TUI pickers, default first.
CLI `new/edit/debug --harness opencode|pi|nvim` overrides the default. OpenCode and Pi run interactive authoring, debugging and model stages; Claude Code
and Codex are chat backends. nvim is a file editor/read-only debug packet viewer,
not a stage backend. Only configured harnesses appear in pickers, default first.
CLI `new/edit/debug --harness opencode|pi|nvim` overrides the default, and
`pipelines harness` launches the configured default in the invocation directory. `pipelines harness` launches the configured default in the invocation directory.
CLI `new/edit/debug` and TUI author/debug build one shared, Docker-aware CLI
prefix. A Docker-linked profile embeds the in-container `/usr/local/bin/pipelines`
(never the host binary: Linux can see but cannot execute a mounted macOS host
executable). Loopback is recognized only via `net.ParseIP(...).IsLoopback()` plus
an exact case-insensitive `localhost`, so a remote DNS name such as
`127.remote.example` stays remote and runs no probe. For a loopback logical
`--url`, a single bounded `docker compose port` probe parses each returned line
as a complete `host:port` binding (IPv4/IPv6/wildcard) and the prefix maps only
when a binding covers the requested loopback address and port; malformed or
non-matching bindings fail closed. A loopback `wss` endpoint is rejected as
having no supported local TLS mapping rather than downgraded to plaintext. On a
match it embeds scoped `PIPELINES_TRANSPORT_SOURCE`/`PIPELINES_TRANSPORT_TARGET`
aliases in the prefix string (not `cmd.Env`, so the pre-existing harness
server's tools inherit them). The client rewrites an endpoint only on an exact
source match; remote endpoints stay remote. Draft metadata (server, base
version, create-only guard) is preserved unchanged.
`provider-check` with a Docker-linked profile runs inside that profile's existing
Compose service with `-T`, the original cwd/model/timeout and exact stdout/exit
propagation; container profiles have no `DockerDirectory` and cannot recurse, and
explicit native profiles keep the host path. The picker uses a true `x/term` TTY
check, so `/dev/null` and pipes fail fast instead of hanging.
`pipelines harness setup <claude|codex|opencode|pi>` is the single setup path on `pipelines harness setup <claude|codex|opencode|pi>` is the single setup path on
native and Docker installations: it checks the CLI is reachable from the server native and Docker installations: it checks the CLI is reachable from the server
(printing the install command when missing), signs in only when needed (`--login` (printing the install command when missing), signs in only when needed (`--login`
forces it) and verifies with the server's own check. Claude Code and Codex have forces it) and verifies with the server's own check. For OpenCode/Pi it picks the
no models to pick. For OpenCode/Pi it runs a styled onboarding interactive harness model and the new-pipeline model; automation passes
wizard (bold title, verified Docker harness versions) and selects separate `--model PROVIDER/MODEL --pipeline-model PROVIDER/MODEL`, and a non-terminal run
harness and new-pipeline models using type-to-filter fuzzy pickers, not numbered with a missing model fails instead of opening a picker. `harness default
prompts. Each picker itself shows its numbered step with the title and purpose [opencode|pi]` switches defaults; `harness list` shows installed / signed-in /
(no duplicate numbered prose is printed outside it); the interactive harness configured / default status (`--json` adds profiles). Setup reads catalogs and
model is `Step 1 of 2` and the new-pipeline model is `Step 2 of 2`, matching login state without inference. Changing defaults never rewrites published
fresh Docker setup. Typing filters, arrow keys or Tab navigate, Enter confirms, definitions or drafts; canceling a picker leaves saved preferences unchanged.
and Esc cancels. The saved value is preselected and marked `(current)`; the window Harness setup/default commands configure the local execution user, not a remote
follows the active row on narrow terminals and the heading, selected row and `--url` server. Pi setup runs no generation check; `provider-check --harness pi
no-match state stay within the real terminal height. --model PROVIDER/MODEL` is a separate, potentially chargeable check.
Automation: `--model PROVIDER/MODEL --pipeline-model PROVIDER/MODEL`.
`harness default [opencode|pi]` switches defaults; `harness list` shows installed /
signed-in / configured / default status for all four (`--json` adds profiles).
Setup reads catalogs/login state without inference. Changing defaults never
rewrites published definitions or retained drafts. Canceling or failing either
picker leaves saved preferences byte-identical. Non-terminal automation with a
missing model fails clearly instead of starting a picker.
On an existing Docker setup, `pipelines harness setup opencode|pi` configures inside its container and link the host Docker image resolution, profile storage, the Docker-aware CLI prefix, Pi sign-in
launcher without restarting/deploying services. They resolve and verify the current and OpenCode V2 settlement internals are in `docs/operator-reference.md` in the
OpenCode V2 release from the single documented complete source checkout; dated verification is in `docs/verification-history.md`.
`GET .../git/matching-refs/tags/v2` response (a bounded complete array with no
pagination parameters; never the moving `latest` tag or the registry's insertion
order) and the current Pi release from npm, resolve the selected tag's immutable
GHCR `sha256` digest, and require a rebuild only when the verified release image
identity no longer matches. A full install always invokes the Docker build for a
dirty source (relying on layer caching); a model/login-only reconfiguration does
not rebuild. Setup writes its generated release receipt to the machine-local root
file `.pipelines-releases.json` (with atomic `.pipelines-releases-*` temporary
files); both are git-ignored, so a fresh clean checkout stays clean and reinstall
still reuses the verified release/image identity. The actual built image's labels
stay authoritative and a dirty source still rebuilds. If discovery, digest
resolution or completeness cannot be established they stop with an error (keeping
the last verified Dockerfile fallback pins); they never guess, fall back to a host
runtime or install a stale pin.
(`./install --opencode`/`--pi` were removed and only point to that command.) The native installation reuses the host OpenCode
configuration, writes **host** (non-Docker) profiles for the harnesses it detects
into XDG config home's `pipelines/harnesses.json`, and clears a stale Docker link
so a Docker-era profile is not left Docker-linked. It never installs, upgrades or
downloads a harness. Container and host credentials and accounts remain independent and
are reused on reinstall/reconfigure. `./install` installs natively by default
(`--native` is equivalent); explicit `./install --docker` selects the Docker
server + ntfy installation.
Fresh setup accepts `./install --docker --harness pi` to skip OpenCode
login. Existing setup can configure either harness independently. Pi setup does
not run a generation check; `provider-check --harness pi --model PROVIDER/MODEL`
is a separate confirmed, potentially chargeable check.
Profiles live in XDG config home's `pipelines/harnesses.json`, store preferences
only, and preserve unrelated configuration. A profile launches a native host
harness unless it records a Docker checkout directory, in which case it launches
through that installation's Compose service. `harness setup <opencode|pi> --host`
configures or converts a host profile and clears any Docker link; without
`--host`, reconfiguring a Docker-linked profile re-verifies that the recorded
directory still has `compose.yaml` and fails naming it rather than saving a link
that cannot launch. Setup's summary and `harness list` report the resulting mode
(and, for Docker, the directory). Harness CLI setup/default commands
always configure the local execution user, not a remote `--url` server.
OpenCode interactive launch uses
`mini --model`: verified V2 full CLI lacks a model flag. Pi uses its CLI with the
packaged skill explicitly loaded. Pi has no standalone `auth login` command
(verified `pi auth --help`: only credential check/print): setup prints a
title-plus-three-lines Pi sign-in handoff and opens a fresh, no-context,
extension-free, no-prompt-templates, no-tools session with Pi's documented
`--tui-mode regular` flag, so the header and handoff stay visible above Pi's
interface at 80x30 instead of the default fullscreen clear. The user types
`/login`, chooses an authentication method ("Sign in with an API key" for
provider API credentials; account and Radius remain the user's choice), finishes
provider sign-in, then exits with `ctrl+c`/`ctrl+d` to return to Pipelines model
configuration. Existing sign-ins are reused by exiting when no new sign-in is
needed; completing a sign-in can update the credentials stored in the Docker
volume. No coding/task prompt or scripted keystrokes are injected.
OpenCode V2 model stages settle long sessions by polling `GET /api/session/active`
about once per second under the stage context, instead of the `.../wait` request
whose CLI-side request timeout failed long stages after roughly six minutes
(HTTP 499, dated 2026-10-10). V1 native settlement is unchanged. Final results
and debug session evidence use the same single bounded latest-assistant readback
(`order=desc&limit=1&type=assistant`), so a small final result is visible behind
large prior tool content; retained transcripts over 32 KiB are stored as valid
bounded preview envelopes that preserve stage limits and diagnostics, and exact
outputs remain authoritative. Pi evidence is JSONL and is not parsed as one JSON
object. Short-lived context-controlled CLI calls (`--help` detection, API calls
and the native export fallback) share one finite inherited-pipe drain grace
(`os/exec.Cmd.WaitDelay` ~250ms) so a canceled context or a descendant that still
holds stdout/stderr cannot block for the child's natural lifetime; the
`context.Canceled`/`DeadlineExceeded` and `exec.ErrWaitDelay` identities are
preserved and partial stdout after the grace is never accepted as success.
Stages set `harness=pi` or `harness=opencode` in configs; omission preserves
historical OpenCode behavior. Pi must be configured on the execution server.
A run may override the pinned model at launch: `pipelines run --model A run may override the pinned model at launch: `pipelines run --model
PROVIDER/MODEL` covers every model stage and repeatable `--stage-model PROVIDER/MODEL` covers every model stage and repeatable `--stage-model
STAGE=PROVIDER/MODEL` overrides one stage, with precedence **per-stage > STAGE=PROVIDER/MODEL` overrides one stage (per-stage > whole-run > pinned).
whole-run > the model pinned in the pipeline version**. Overrides are validated Overrides are validated against the pinned version before the run starts (an
against the pinned version before the run starts (an unknown stage key fails unknown stage key fails naming the valid keys; a non-model stage cannot be
naming the valid keys; a non-model stage cannot be overridden), apply to that run overridden), apply to that run only, and are recorded so `retry` reproduces them.
only, and are recorded on the run so `retry` reproduces them. The effective The effective provider/model is stamped on the step.
provider/model is stamped on the step and exposed by the run's graph, and the
stage's repair/formatter path uses the same resolved model because both read the
stage's effective configs.
