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.
This commit is contained in:
@@ -100,8 +100,8 @@ How the stage service behaves:
|
||||
- `pipelines debug` is unchanged: it opens a fresh interactive harness
|
||||
conversation, not the stage session.
|
||||
|
||||
Claude Code and Codex are chat-only harnesses (stages accept only
|
||||
`harness=opencode` or `harness=pi`), so they need no stage limit. Their chats
|
||||
Codex is a chat-only harness and Claude Code stages (`harness=claude`) run the
|
||||
CLI's own print mode, so neither has a stage limit here. Their chats
|
||||
keep their own defaults. Claude Code has `BASH_MAX_OUTPUT_LENGTH` and
|
||||
`MAX_MCP_OUTPUT_TOKENS` (environment or `--settings`). Codex has
|
||||
`tool_output_token_limit` (config override `-c`). Pi stages keep Pi's built-in
|
||||
@@ -176,7 +176,8 @@ instead of being silently redirected or downgraded to plaintext. `provider-check
|
||||
on a Docker-linked profile runs in-container and preserves the caller's output
|
||||
mode (`--json` only when requested) with exact stdout/exit propagation.
|
||||
|
||||
Put `harness=pi` in a model stage's configs to select Pi. nvim edits definitions
|
||||
Put `harness=pi` in a model stage's configs to select Pi, or `harness=claude`
|
||||
with `provider=anthropic` for Claude Code ([harnesses](harnesses.md#claude-code-stages)). nvim edits definitions
|
||||
or displays debug evidence; it does not execute model stages.
|
||||
|
||||
For bounded review loops, add a fenced `limits` JSON object to the reviewer:
|
||||
|
||||
+46
-4
@@ -8,10 +8,10 @@ harness's own login, which `pipelines harness setup <name>` opens for you.
|
||||
| --- | --- | --- | --- | --- |
|
||||
| OpenCode | yes (default) | yes (default) | queued until the turn ends | yes |
|
||||
| Pi | yes (`harness=pi`) | no | n/a | yes |
|
||||
| Claude Code | no | yes | yes, delivered into the running turn | no |
|
||||
| Claude Code | yes (`harness=claude`) | yes | yes, delivered into the running turn | no |
|
||||
| Codex | no | yes | yes, via `turn/steer` | no |
|
||||
|
||||
Stage configs accept only `harness=opencode` or `harness=pi`.
|
||||
Stage configs accept `harness=opencode`, `harness=pi` or `harness=claude`.
|
||||
|
||||
## Set up harnesses
|
||||
|
||||
@@ -77,6 +77,19 @@ reasoning_effort=high
|
||||
[harnesses and control](harnesses-and-control.md). Use the exact IDs your
|
||||
harness lists (`opencode models`, `pi --list-models`).
|
||||
|
||||
A stage on Claude Code uses the server user's Claude sign-in and a Claude model
|
||||
ID, for example a cheaper model for a small change:
|
||||
|
||||
````markdown
|
||||
```configs
|
||||
harness=claude
|
||||
provider=anthropic
|
||||
model=claude-haiku-5-5
|
||||
```
|
||||
````
|
||||
|
||||
See [Claude Code stages](#claude-code-stages) for what such a stage can do.
|
||||
|
||||
**Per run**, without changing the definition:
|
||||
|
||||
```sh
|
||||
@@ -114,6 +127,7 @@ its own catalog.
|
||||
pipelines doctor # health + OpenCode API discovery, no inference
|
||||
pipelines provider-check --model P/M # one tiny tool-free generation (may cost)
|
||||
pipelines provider-check --harness pi --model P/M
|
||||
pipelines provider-check --harness claude --model anthropic/claude-haiku-5-5
|
||||
python3 scripts/check-pi-rpc.py # Pi RPC and policy, no inference
|
||||
```
|
||||
|
||||
@@ -173,7 +187,7 @@ return to model selection.
|
||||
|
||||
## Claude Code
|
||||
|
||||
**Used for:** chat only.
|
||||
**Used for:** chat, and pipeline stages with `harness=claude` (see [Claude Code stages](#claude-code-stages)).
|
||||
|
||||
**Found by:** `PIPELINES_CLAUDE`, then `PATH`, then `~/.local/bin/claude`,
|
||||
`/opt/homebrew/bin/claude`, `/usr/local/bin/claude`. The server checks again
|
||||
@@ -211,9 +225,37 @@ for the next turn.
|
||||
**Mid-turn messages:** yes. The message is written to the running CLI's stdin
|
||||
and read at its next step. Model changes apply from the next turn.
|
||||
|
||||
### Claude Code stages
|
||||
|
||||
A model stage with `harness=claude`, `provider=anthropic` and
|
||||
`model=<Claude model ID>` runs one `claude -p` process per visit in the run
|
||||
directory, signed in as the server user (the same sign-in the chats use; a run
|
||||
directory that chooses its own account keeps it).
|
||||
|
||||
- **Tools.** Only the tools in the stage's `tools` block exist for the session
|
||||
(`read`, `glob`, `grep`, `edit`, `shell`, `webfetch`, `websearch`). Nothing
|
||||
else is approved: the CLI runs with `--permission-mode dontAsk`, and file
|
||||
edits are approved only below the run directory and the stage's artifacts
|
||||
directory. An undeclared tool or an edit elsewhere is refused by the CLI.
|
||||
- **Not supported; the stage or run is refused, never widened:** a
|
||||
`permissions` block, a run launched with `--write-path`, `delivery=true`
|
||||
(landing stays on OpenCode), and `reasoning_effort` `none` or `minimal`.
|
||||
- **Isolation.** User, project and local Claude Code settings, hooks, MCP
|
||||
servers, plugins and slash commands are not loaded. A `CLAUDE.md` in the run
|
||||
directory is still read by the CLI.
|
||||
- **Usage.** Cost and tokens come from the CLI's final result and count toward
|
||||
stage and run budgets; a result without usage fails a budgeted stage.
|
||||
- **Failures.** Diagnostics are fixed text. A billing, quota or rate-limit
|
||||
refusal stops the run without retries; a missing sign-in says so. The CLI's
|
||||
redacted stream is kept as the session export and evidence.
|
||||
- **Recovery.** A server restart during a Claude Code stage stops that process
|
||||
and fails the visit; it is not reattached.
|
||||
- **Overrides.** `--model` and `--stage-model` must give an
|
||||
`anthropic/<model>` for these stages; the launch is refused otherwise.
|
||||
|
||||
## Codex
|
||||
|
||||
**Used for:** chat only.
|
||||
**Used for:** chat, and pipeline stages with `harness=claude` (see [Claude Code stages](#claude-code-stages)).
|
||||
|
||||
**Found by:** the Codex App Server control socket at
|
||||
`$CODEX_HOME/app-server-control/app-server-control.sock` (default
|
||||
|
||||
Reference in New Issue
Block a user