Files
pipelines/internal/author/skill/references/harnesses.md
T
alan bd07abcde8 Run pipeline stages on Claude Code (harness=claude)
A model stage with harness=claude, provider=anthropic and a Claude model id
runs one claude -p process per visit with the server user's Claude sign-in.
Only the declared tools exist (--tools) and nothing else is approved
(--permission-mode dontAsk); edits are approved only below the run directory
and the stage's artifacts directory. A permissions block, run write paths,
delivery=true and reasoning_effort none/minimal are refused, not widened.

Usage comes from the CLI's final result and counts toward budgets. Failures
are fixed text; billing, quota and rate-limit refusals map to
ErrProviderQuota. The redacted stream is the session export and evidence.
provider-check --harness claude and model overrides are covered.
2026-11-11 10:30:37 +00:00

47 lines
3.0 KiB
Markdown

# Configured harnesses (operator only)
Authoring needs only the `harness=` config (`references/format.md`). The rest is
for an operator setting up or debugging the execution computer.
OpenCode and Pi run interactive authoring, debugging and model stages; Claude Code
is a chat backend that also runs model stages (`harness=claude`,
`provider=anthropic`, declared tools only); Codex is a chat backend. 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 setup <claude|codex|opencode|pi>` is the single setup path on
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`
forces it) and verifies with the server's own check. For OpenCode/Pi it picks the
interactive harness model and the new-pipeline model; automation passes
`--model PROVIDER/MODEL --pipeline-model PROVIDER/MODEL`, and a non-terminal run
with a missing model fails instead of opening a picker. `harness default
[opencode|pi]` switches defaults; `harness list` shows installed / signed-in /
configured / default status (`--json` adds profiles). Setup reads catalogs and
login state without inference. Changing defaults never rewrites published
definitions or drafts; canceling a picker leaves saved preferences unchanged.
Harness setup/default commands configure the local execution user, not a remote
`--url` server. Pi setup runs no generation check; `provider-check --harness pi
--model PROVIDER/MODEL` is a separate, potentially chargeable check.
Docker image resolution, profile storage, the Docker-aware CLI prefix, Pi sign-in
and OpenCode V2 settlement internals are in `docs/operator-reference.md` in the
source checkout; dated verification is in `docs/verification-history.md`.
A run may override the pinned model at launch: `pipelines run --model
PROVIDER/MODEL` covers every model stage and repeatable `--stage-model
STAGE=PROVIDER/MODEL` overrides one stage (per-stage > whole-run > pinned).
Overrides are validated against the pinned version before the run starts (an
unknown stage key fails naming the valid keys; a non-model stage cannot be
overridden), apply to that run only, and are recorded so `retry` reproduces them.
The effective provider/model is stamped on the step.
Pi stages start a new retained session per visit with explicit tools and a
Pipelines permission extension; ambient extensions, skills, context files, prompt
templates, automatic retries and compaction are disabled. Tool gates are not an
OS sandbox: approved shell can have broad side effects. Usage accumulates across
attempts and visits; missing required accounting fails closed. Session/RPC audit
lives in the execution user's cache under `pipelines/pi-sessions`; unconfirmed
cleanup blocks continuation and retry.