The RPC adapter starts new retained sessions per visit with explicit tools and
a Pipelines permission extension. Ambient extensions, skills, context files,
prompt templates, automatic retries/compaction are disabled. Tool gates are not
an OS sandbox: approved shell can have broad side effects. Usage accumulates
across attempts/visits; missing required accounting fails closed. Strict envelope
validation and bounded syntax-only repair never replay tools. A model-driven
repair, when needed, uses a separate deny-all session with retained ownership
and the same cumulative budget. Its output is checked locally for value changes.
Session/RPC audit lives in the execution user's cache under `pipelines/pi-sessions`. Pi stages start a new retained session per visit with explicit tools and a
Ownership persists before prompts. Cleanup waits for settlement; expired leases Pipelines permission extension; ambient extensions, skills, context files, prompt
request abort through the extension. Unconfirmed cleanup blocks continuation/retry. templates, automatic retries and compaction are disabled. Tool gates are not an
OS sandbox: approved shell can have broad side effects. Usage accumulates across
2026-10-10 verification: `scripts/check-pi-rpc.py` checked installed Pi 0.87.1 attempts and visits; missing required accounting fails closed. Session/RPC audit
readiness, metadata/config RPC and **idle** lease cleanup without inference. lives in the execution user's cache under `pipelines/pi-sessions`; unconfirmed
Go RPC fixtures cover result/budget/missing-accounting/timeout/format-repair paths; cleanup blocks continuation and retry.
Node tests cover permission checks. `PIPELINES_PI_LOCAL=1 go test ./internal/stage
-run TestPiInstalledLocalIntegration` also exercised the **installed Pi** against
scripted loopback responses: actual allowed/denied writes, budget exhaustion,
and active-shell cancellation (including no delayed write after cleanup).
The installed-Pi loopback suite also covers isolated deny-all syntax repair with
retained ownership and cumulative usage. The compiled fuzzy picker passed PTY
selection/cancellation; installed Pi catalog discovery/configuration passed with
an unreachable local endpoint and no prompt.
This is integration evidence, not real-provider/model evidence. Active lease-expiry
recovery, web search delivery and fresh interactive Docker Pi setup remain
**not tested**. Pi catalogs exclude ambient provider extensions for parity with
audited stages; compatible custom endpoints can use Pi's private `models.json`.
An isolated built Docker image also passed non-root, network-disabled policy/RPC
readiness and idle lease cleanup, without credentials/mounts or inference.
Codex/Claude
adapters and AI-assisted server guidelines validation remain future work.
2026-10-11 source-level coverage (source-level regressions; the separate dated
2026-10-11 final install is live evidence): the
shared Docker-aware CLI prefix, exact-match client transport rewriting,
Docker-linked `provider-check` dispatch and the `x/term` TTY check have
source-level regression tests (`internal/harness`, `internal/client`,
`internal/cli`). The prefix tests cover the remote-DNS negative
(`127.remote.example` stays unmapped with no probe), IPv4/IPv6/`localhost`
positives, complete `host:port` binding matching (a different service on the same
port, or a family mismatch, does not match), malformed/empty output failing
clearly, multiple bindings under a single probe, and loopback `wss` rejection.
Terminal Pick regression tests use a short deadline so a TTY regression fails
fast rather than hanging. Docker dispatch tests assert `--json` is passed only in
JSON mode while plain text stays readable. Python fixtures cover arbitrary-digit
OpenCode patches (a parsed `2.0.260` is still rejected against an expected
`2.0.26` by exact equality; 260/100 are illustrative valid/future examples, not
verified releases) and reject both raw and canonical reserved homes. Real
in-container `provider-check`/ping confirmation, a compiled PTY run and a real
Docker reconfigure remain **not tested** in this change. These source-level
regressions are not a claim about the deployed image; the separate dated 2026-10-11
FINAL INSTALLED verification recorded that the runtime was actually installed and
used (OpenCode 2.0.26 / Pi 1.1.0 / Node 24.18.1, image
`sha256:1810ab50f3ea3991e7f3548c79250e65a114bb1821eac52efd872b91cf7c3136`, with
both real stages executed in run17 and passed in Root's full host race/vet runs).
Active lease-expiry recovery, web search delivery and fresh interactive Docker Pi
sign-in remain **not tested**.
+16 -227
View File
@@ -38,23 +38,6 @@ parallel/distributed task engine or a guarantee that model reports are correct.
- Services are native or Docker-based. With an existing Docker installation do not - Services are native or Docker-based. With an existing Docker installation do not
start a competing native server. Server APIs are unauthenticated: trusted networks start a competing native server. Server APIs are unauthenticated: trusted networks
only; never recommend public exposure. Tool scope is not a universal OS sandbox. only; never recommend public exposure. Tool scope is not a universal OS sandbox.
- Docker setup resolves the current supported OpenCode V2 release from the single
documented complete `GET .../git/matching-refs/tags/v2` response (a bounded
complete array with no pagination parameters; never the moving `latest` tag or
the registry's insertion order) and the current Pi release from npm, resolves the
selected tag's immutable GHCR `sha256` digest, builds `FROM` that digest, and
verifies the built image reports exactly those executable versions plus a
Node-compatible Pi engine.
It fails closed, keeping the last verified Dockerfile fallback pins, when discovery,
digest resolution, completeness, build or compatibility cannot be established: never
a hardcoded fallback, never a silent stale-pin substitution. A full install skips a
rebuild only when the release receipt **and** the actual built image's release and
source identity labels already match; a dirty source always invokes the Docker
build and relies on layer caching. A model/login-only reconfiguration compares only
the verified release image identity, so a changed source alone does not rebuild.
`pipelines harness setup opencode|pi` reconfigures inside the existing container and
refuses an image that does not match; it does not rebuild or restart services (an
explicit ordinary `./install` does when the user asks).
## Where data lives ## Where data lives
@@ -72,7 +55,6 @@ delete databases, sessions, volumes or credentials to repair a workflow.
Use the authoritative `CLI_PREFIX` from the prompt: Use the authoritative `CLI_PREFIX` from the prompt:
- `CLI_PREFIX runs --json`: run history (optional `--pipeline NAME` scope).
- `CLI_PREFIX search QUERY [--type KIND] [--limit N] --json`: one read-only query - `CLI_PREFIX search QUERY [--type KIND] [--limit N] --json`: one read-only query
across pipelines, versions, runs, steps, field text and artifacts. QUERY is free across pipelines, versions, runs, steps, field text and artifacts. QUERY is free
text, a bare status word (`queued`/`running`/`succeeded`/`failed`/`canceled`/ text, a bare status word (`queued`/`running`/`succeeded`/`failed`/`canceled`/
@@ -112,17 +94,7 @@ Use the authoritative `CLI_PREFIX` from the prompt:
limits, failure/format diagnostics and the retained session pointer), not the limits, failure/format diagnostics and the retained session pointer), not the
complete tool history. complete tool history.
- `CLI_PREFIX decide RUN_ID [STAGE] --option KEY [--feedback TEXT] [--json]`: answer - `CLI_PREFIX decide RUN_ID [STAGE] --option KEY [--feedback TEXT] [--json]`: answer
a run that is `waiting` on a `type=human` stage. The status and the stage's a run `waiting` on a `type=human` stage (`references/format.md`).
instructions/options are visible in `runs` and `inspect --json` (and the TUI
picker); the stage is inferred from the run's current stage unless named. The
choice and feedback are recorded as the step's evidence (its output and derived
verdict; the feedback is never an error diagnostic) and the run resumes along
`edges[KEY]`. An unknown option is
refused with the valid list; a stage that is not waiting is refused; a repeated
decision for an already-decided visit does not double-apply. The wait is persisted,
so `decide` still works after a server restart. `cancel` and `retry` keep working
while waiting and after a decision; a human stage is never killed by a stage
timeout or `max_visits` (the shared 30-step run budget still applies).
- `CLI_PREFIX run ... --json --wait --wait-timeout DURATION`: `--wait` polls until - `CLI_PREFIX run ... --json --wait --wait-timeout DURATION`: `--wait` polls until
terminal and `--wait-timeout` bounds only the client wait after admission, terminal and `--wait-timeout` bounds only the client wait after admission,
independent of per-request `--timeout`. A reached wait limit leaves the admitted run independent of per-request `--timeout`. A reached wait limit leaves the admitted run
@@ -160,22 +132,6 @@ runs natively through `./install` by default (`scripts/setup-native.py`, with
`--native` equivalent); the Docker server + ntfy installation is explicit with `--native` equivalent); the Docker server + ntfy installation is explicit with
`./install --docker`. `./install --docker`.
In the TUI, Home advertises `/` omni search and `:` commands. Home `/` opens one
popup over pipelines, versions, runs, steps/visits, artifact names and stage
input/output/evidence text; each row shows a short type badge and a text match
shows a bracketed snippet, and a bare status word or date selects runs. The same
query is available as `pipelines search QUERY [--type KIND]`, where `--type`
narrows the kind. Run Tab switches only
Details ↔ Graph. `n/p` select recorded visits, including repeated stages; `d`
focuses/toggles file changes, `A` opens the run's grouped artifacts view (name,
content type, size and URL per entry, `PgUp`/`PgDn` scroll so a trailing visit
that recorded none stays reachable, `Enter`/`o` to open the selected URL and
`y` to copy it), `a` selects the active/latest retained
configured-harness agent session's bounded, redacted tool evidence, `D`/`:debug`
opens fresh investigation, and `P` opens the pinned pipeline version. `:quit`
exits; `q` does not. Results are retained reports, not independently confirmed
achievements. Distinguish partial output from full success.
## Retained stage file changes ## Retained stage file changes
Each newly executed visit compares a bounded, read-only workspace snapshot just Each newly executed visit compares a bounded, read-only workspace snapshot just
@@ -228,18 +184,11 @@ file diffs: current capture is server-owned. Do not promise full files/rollback.
## Retained stage artifacts ## Retained stage artifacts
Every model visit gets a file-based turn under the data directory Turn files (`input.md`, `memory.md`, `history.md`, `output.md`, `private/`) and
(`<data>/artifacts/<run>/stages/<seq>-<stage>/`) with `input.md`, `memory.md` the run-level `public/` are described in `references/format.md`. They live under
(capped essential memory, inlined), `history.md` (full earlier turns, read on `<data>/artifacts/<run>/stages/<seq>-<stage>/`; the root is configurable and
demand), `output.md` and `private/`; `public/` is run-level and shared by every stage. defaults next to the database. The server owns `input.md`, `memory.md`,
The root is configurable and defaults next to the database. The writable `history.md` and `output.md`.
`private/` and shared `public/` directories are stated in the agent prompt for
every harness, and `PIPELINES_ARTIFACTS_DIR` points at the turn directory for a
locally spawned Pi process. OpenCode V2 tools run inside the shared serve
process, so there the prompt, not the environment, is the reliable carrier.
Turn-local files belong in `private/`; reports, logs and screenshots for later
stages belong in `public/`. The server owns `input.md`, `memory.md`,
`history.md` and `output.md` and never asks the model to write them directly.
After the visit the server makes one bounded inventory of the turn and public After the visit the server makes one bounded inventory of the turn and public
directories and records each file's name, size, content type (extension, sniff directories and records each file's name, size, content type (extension, sniff
@@ -247,9 +196,8 @@ fallback) and a relative url; these appear under each step's `artifacts` in
`inspect RUN_ID --json` and the TUI's `A` artifacts view, which groups them by `inspect RUN_ID --json` and the TUI's `A` artifacts view, which groups them by
stage and visit, marks images and shows the recorded count, stage and visit, marks images and shows the recorded count,
capture-pending/not-recorded wording and partial-capture notes. Public entries capture-pending/not-recorded wording and partial-capture notes. Public entries
carry a `public/` prefix. `input.md`, `memory.md`, `history.md` and `output.md` carry a `public/` prefix. To see what a late stage was given, read its
are the primary artifacts of every model visit. To see what a late stage was `memory.md`; `history.md` is the full record it could consult.
given, read its `memory.md`; `history.md` is the full record it could consult.
`GET /artifacts/<run>/<step>/<name>` serves the bytes (correct Content-Type and `GET /artifacts/<run>/<step>/<name>` serves the bytes (correct Content-Type and
Content-Length, HEAD, and Range/206/416 via `http.ServeContent`), refusing Content-Length, HEAD, and Range/206/416 via `http.ServeContent`), refusing
traversal, absolute paths, symlink escapes and unknown runs/steps. A pre-turn traversal, absolute paths, symlink escapes and unknown runs/steps. A pre-turn
@@ -302,158 +250,6 @@ and one WAL checkpoint, reporting measured bytes. Pipeline definitions and their
immutable versions are never touched. The commands are local, require an existing immutable versions are never touched. The commands are local, require an existing
`--db`, and need no running server. `--db`, and need no running server.
## Brokered OpenCode chat
The protocol declares the brokered `chat_*` surface (`chat_sessions`,
`chat_create`, `chat_directories`, `chat_prompt`, `chat_messages`,
`chat_interrupt`, `chat_permission`, `chat_reply`). The server dispatches all of
them, and pushes `chat_event` frames derived from OpenCode's global SSE firehose
(`/event` on the native serve, `/api/event` on the V2 API), with retained
per-session/per-message state so a reconnecting client re-syncs instead of
replaying deltas.
At startup `cmd/pipelines-server` calls `opencode.OpenChat`, which detects the
installed backend and opens exactly one owned `opencode serve` endpoint for it:
the native wire for v1, the V2 API for the installed V2 CLI. Chat is enabled only
when that connection carries a URL-bearing, SSE-capable event endpoint; otherwise
chat stays disabled and every `chat_*` request is answered with a protocol error
naming the missing configuration rather than hanging. Stage generation still
reaches V2 through the `opencode api` CLI, so the owned serve process is chat's
single transport and starts no process for stages. The adapter skips firehose
events it does not surface before decoding their data, so an unrelated event
whose `delta` has a different shape (`session.instructions.updated` carries an
object) never fails the stream.
The operator can instead broker chat from their own OpenCode service with the
opt-in `-opencode-endpoint` flag or `PIPELINES_OPENCODE_ENDPOINT`, with precedence
flag > environment > the endpoint recorded on a previous run and the spawned
instance as the default. `opencode.OpenEndpoint` validates the reference once
(the established http(s)/host/no-credentials/no-query/no-path idiom), detects the
backend from the service's own `/api/info` (V2) or `/global/health` (native)
contract and requires a streamable `text/event-stream` event path; it returns a
connection with **no owned process** and never calls `startServe`. A malformed
reference, an unreachable host, a reachable non-OpenCode service or a
health-ok-but-no-SSE service each disable chat with an error naming the endpoint
and never fall back to the spawned instance. An authenticating endpoint accepts an
optional password only through the private file
`PIPELINES_OPENCODE_ENDPOINT_PASSWORD_FILE` (regular, 0600, single-owner), and
`PIPELINES_OPENCODE_ENDPOINT_USERNAME` overrides the detected default user. The
validated choice is recorded in the additive `server_settings` table so a restart
with no flag/environment reuses it; an unreachable recorded endpoint disables chat
with a clear message and no fallback. `pipelines service enable` preserves the
endpoint and the password-file reference in autostart.
`chat_sessions` lists the operator's own chat sessions, not the sessions pipeline
runs create. Operator sessions are recorded in the dedicated `operator_sessions`
table (`session_id` primary key, plus `directory`, `title`, `tag`, `created_at`,
`last_used_at`), separate from `run_steps`/`run_session_owners`, so an operator
chat is a first-class thing and a pipeline stage session — recorded as run
ownership, never in the operator registry — is never listed. The handler reads the
registry once (bounded to 128 rows, most-recently-used first), calls OpenCode's
session list once, and keeps only registry rows the endpoint still reports, so a
session with no recorded tag is never listed and a deleted upstream session does
not linger. It fills each session's `directory`, `tag` and `created_at`/
`updated_at` from the registry and marks `busy` when another client currently
holds the session (an in-server claim, released when the stream ends or the client
disconnects); a second client's `chat_prompt` for a held session is rejected
before any OpenCode call. It is fail-closed: with no registry configured it
returns an empty list, never the endpoint's whole session list. The OpenCode
session list is read unscoped by directory (the V2 `GET /api/session` otherwise
defaults to the caller's directory), because an operator session may live in any
directory.
`chat_create` creates one operator session and records it in the same registry
with the stored tag `operator` (the display label `Operator` is derived from it,
so there is no second tag vocabulary). It takes a `title` (default "New chat") and
a `directory` (default `~`): an omitted or empty value, `~`, and any `~/...` value
all resolve to `os.UserHomeDir`, never the server's working directory; a relative
path or a missing directory is rejected before any OpenCode call, and a session
created but not recordable is reported as an error naming its id. Create posts the
verified V2 shape `POST /api/session` `{"title":...,"location":{"directory":...}}`.
`chat_directories` returns the operator's home first, then the directories of
previous operator sessions most-recently-used first, deduplicated and bounded (8);
it is a dedicated request so the create dialog can load the choices without first
listing sessions and `chat_sessions` stays a pure, fail-closed session list. A
successful `chat_prompt` touches the session's `last_used_at` in one UPDATE, so it
moves to the front of the list; a non-operator session id touches no row.
`chat_adopt` records a session that already exists on the configured endpoint in
the same operator registry, using the endpoint's own directory and title
verbatim (never a guess, the server's working directory or the home directory).
It reads the endpoint once through the shared `Chat.Session` (which reuses
`Sessions`/`decodeChatSessions`), records through the existing
`RecordOperatorSession` with the `operator` tag, and echoes the adopted session
plus its registry row like `chat_create`, so `chat_sessions` lists it and
`chat_prompt` continues it. A nil payload, a blank or foreign-shaped id, a nil
broker or a nil registry is refused before any endpoint call; an id the endpoint
does not report is refused naming the id and records nothing; an endpoint record
with an empty directory is refused rather than substituting a directory. The CLI
equivalent is `pipelines chat-adopt <session-id>` (`--json` prints the full
response, otherwise a short `Adopted <id> · <directory>` line).
While a `chat_prompt` subscription is open the server also polls
`GET /api/permission/request` on a fixed small interval (first poll immediately) and
pushes one `chat_permission` frame per newly pending approval request, deduped by
request id so a repeated poll never re-pushes the same request. The app answers with
`chat_reply`, which the server forwards as
`POST /api/session/{id}/permission/{requestID}/reply` with
`{"decision":"once"|"always"|"reject"}`. A missing session/request id or an invalid
decision is rejected before any OpenCode call, and the poller stops when the stream
ends or the client disconnects.
The permission list and reply are implemented against the V2 HTTP API only: their
field names match the service's `Permission.Request`/`Permission.Reply` schemas
(verified against the installed service's `/openapi.json`). The native v1 serve
translation rejects them explicitly instead of guessing an endpoint, so on v1 the
permission poller stops quietly rather than reporting the documented limitation as
a per-prompt error.
### Verification evidence (2026-10-17)
Verified against the installed OpenCode 2.0.20 on 2026-10-17:
- `opencode --version` reports `2.0.20`; `opencode --help` advertises `api` and
`serve`. `GET /openapi.json` on an owned `opencode serve` lists `GET /api/event`
(SSE) and the session/prompt/interrupt/permission endpoints.
- A live turn streamed token-level `session.text.delta` and
`session.reasoning.delta` events (each with `assistantMessageID` and `ordinal`),
plus `session.step.*` and `session.usage.updated`; the V2 API server
authenticates the fixed `opencode` basic-auth user.
- The opt-in live end-to-end test (`PIPELINES_TEST_OPENCODE_CHAT_LIVE=1 go test
./internal/server -run TestChatLiveEndToEnd -v`) opened an owned V2 endpoint,
created an operator session through `chat_create` in a chosen directory, listed
exactly that session through `chat_sessions` (with its directory and tag
`operator`), recorded a genuine pipeline stage session in
`run_steps`/`run_session_owners` and showed it never appeared in the list, and
streamed a completed turn as `[step:started,text,step:streamed,step:ended]`
(first delta `"pong"`). The operator-session registry, the filter, directory
defaulting and the recents bound are also covered by the `pipeline`, `opencode`
and `server` unit tests, which run without the live gate.
- Not verified live: a genuine pending-approval round trip and any backend other
than the installed 2.0.20. The permission wire shapes are unit-tested over an
httptest fixture, not against a live pending request.
- Operator-supplied endpoint selection and `chat_adopt` (added 2026-10-17):
`opencode.OpenEndpoint` and the flag/env/recorded precedence, the URL-shape
validation failures (scheme, empty host, userinfo, query, fragment, non-empty
path), the unreachable/non-OpenCode/no-SSE/auth-mismatch failures, the
no-owned-process property (`conn.process == nil`) and the password-file rule
are unit-tested over httptest fixtures in `internal/opencode/endpoint_test.go`.
`chat_adopt` (endpoint directory/title recorded with the `operator` tag, echo,
missing id refused naming the id and recording nothing, nil payload/blank id/nil
broker/nil registry refused before any endpoint call, empty endpoint directory
refused) is unit-tested over the server fake broker in
`internal/server/chat_test.go`; the recorded-endpoint round-trip across a store
Close/Open is in `internal/pipeline/settings_test.go`; the protocol round-trip
and the CLI dispatch (`pipelines chat-adopt`) are covered in
`internal/protocol/chat_test.go` and `internal/cli/chat_adopt_test.go`. The
live scratch-server check against the operator's real endpoint (adopt, list,
prompt) was **not** run in this change; only the unit fixtures above were
executed.
Deployment state: not deployed. This is reviewed and committed locally only;
deploying it (and restarting the server) is the operator's step. Do not describe
brokered chat as already deployed.
## Debug and retry ## Debug and retry
Debug opens a new conversation with retained failure context, exact definition and Debug opens a new conversation with retained failure context, exact definition and
@@ -471,18 +267,11 @@ side effects remain and can happen again. Never describe retry or cancellation a
rollback, or resume/replay admitted tool work just to recover formatting. rollback, or resume/replay admitted tool work just to recover formatting.
Retained model-stage failures carry a fixed sanitized category. `FINAL RESULT Retained model-stage failures carry a fixed sanitized category. `FINAL RESULT
VALIDATION` names the exact duplicate-field/syntax detail and byte offset for a VALIDATION` means `output.md` had a missing, duplicate, empty or undeclared
strictly invalid final result; `HARNESS TRANSPORT` covers request, active-session outcome (`references/format.md`); `HARNESS TRANSPORT` covers request, session-poll
poll and final-readback failures. A validation failure never re-prompts the and readback failures. Completed edits and tool side effects are retained, not
admitted tool-using stage: completed edits and tool side effects are retained and undone, so a full retry repeats work. A failure before any prompt is admitted is
not undone, so a full retry repeats work. An explicit read-only stage is the one retried within `retries` for any stage; a post-admission deadline or transport
exception: a malformed result there mutates nothing, so it may be re-emitted up failure is retried only on an explicit read-only stage; a stage with `edit`/`shell`
to `retries` with its `format_repairs` evidence retained, and a post-admission (or no tools block) is never replayed. Neither category exposes provider/model
deadline or transport failure may be retried. A failure to reach the harness bodies or credentials.
before any prompt or tool call is admitted (connecting, or creating the session)
replays nothing, so it is retried within `retries` for any stage, mutating or not.
A stage whose tools include
`edit`/`shell`, or that has no tools block (the legacy read/glob/grep/edit/shell
bundle), is never replayed. Neither category exposes provider/model bodies or
credentials. The isolated formatter's deadline is proportional to the stage
timeout and clamped so it never extends the stage's own deadline.
@@ -13,11 +13,13 @@ at integration. Serialize only actual dependency or resource conflicts.
## Stage jobs ## Stage jobs
- Plan: a short approach and acceptance checks when they help. - `plan`: a short approach and acceptance checks when they help.
- Code: the focused change, tests and focused checks. - `implement`: the focused change, tests and focused checks.
- Review: the whole task diff and independent verification. - `review`: the changed hunks (server-captured changed list, `git diff --stat`,
- UIReview: rendered behavior with controlled data and captures. then per-file diffs) and the reported checks; it runs no suites.
- Land: commit the reviewed work, integrate main and resolve conflicts. - `ui-review`: rendered behavior with controlled data and captures.
- `decide`: a human choice between edges.
- `land`: commit the reviewed work; the delivery gate checks and lands it.
Names are a convention, not a requirement; a pipeline can use any clear stage Names are a convention, not a requirement; a pipeline can use any clear stage
names. Keep each stage's job narrow enough to judge its output. names. Keep each stage's job narrow enough to judge its output.
+38 -30
View File
@@ -8,22 +8,23 @@ below (errors block publishing; warnings print and do not).
## Where work belongs ## Where work belongs
- **Deterministic checks belong in the server `checks` block, not the model.** - **Deterministic checks belong in the server `checks` block, not the model.**
The landing stage sets `delivery=true` and lists the full check commands; the The `land` stage sets `delivery=true` and lists the full check commands; the
server runs them on the committed candidate. A model running the suite puts server runs them on the committed candidate (`references/format.md`, Delivery
every log line into its context, and every later call pays for it again. gate). A model running the suite puts every log line into its context, and
- **Code runs focused tests only**: the test file or package it touched, with every later call pays for it again.
quiet or summary output. Never the full suite. - **`implement` runs focused tests only**: the test file or package it touched,
- **Review reads the diff, not the repository.** Start from the server-captured with quiet or summary output. Never the full suite.
changed-file list the runner adds to the prompt and `git diff --stat`, then read - **`review` reads the changed hunks, not the repository.** Start from the
only the changed hunks and the code around them. Review runs no suites; it judges server-captured changed-file list the runner adds to the prompt and
the reported checks and names missing coverage. `git diff --stat`, then read per-file diffs and only the code around them.
- **Land/committer relies on server checks.** With a delivery gate its prompt Review runs no suites; it judges the reported checks and names missing coverage.
commits and stops; it does not re-run what the gate runs. Do not claim "the - **`land` relies on server checks.** With a delivery gate its prompt commits and
server lands it" unless a stage has `delivery=true` (error otherwise). stops; it does not re-run what the gate runs. Do not claim "the server lands
it" unless a stage has `delivery=true` (error otherwise).
- Every stage that can modify the workspace declares `checks`, even if only - Every stage that can modify the workspace declares `checks`, even if only
`none: <reason>` (`references/format.md`, Checks). Checks must fail when a tool `none: <reason>`. Checks must fail when a tool is missing: no `|| true`,
is missing: no `|| true`, `[ ! -x tool ] || ...` or similar guards (error). `[ ! -x tool ] || ...` or similar guards (error). Cover every language the run
Cover every language the run can change. can change.
## Prompts ## Prompts
@@ -31,34 +32,41 @@ below (errors block publishing; warnings print and do not).
warns. Shared procedure belongs in project docs or this skill. warns. Shared procedure belongs in project docs or this skill.
- **No runner boilerplate.** The runner already explains `output.md`, the - **No runner boilerplate.** The runner already explains `output.md`, the
`# outcome` and `# handoff` sections, allowed outcomes, turn files, tools and `# outcome` and `# handoff` sections, allowed outcomes, turn files, tools and
honesty rules (`internal/stage/model_prompt.go`). Repeating them warns. honesty rules. Repeating them warns.
- **Every outcome a prompt names is a declared edge.** "Return skipped" with no - **Every outcome a prompt names is a declared edge.** "Return skipped" with no
`skipped` edge, or an undeclared `blocked_retryable`, fails the stage at run `skipped` edge, or an undeclared `blocked_retryable`, fails the stage at run
time; validation rejects it (unquoted outcome words such as `skipped`, time; validation rejects it (unquoted outcome words such as `skipped`,
`blocked`, `rejected`, `approved`, `advisory`; other back-quoted words after `blocked`, `rejected`, `approved`, `advisory`; other back-quoted words after
return/report warn). return/report warn).
- **Missing tools or evidence**: declare `blocked` where a stage can lack required
input; the runner tells the model to choose `blocked` when declared, else
`error`.
## Memory and handoffs ## Memory and handoffs
- The runner inlines the **essential memory** (`memory.md`: task, previous - The runner inlines the essential `memory.md` into every prompt and asks each
stage's handoff, outcome ledger, changed files; capped) into every prompt, and stage for a short `# handoff` after its `# outcome` (`references/format.md`).
asks each stage to start its output with a short `# handoff`: what it did, Do not repeat that instruction; say only what this stage's handoff must carry
outcome, files changed, open findings, in a few lines. Do not repeat that if it is special.
instruction; say only what this stage's handoff must carry if it is special. - The full `history.md` and `input.md` are on demand for stages with `read`.
- The **full history** (`history.md`) and full `input.md` are on demand. Never Never tell a stage to read the whole history every visit (warning); say when it
tell a stage to read the whole history every visit (warning); say when it
needs it, e.g. "read history.md only if the handoff lacks a detail you need". needs it, e.g. "read history.md only if the handoff lacks a detail you need".
- A stage without `read` gets `input.md` inlined (up to 32 KB) on every call. Give
`read` to any stage that follows a large output so it reads detail only when
needed.
## Loops and budgets ## Loops and budgets
- **Loops get limits.** An edge back to the same or an earlier stage needs - **Loops get limits.** Put `{"max_visits":3,"on":["rejected"]}` on the reviewer;
`limits` on the source outcome or the target (error). Use `max_visits` 2–3. leave the loop target unlimited or capped at least as high
(`references/control.md`).
- **Re-entry gets only findings**: a rejected review hands back must-fix items - **Re-entry gets only findings**: a rejected review hands back must-fix items
with location and fix, not a full re-review, and the implementer fixes those with location and fix, and the implementer fixes those items rather than
items rather than redoing the task. Use `advisory` for non-blocking notes so redoing the task. Use `advisory` for non-blocking notes so they do not buy
they do not buy another loop. another loop.
- Set **per-stage `budget_tokens`** (and `budget_usd` if wanted) as a runaway - **`budget_tokens` only when the user asks or a measured visit exists**
guard on stages that loop or explore, sized a few times a normal visit. (`pipelines inspect RUN_ID --json`, `usage.tokens_total`). Size it 3–5× that
visit, remembering totals include cache reads, so a normal visit never trips it.
## Commands and scope ## Commands and scope
+47 -597
View File
@@ -1,609 +1,59 @@
# Verification, accounting and real-provider evidence # Verification and evidence
Historical note: model stages now use file-based turns and parse only the
`# outcome` section. The JSON/line-format envelope and format-repair ladder
described in the dated sections below are retired; see `docs/model-results.md`
for the current contract. The dated evidence remains as a record.
Structural validation is not inference, tool execution, correct task completion, Structural validation is not inference, tool execution, correct task completion,
phone delivery or correct billing. Distinguish observed artifacts/command results phone delivery or correct billing. Distinguish observed artifacts and command
from model-written reports. State the command/check actually run and say **not results from model-written reports. State the command or check actually run and
tested** for anything not executed. Never present mocked results as live-provider say **not tested** for anything not executed. Never present mocked results as
evidence or a different backend/model as already validated. live-provider evidence or a different backend/model as already validated. Dated
verification logs live in `docs/verification-history.md` in the source checkout.
## Authoring useful verification ## Where verification happens in a pipeline
Preserve the facts later stages need in free-form output headings; only the - The `delivery=true` stage's `checks` block is the run's deterministic suite;
`# outcome` section is interpreted. Implementer/reviewer stages the server runs it (`references/format.md`, Checks).
can use appropriate permitted commands; do not accept a preceding stage's success - The implementer runs focused checks for what it touched and reports the exact
summary as independent proof. Actual file bytes, command exit status, retained tool commands and results.
parts and server-captured diffs are stronger evidence than prose. A read failure - The reviewer reads the changed hunks (the server-captured changed-file list,
can prove a deliberately missing input, but is not a successful read. Tool names then `git diff --stat`, then per-file diffs), judges the reported checks and
mentioned in text do not prove tools executed. A reviewer stage must inspect the names missing coverage. It runs no suites. Its verdict concerns the current
actual files and run its own checks; a source-only review runs no commands and change only.
must state that runtime behavior was not tested. Structural, mocked or - Actual file bytes, command exit status, retained tool parts and server-captured
authoring-time checks are not deployed or live-provider evidence. diffs are stronger evidence than prose. Tool names mentioned in text do not prove
tools executed. Do not accept a preceding stage's summary as proof of runtime
behavior.
Do not add technology-specific checks unless the task/repository requires them. Do not add technology-specific checks unless the task or repository requires
Keep runtime verification separate from authoring. Execute relevant code and fixture them, and do not weaken an acceptance check just to get a passing run. Ask before
checks within the authorized task; ask before unrelated chargeable calls or notifications. unrelated chargeable calls or notifications. `provider-check` must run on the
Do not weaken an acceptance check just to get a passing run. intended execution computer/container with its credentials; a client-side check
`provider-check` must run on the intended execution computer/container with its is not proof of a remote server's provider health.
credentials; a client-side check is not proof of a remote server's provider health.
## Budgets and backend caveats ## Usage evidence
Defaults remain two retries and one hour per stage attempt; a run-level wall-clock `pipelines inspect RUN_ID --json` exposes each model step's `tokens_total`,
deadline is not added. Budgets are optional, positive and independent USD/token `tokens_in`/`tokens_out` (only when `split_known`), `cost_usd` (only when
reported-usage limits shared across attempts and repeat visits. `cost_known`) and the model it ran with, plus the run's totalled `usage`;
Accounting failures stop budget-limited stages. In-flight calls can overshoot; `pipelines stats --json` adds history-wide totals. Token totals include cache
these are **not provider-side hard caps or a guaranteed bill ceiling**. Reported reads. An unreported cost or split is shown as unavailable, never zero; runs
USD may validly be zero; do not fabricate prices/accounting from output length. recorded before usage tracking omit `usage`. Budgets are reported-usage limits,
**not provider-side hard caps or a guaranteed bill ceiling**; in-flight calls can
Per-run usage is recorded as typed step evidence from the usage the stage already overshoot.
measured for its budget (no second harness read and no transcript parse), and
totalled for the run and over all history. A stage revisited within a run shares
one budget, so each step records only that visit's increment of it and the run
total is not the cumulative stage budget counted again; a revisit that reports
nothing new (a failure or timeout before any usage poll, or a Pi visit that never
reaches a usage stat) records no usage for that visit rather than a known zero.
`CLI_PREFIX inspect RUN_ID --json`
exposes each model step's `tokens_total`, `tokens_in`/`tokens_out` (only when
`split_known`), `cost_usd` (only when `cost_known`) and the model it ran with,
plus the totalled `usage`; `CLI_PREFIX stats --json` adds the history-wide totals,
which equal the sum of the per-run totals. A stage that reported no cost exposes
its tokens and marks the cost unavailable rather than showing zero; a harness that
reports only a total (Pi) exposes the total and marks the in/out split
unavailable rather than presenting the total as input tokens. An upgraded or
historical database gains an empty usage table with no backfill, so old runs omit
`usage` instead of showing zero. This is current source, not deployment evidence.
Dated current-source evidence (2026-10-17, this machine). A throwaway read-only
reader (`internal` store API) over a scratch copy of
`~/.local/share/pipelines/data/pipelines.db`, taken with
`sqlite3 "file:$HOME/.local/share/pipelines/data/pipelines.db?mode=ro" ".backup <scratch>"`
so the live DB is never mutated, opened 228 runs and found **no** `step_usage`
rows: every stored run predates this change, so per-run figures are unavailable
rather than zero. Run 314 (this item's own run) and run 239 (whose implementer
step ran `opencode-go/kimi-k2.7-code`, a stage model different from the pinned
`opencode-go/deepseek-v4.1-flash`) both report `usage=(none recorded)`, and
`stats` omits the history-wide totals. The recorded figures themselves are
covered by the passing current-source round trips — `internal/pipeline/usage_test.go`,
`internal/server/usage_test.go` (including `inspect --json` over a websocket) and
the pre-upgrade/read-bounded/stats-sum cases — not by a live run, because the
deployed server predates this change and was not restarted. No live model call,
deploy or rebuild produced this evidence.
A live V2 trial found `/generate` returned text while its retained session had no
messages and zero counters. Current source uses tracked `/prompt` → bounded
active-session polling → message readback for **budgeted V2 text-only calls, with
all tools denied**. Completed token-budgeted responses reporting zero tokens fail
closed. No new definition flags or agent tools are required for this fix.
Unbudgeted tool-free V2 generation can still have empty backend message history;
pipeline inputs, results and command audit remain retained. An unbudgeted V2
audited agent stage makes exactly one extra bounded final session-aggregate read
to record any reported USD/token usage best-effort: missing or invalid usage stays
unknown and never turns a valid run into a failure, cumulative sessions/retries
are keyed per session so they cannot double count, and totals are never inferred
from final-assistant-only or native-partial data. Budgeted settlement and native
V1 enforcement are unchanged. Native V1 uses its existing path.
The V2 `.../experimental/session/{id}/wait` request is **no longer used**: a dated
Docker log shows it timing out at the CLI's own request timeout after about six
minutes (run started 2026-10-10T23:07:16.547Z, `TimeoutError` logged at
2026-10-10T23:13:17.262Z, server `http.status=499`), which aborted a long
implementation stage. Instead current source polls `GET /api/session/active`
about once per second with a context-aware delay and no busy loop, until the
admitted session is absent (inactive). Missing/null/non-object `data`, or a state
other than the documented `running` type, fails closed and is never treated as
inactive. This is **mocked regression coverage** in `internal/stage` (fake CLI),
not live-provider evidence; V1 native settlement is unchanged.
Current source reads the V2 final result with a single bounded descending
final-assistant readback (`order=desc&limit=1&type=assistant`) after the settled
poll, for both audited agent stages and budgeted V2 text-only calls, so large
retained history (including prior tool-read contents) is no longer fetched just
to select the completed result. A truncated/incomplete readback, an empty data
list, or a latest message that is neither completed `stop` nor a completed
structured tool-call fails closed with a sanitized diagnostic that omits
provider content; retained audit previews are **not** executable final results.
Session/debug evidence now reuses the same single latest-assistant readback
instead of a recent-20 all-message fetch, and returns each payload as a labelled
bounded, credential-redacted envelope with explicit preview/truncation/missing
diagnostics; a small final assistant result is therefore selected even when large
prior tool content exists. Pi evidence remains documented JSONL and is never
parsed as one JSON object. This describes current source behavior, not a guarantee
that a user's installed server includes the fix. An updated skill/client is not
deployment evidence; never rebuild/restart services or log into providers without
specific authorization.
Retained model-stage failures now carry a fixed sanitized category. A strictly
invalid final result (a duplicate nested field, or malformed/ambiguous JSON with a
byte offset) is labeled `FINAL RESULT VALIDATION`; request, V2 active-session poll
and final-readback failures are labeled `HARNESS TRANSPORT`. A pre-admission
request failure replays nothing and is retried for any stage; a post-admission
failure is retried only on an explicit read-only stage (see the 2026-10-17 section
below). A validation failure
preserves the admitted session, transcript and evidence and performs no second tool
execution. Confirmed ordinary-endpoint failures on 2026-10-11: an all-history
readback of exactly 262144 bytes of incomplete JSON (`invalid agent messages`), a
reviewer result with a duplicate nested `performance_review` field, and an
onboarding visual-review result with `invalid character 'z' after object key:value
pair at byte 3968` where unsafe lossless repair was rejected. These are **mocked
`internal/stage` fixtures**: executable source-level evidence, not live-provider
evidence and not a deployment. OpenCode V2 prose `output_contract` does not enforce
structured output; V2 results are validated locally and no unsupported V2 format
field is sent. A review-only fresh execution is a future recovery idea, **not
implemented**. Onboarding UI visual approval remains unresolved and must not be
reported complete.
## Bounded malformed-result recovery: 2026-10-16
Source-level, mocked `internal/stage` regression coverage (not live-provider
evidence and not a deployment): malformed final-result recovery now tries a
deterministic local pass first (append missing closers, 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, the stage
timeout and the attempt's remaining budget rather than a fixed 30-second
constant. Every path
records `repaired`, `partial` or `unrecoverable` in `format_repairs`; a `partial`
or `unrecoverable` payload is never returned as a completed result, and an
ambiguous payload (an unescaped quote/colon inside a string value) is never
guessed at. A shell-enabled stage's malformed but deterministically recoverable
result now completes without replaying admitted tool work; `safeToReplay` is
unchanged. The run-55 `ui_reviewer` payload was retrieved read-only with
`pipelines inspect 55 --json` and reproduced its exact byte offset 7837; it is the
ambiguous error class, so it is reported unrecoverable rather than repaired. This
does not update or restart any running server.
## Harness transport reach retry and repair deadline: 2026-10-17
Source-level, mocked `internal/stage`, `internal/opencode` and `internal/server`
regression coverage (not live-provider evidence and not a deployment): the
harness transport path now distinguishes a pre-admission reach failure
(connecting or creating the session) from a post-admission readback/poll/agent
failure under the one `HARNESS TRANSPORT` category. A pre-admission reach failure
replays nothing, so it is retried within `retries` for any stage with a fresh
session and no replayed prompt; a post-admission failure is retried only on an
explicit read-only stage, and an `edit`/`shell`/legacy stage still never replays
admitted work. A context that expires during a request keeps both the sanitized
transport detail (operation/status/exit) and
`errors.Is(err, context.DeadlineExceeded)`; a bare attempt-boundary deadline is
not treated as a reach failure and stays terminal for a mutating stage. An
unrecognized provider execution-error name is reported as a bounded, sanitized
identifier plus any HTTP status. The isolated formatter deadline is now
proportional to the stage timeout (floored, capped, and clamped to
`remaining - margin` so it can never extend the stage/attempt deadline). These are
mocked fixtures; a deployed server is not updated by this change.
## Failure-handling source changes: 2026-10-15
Source-level, mocked `internal/stage` and `internal/server` regression coverage
(not live-provider evidence): an explicit read-only tools stage now actually
retries a post-admission stage deadline or harness transport failure, creating a
fresh bounded session per attempt, while a stage with `edit`/`shell` or no tools
block still never replays admitted work; a malformed final result is re-emitted
up to `retries` only on such a read-only stage with its `format_repairs` evidence
retained. A timed-out agent stage settles knowable V2 usage and retains one
bounded, redacted latest-assistant readback plus a `retained_session` pointer in
its stored transcript. A declared outcome routed to `#failure` with no step
diagnostic now yields a run diagnostic like `stage <key> returned outcome
"blocked"`; an existing step diagnostic is still used verbatim.
## Dated source-level coverage: 2026-10-11
Source-level/mocked regression coverage (not live-provider evidence):
`resolve-releases` now uses a single bounded
`GET .../git/matching-refs/tags/v2` response that the GitHub REST docs describe as
complete with no pagination; offline fixtures cover a 100+ ref array,
`MAX_REFS`/`MAX_BODY` caps, ignored prerelease/build tags, malformed refs and a
missing newest-tag digest failing closed with no older fallback, with no
`tags/list` cross-check. Picker tests cover blink/index preservation,
ANSI-readable selection without a colliding background, and
40x16/80x24/120x36 height budgets. The compiled picker PTY check (opt-in via
`PIPELINES_HARNESS_PTY_DIR`) waits through blink intervals and asserts exact
saved/arrow-scrolled models. `setup-docker.py` accepts the actual
`opencode v2.0.26` probe token and compares source identity only on a full
install; model/login-only reconfiguration compares the verified release image
identity. Python fixtures bind temporary HOME directories so the suite passes
under the container default `/home/pipelines` without weakening mount guards.
The Docker authoring transport is also covered at source level: the shared
prefix picks `/usr/local/bin/pipelines` for a Docker-linked profile. Loopback is
recognized only via `net.ParseIP(...).IsLoopback()` and an exact case-insensitive
`localhost`, so a remote DNS name such as `127.remote.example` stays remote with
no probe. A single bounded `docker compose port` probe parses complete
`host:port` bindings, and scoped source/target aliases are embedded only when a
binding covers the requested loopback address and port; malformed or non-matching
bindings and a loopback `wss` endpoint fail closed, and `client.Dial` rewrites
only an exact source match. `provider-check` dispatches through a Docker-linked
profile's existing service with `-T`, the original cwd/model/timeout, exact
stdout/exit propagation and `--json` passed only in JSON mode (fixture tests, no
real provider), while explicit native profiles keep the host generator. The
picker uses a true `x/term` TTY check so `/dev/null` and pipes fail fast, with a
short context deadline so a regression fails rather than hangs. Real Docker
rebuild/reconfigure against live registries, a real
40x16/80x24/120x36 terminal capture, and real model inference remain **not tested**
in this change.
### 2026-10-11 Pi sign-in handoff (source + Root PTY observation)
Root separately exercised current-source `pipelines harness setup pi --login`
under a real Docker PTY with copied harness preferences. Root observed that
Pi 1.1.0 defaults to fullscreen and clears the Pipelines login instructions, so
the user sees a coding interface without the `/login` guidance, and that
`/login` first shows "Select authentication method" (account / API key / Radius)
rather than a provider picker. The same handler run with a temporary executable
wrapper passing `pi --tui-mode regular` retained the Pipelines header and
instructions above Pi's interface. Installed `pi --help` documents the supported
`--tui-mode regular` flag and the fullscreen default; `pi auth --help` confirms
there is no standalone login (only print/check, never run). These are source/root
observations with copied preferences: **no provider was selected, no key was
entered and no inference occurred**, and this source is **not deployed** and is
not live-provider evidence. A first reviewer capture at 80x30 found the longer
handoff plus Pi's own banner scrolled the Pipelines header off the top, so the
copy was shortened to a title plus three short lines (existing-credential reuse
folded into the `/login` line, with the account/API key/Radius method choice and
`ctrl+c`/`ctrl+d` exit keys kept) and the redundant trailing blank removed.
Independent PTY re-capture at 80x30/100x36 after this shortening is **not
tested** in this change. The matching exact login-argv and copy assertions are
covered by fixture tests in `internal/cli`/`internal/harness`.
### 2026-10-11 server CLI fixture isolation (source-level + Root-reported run)
Root-reported runtime evidence supplied for this change (not re-executed by the
authoring stages): the deterministic seeded-profile regression
`go test ./tmp/preview-verification -run TestServerCLIFixtureDoesNotInheritUserDockerProfile -count=1`
seeds a synthetic Docker-linked harness profile in a child
`go test ./internal/server -run '^TestCLIHeadlessRunInspectionCancellationAndRPC$'`.
It previously failed because the child inherited the caller's real
`PIPELINES_HARNESS_CONFIG`, so the CLI `debug` prefix failed closed
("refusing to redirect") against the test's ephemeral httptest endpoint. Root's
four independent preview tests for the bounded transcript helpers pass; Root's
full host race run produced no race warning and only this fixture failure, and
`go vet ./...` passed. Current source therefore isolates the server CLI fixture
with the same missing-temp-file
`t.Setenv("PIPELINES_HARNESS_CONFIG", filepath.Join(t.TempDir(), "harnesses.json"))`
pattern already used by `internal/cli`'s setup, so the host executable stays
authoritative and no Docker probe runs for an ephemeral test endpoint. The
production fail-closed redirect guard in `internal/harness/prefix.go` and its
`refusing to redirect` / loopback-wss regressions are unchanged; the failing
verification was fixed rather than removed.
This is a current-source and Root-reported observation. At the time of that
observation, independent re-execution of the full `go build`/`go vet`/`go test`
matrix (including Docker-only race results) and the final installed-host Docker
verification were **pending**; they are now recorded in the 2026-10-11 FINAL
INSTALLED section below, so this phase-specific wording is superseded by that dated
install. The packaged reference describes source behavior; a source fix or updated
skill is not deployment evidence.
### 2026-10-11 retained run11 reviewer re-capture (source-level, not a final install)
Independently reading the retained run11 verification at
`tmp/maintenance-run11-verification.json` records the source-level review
sequence: an earlier reviewer PTY capture rejected the longer handoff because at
80x30 it scrolled the Pipelines header off the top; the implementer then
shortened `AuthHandoff` to a title plus three short lines; and the re-run
`reviewer` and `ui_reviewer` stages approved from real current-source Pipelines
PTY captures at 80x30 and 100x36 that showed the header and handoff visible above
installed Pi 1.1.0's regular interface. A labelled controlled fixture that
stripped `--tui-mode regular` reproduced the pre-fix fullscreen clear, and the
review stages report no provider selected, no key entered and no inference. This
is source-level reviewer evidence, read from retained output; it was not a
deployed/installed state at that time, and the final full Docker install
verification was then **pending** — it is now recorded in the 2026-10-11 FINAL
INSTALLED section below, so this phase-specific wording is superseded by that dated
install.
Root-reported actual runs (source-level observations supplied by Root for this
change and not re-verified here): run7 showed both configured providers' exact
handoff markers; runs6/9/10 exercised live maintenance with final-assistant
polling/readback succeeding. These are Root observations, not mocked-regression
coverage and not a completed installation; no final deployed/installed state is
claimed.
### 2026-10-11 run13 interruption, Docker race limitation and state separation
Four states are kept explicitly separate and must not be conflated:
1. **Current source** (this checkout, not deployed): bounded 32 KiB
(`transcriptBound = 32<<10`) redacted transcript previews produce a valid JSON
envelope with redaction applied before truncation and a rune-safe 8 KiB preview;
session/debug evidence is scoped `latest_bounded_evidence` with the single
bounded latest-assistant readback and at most the 3 most recent session-bearing
steps; an unbudgeted V2 audited agent stage records reported usage best-effort
through exactly one 2s-bounded final session-aggregate read, leaving
missing/invalid usage unknown; and the isolated server CLI fixture uses the
missing-temp-file `PIPELINES_HARNESS_CONFIG` pattern while the production
fail-closed redirect guard in `internal/harness/prefix.go` is unchanged. Pi JSONL
is never parsed as one JSON object; native V1 keeps its existing path.
2. **Host verification evidence independently recorded by Root**: after the fixture
fix, Root ran the full `go test -race -count=1 ./...` and `go vet ./...`; after
three harness-neutral evidence labels and Step wording changes Root re-ran the
affected `tui`/`author`/`cli` race and vet checks, the Python suite (80) and the
opt-in compiled picker PTY check (4). These are Root-recorded host results, not
re-executed by the authoring stages.
3. **Deployed old image**: the running Docker image predates these source changes
and does not include them.
4. **Final install (completed 2026-10-11)**: the final install and installed
authoring/provider verification were **pending** when this separation was
written and are now recorded in the 2026-10-11 FINAL INSTALLED section below; an
updated skill/client or source checkout is still not deployment evidence on its
own.
Docker race limitation (confirmed): the Docker runtime is built with
`CGO_ENABLED=0` and has **no C compiler** (the Alpine runtime stage installs no
GCC/musl-dev), so `go test -race` cannot run there. In-Docker reviewers must use
ordinary `go build`/`go test`/`go vet` and rely on independently executed host
`-race` runs. Race checks must not be attempted in Docker and no compiler may be
installed or searched for.
Run13 interruption (dated evidence, not a fix): the previous reviewer ran `find /`
looking for GCC; the tool timeout left a process in disk sleep, Docker could not
stop the container, and an approved Desktop restart recovered run13 as interrupted
(`executing=false`, every step `agent_active=false`) with **no automatic replay**.
This is an environment/interruption observation only: no general cancellation fix
is inferred and process termination is unchanged. Docker startup recovery already
sets running steps to `interrupted` with `agent_active=0`.
### 2026-10-11 short-lived CLI inherited-pipe cancellation (current source)
Current source (not deployed) adds one shared, dependency-free constructor in
`internal/opencode`: `CommandContext(ctx, executable, args...)` sets the single
finite `os/exec.Cmd.WaitDelay` constant `ShortLivedWaitDelay = 250ms` and is the
only place that value is defined. It is reused by the `internal/stage`
`OpenCodeClient.call()` API/agent path (including `Interrupt`), `opencode.Detect()`
`--help` and the native `Connection.Messages()` export fallback. It bounds
**draining of inherited output pipes only**: after the child exits os/exec waits at
most the grace for descendants holding the inherited stdout/stderr pipes, then
closes them and reports `exec.ErrWaitDelay`; it does not terminate or confirm
cleanup of descendants.
`context.Canceled`/`context.DeadlineExceeded` identities, `exec.ErrWaitDelay` on
the sanitized errors, the ≤64 KiB request / ≤1 MiB response / 8 KiB stderr bounds,
`boundedBuffer`/`boundedOutput` drain-with-overflow behavior, redaction, strict
result validation and cleanup-unconfirmed active ownership (`ErrStageCleanup`, no
replay) are unchanged; no new module dependency is added and a parent that exits
successfully while a descendant still holds partial stdout is never treated as
success.
Dated synthetic reproduction (`tmp/interrupt-verification`, synthetic
real-subprocess diagnostics, **not provider evidence**): with Root waiting for the
descendant itself to start before cancelling public
`OpenCodeClient{Backend:"v2"}.Interrupt`, two Docker/Linux returns took
3996/3995ms despite `context.Canceled` (`descendant-started.jsonl`); the stronger
host reproduction took 4003/4000ms (`reproduction.log`). Added source-level
regressions use real `os/exec` fixtures with start-marker barriers, bounded
watchdogs and naturally terminating children for cancel-after-descendant,
deadline identity, descendant-held pipes → `ErrWaitDelay`, ordinary
output/exit/redaction, failed-interrupt ownership/no replay, plus `Detect`/export
wait-delay and cancellation cases. This is **current source, not deployed**:
descendant termination, confirmed remote interruption and any run13 Docker disk
sleep fix are **not claimed**, and Docker race remains unavailable (no C
compiler).
### 2026-10-11 FINAL INSTALLED verification (friend-ready preview)
This is the dated receipt for the installed runtime, recorded by Root from
`tmp/friend-final-verification/summary.json`; it supersedes the earlier
"pending final install" statements above, which stay as phase-specific history.
A normal interactive `./install --model opencode-go/deepseek-v4.1-flash
--harness-model opencode-go/deepseek-v4.1-flash` exited **0**, resolving the current
releases live and building fresh dirty source into actual image
`sha256:1810ab50f3ea3991e7f3548c79250e65a114bb1821eac52efd872b91cf7c3136`
(OpenCode 2.0.26 / Pi 1.1.0 / Node 24.18.1) with real tool-free provider
validation, ntfy authenticated publish, server + host health, home/workspace entry,
preserved authoritative endpoint and `ok` pre-install database/home backup
integrity. Post-install preservation all passed (original definitions 1–4, history
1–16, host/container default Pi and both models/profiles, logical endpoint,
service URLs/timezone/ports/models, Pi credential hash, OpenCode connected accounts,
ntfy token); neither original-repo commit/push nor credential/data cleanup ran.
Installed host-CLI authoring with **both** Docker harnesses (separate retained
drafts, each changing only the worker prompt) performed real `ping` → `pong` and
`validate` → `validated` through the generated Linux `/usr/local/bin/pipelines` and
scoped transport aliases preserving the logical `8081` endpoint and draft metadata,
independently inspected from native OpenCode tool outputs and retained Pi JSONL
`toolResults`, with no draft submit/run/publication. Docker-proxy submit on
verification-only definition 5 published v2, a second stale v1 draft was rejected as
conflict, and **Run17** succeeded in 7 seconds with the exact
`pipelines-docker-verified` markers in OpenCode then Pi, both inactive and exactly
one completed marker read verified from retained native history (not the
latest-assistant preview); best-effort unbudgeted usage was OpenCode 4011
tokens/$0.00029769599999999996 and Pi 1071 tokens/$0.000142002, and
`/api/session/active` was empty after exit. Installed-UI captures
(`installed-pi-*`, `pi-signin-*`, `installed-pi-models-*`) cover the actual run17
80x30/120x36 neutral-Pi/green-both-stage renders, the Pi auth handoff/method menu
viewed/canceled/exit0 with no sign-in, and the model wizard using copied
preferences only while production preferences stayed preserved. Root's independent
checks passed: full host `go test -race -count=1 ./...` and `go vet ./...`,
Python 80 tests (1 optional PTY skipped), Node policy, isolated developer lifecycle
fixture (no inference/deploy) and author package tests; earlier independent
reviewers ran ordinary Docker build/vet/tests and focused subprocess regressions
(no Docker race, no GCC search, no global `find`). **UNVERIFIED** here: fresh
OAuth/provider login completion, phone delivery, other real providers, the
D-disk-sleep fix and active lease expiry; authentication menus and
existing-credential inference are not fresh sign-in proof. The stronger synthetic
PUBLIC `Interrupt` child-start barrier (host 252/252 ms, Docker 250/251 ms, context
canceled true, bounded true vs ~4 s before) is not proof of descendant termination,
remote cleanup or a Docker VM disk fix. Archive extraction, build-identity and
compile verification remain pending until Root executes them.
### 2026-10-11 generated release receipt ignore (source-hygiene regression)
Current source adds two root-anchored `.gitignore` rules for the installer's
machine-local generated artifacts: `/.pipelines-releases.json` (the receipt path
from `setup-docker.py` `release_receipt_path()`) and `/.pipelines-releases-*` (the
`tempfile.mkstemp` `prefix=".pipelines-releases-"` in `record_release_receipt()`);
no installer/runtime code changed and the pre-existing receipt and other files are
retained. A new `scripts/test_build_metadata.py` case is a controlled, isolated Git
fixture using the repository's actual `.gitignore`: a clean tracked source plus a
representative generated receipt/`.pipelines-releases-*` temporary file leave `git
status --porcelain` empty and `build_metadata.docker_args` at
`PIPELINES_DIRTY=false` with no `-dirty` version; editing the tracked source then
makes the status non-empty and `docker_args` report `PIPELINES_DIRTY=true` with a
`-dirty` version. This is **offline source-level regression coverage**, not the
recorded actual new-account install/provider login above and not live-provider or
deployment evidence; this docs-and-ignore change has no rendered UI.
## Dated live reference validation: 2026-10-10
Environment: Docker Linux aarch64, OpenCode v2.0.20,
**opencode-go/deepseek-v4.1-flash**. Isolated databases/fixtures and local HTTP
notification endpoints; normal published pipelines/repositories were not changed.
- Incident extraction → report: exact IDs/severities/counts, unchanged handoff,
retained session readback and one local success receipt passed (6.63s).
- File edit → verification: exact final release-file bytes, unchanged fixtures,
independently executed `cmp`, completed read/edit/shell evidence, retained edit
diff and no verifier edits passed (14.60s).
- Missing required input: blocked route ended failed; missing file was not invented;
retained read attempt and one local failure receipt passed (4.21s).
- Accounting/one-token budget initially failed its acceptance check because session
zeros let the run succeed. After the tracked-prompt fix, a focused live rerun
passed: **952 reported tokens, $0.00016440**, budget-exceeded failure, stopped
owned session (2.43s). This is not an independently reconciled provider bill.
The earlier three workflows were rechecked from retained artifacts with current
assertions, without more inference. There was **no fresh full-suite live run of
all four workflows after the fix**. Do not generalize these results to all five
starter templates, other models/providers, or compatible native schema/tool usage.
Real ntfy authentication/storage, phone reception, provider outages/timeouts,
long-stream interruption and promptness of cleanup were **not tested** by this trial.
The trial ran rebuilt test binaries; it did not deploy the fix to the ordinary server.
## Dated live reference validation: 2026-10-11 (run7)
One existing real run7 (2026-10-11) is the retained live evidence dated for this
change: it executed both configured harnesses, OpenCode 2.0.26 and Pi 1.1.0, with
`opencode-go/deepseek-v4.1-flash` stages on the Docker server, and both steps
succeeded (6s; the retained Pi evidence panel reports 1054/10000 tokens). The
captures are retained at `tmp/friend-ui-verification/source-pi-80-*` and
`source-pi-120-*`, and a current-source TUI inspection of that run recorded actual
80x30 and 120x36 renderings, including the run graph and the bounded evidence
panel.
This is a single real run, **not** a fresh full reference suite. Other providers,
real outages/long-stream interruption, fresh OAuth and phone delivery remain
**not tested**; the new-source installer and installed-authoring verification were
separately completed by the dated 2026-10-11 FINAL INSTALLED section above. The
[2026-10-10 OpenCode v2.0.20 trial](#dated-live-reference-validation-2026-10-10)
above remains dated history.
## Reference suite when explicitly requested
The source checkout's `TestReferenceWorkflowsLive` uses six model stage attempts
plus possible compatibility/format-repair calls. Retries are disabled and stages
have two-minute timeouts. It uses real existing credentials and retains private
`runs.db`, pinned definitions, fixture directories, run/session JSON and report.
The accounting case has a one-token/$0.25 budget; other cases have no spending
limit. Test notifications use a local endpoint, not the configured phone topic.
Live inference requires explicit `PIPELINES_REFERENCE_LIVE=1`, a chosen
`PIPELINES_REFERENCE_MODEL=PROVIDER/MODEL`, and an existing private
`PIPELINES_REFERENCE_DIR`. Get consent for chargeable inference and confirm which
execution computer/account to use. Ordinary tests skip live inference. Do not
search the repository or run the suite during normal draft authoring.
If the user explicitly asks to run the suite and provides a source checkout:
```sh
PIPELINES_REFERENCE_LIVE=1 \
PIPELINES_REFERENCE_MODEL=PROVIDER/MODEL \
PIPELINES_REFERENCE_DIR=/private/approved/artifacts \
go test ./internal/server -run '^TestReferenceWorkflowsLive$' -count=1 -v -timeout 15m
```
Docker credentials require running the correctly compiled test binary in that
container; do not copy host credentials or publish tests to the normal database.
`TestReferenceDefinitions` checks definitions without inference.
`TestReferenceArtifactsReview` rechecks copied run/fixture evidence without
inference using `PIPELINES_REFERENCE_REVIEW_DIR`; select only cases present in
that artifact directory. Missing cases skip and must not be reported as passed.
## 2026-10-12 run22 success, run23 live CSV fixture and run24 interruption
Source/structural and live-fixture evidence stays separate from runtime
deployment; nothing here is a deployment claim.
- **run22 (structural/source checks, success):** the retained run22 verification
passed its structural/source checks of the scoped template and prompt changes.
- **run23 (live Pi CSV fixture):** a real exact-template Pi CSV run fetched the
official Python `csv` documentation through the conditional official-source
webfetch and implemented CSV parsing with the standard library's `csv.reader`
through an existing shared helper, adding no duplicate preview parser; both the
implementer and reviewer checks actually passed. Root independently verified the
full retained native tool results and protected-file hashes against its saved
baseline, rather than relying on model-written reports.
- **run24 (interrupted, not a pass):** the run24 implementation completed, but its
reviewer ignored the scope instruction and ran a prohibited filesystem-root scan
(`find /`), leaving a process in uninterruptible D-state and stalling Docker
mount/snapshot reads. Root canceled the run, made a consistent SQLite backup
(`integrity ok`), recovered Docker with the supported stop/start path, and
restored the existing ntfy/Pipelines services with the original definitions, run
history, credentials and settings verified unchanged. run24 is retained as
**interrupted**, not a success.
- **run25 (live Pi source-only review):** the reviewer identified duplicated
implementation, a hardcoded special case, suppressed errors and test gaps.
Root inspected retained native calls: only local read/search tools ran, with no
shell/edit/network calls. Original fixture hashes were unchanged; runtime
behavior was explicitly marked untested.
- **run26 (final maintenance review, success):** the scoped plan/implement/review
workflow passed package tests, vet, build and formatting checks. Root inspected
the actual retained outputs and changes. No rendered UI change was claimed.
The scoped prompt guidance asks stages to keep inspection/verification to relevant
repository paths and supported commands; it is a working instruction, **not** an OS
sandbox, and neither fixes Docker VM/disk bugs nor universally enforces tool
boundaries. At these recorded checkpoints the source changes had not been deployed.
Catalog deployment requires a separate check of the running server and its actual
template contents; these observations do not establish publication or deployment.
Other providers and phone delivery remain **not tested** by this record.
## 2026-10-12 final template verification and Docker catalog deployment
The final three-stage template ran as live Pi run27 (verification definition7,
version2) in a fresh disposable CSV fixture. Root inspected full retained native
results: the planner fetched official Python CSV documentation, the implementer
used the standard library through the existing shared parser, and implementer and
reviewer independently ran `python3 checks.py` successfully. Root reran those
checks, verified the protected fixture hashes and planner-owned review criteria,
and confirmed the preview reused the shared parser.
The Docker server was then refreshed from clean source commit
`143f237268dbde2efd6c5ce5722a3e1fd7e08c9c`, retaining OpenCode 2.0.26, Pi 1.1.0
and Node 24.18.1. The running server reported that exact commit and `dirty=false`;
all five served templates matched current source with the saved Pi/model defaults.
A consistent pre-deployment database backup passed integrity checks. Every stored
definition version/source, retained run ID, saved setting, endpoint and provider
credential/account checked by Root was preserved. This record is a documentation
follow-up to that deployed build; it changes no runtime code or template source.
These bounded fixtures establish the observed behavior on this instance, not a
guarantee of every future model review, provider, task or platform. They do not
establish fresh account sign-in or phone notification reception.
## Orchestration verification habits ## Orchestration verification habits
A run's status and a stage's summary are **claims**, not evidence. When the agent A run's status and a stage's summary are **claims**, not evidence. When the agent
manages runs rather than making the change, its job includes independently checking manages runs rather than making the change, its job includes checking what each
what each run claims. run claims.
- **Read the retained evidence yourself** — `inspect RUN_ID --json` for the exact - **Read the retained evidence yourself**: `inspect RUN_ID --json` for the exact
stage outputs, outcomes, diagnostics, file changes and artifacts — instead of stage outputs, outcomes, diagnostics, file changes and artifacts.
trusting the model-written summary of the run. - **Run the check.** Where an item claims a build or tests, run the exact command
- **Run the check.** Where an item claims a build or tests, run the exact command and and read its output. Never report a check you did not execute.
read its output; "tests pass" without a command and its observed result is not a - **Read the images.** Open the screenshots a reviewer cites and confirm each is a
check. Never report a check you did not execute. real image (magic bytes or content type), not a text file named `.png`.
- **Read the images.** Open the screenshots the reviewer cites; do not accept a - **Compare the built artefact with what was delivered** (md5 or equivalent), so a
description of an image you can open. Confirm a capture is a **real image** (magic stale or substituted file cannot pass (`references/delivery.md`).
bytes or the reported content type), not a text file named `.png` - **State "not tested" explicitly.** A `succeeded` run means its stages reported
(`references/debugging.md`). success, not that the operator's acceptance criteria were met.
- **Compare the built artefact with what was delivered.** Check the md5 (or - **Report failures as failures.** Never re-run until something passes and then
equivalent) of what was built against what is installed or published, so a stale or call that verified; record the failure and its category.
substituted file cannot pass as the artefact (`references/delivery.md`).
- **State "not tested" explicitly.** A run that `succeeded` means its stages reported
success; it is not proof that the operator's acceptance criteria were met. Name what
was not covered.
- **Report failures as failures.** Never re-run until something passes and then call
that verified; record the failure and its category.