Run tasks directly with language-independent project tools

This commit is contained in:
2026-10-09 01:48:46 +01:00
parent 998b0941d3
commit ed93d055bf
23 changed files with 170 additions and 156 deletions
+12 -8
View File
@@ -102,20 +102,24 @@ transient client logs are presentation, not separate server capabilities.
```sh
cd ~/repos/project
pipelines run "bug fix" "Fix the layout" --yes --json
pipelines run "bug fix" "Fix the layout" --yes --json --wait --timeout 10m
pipelines run "bug fix" "Fix the layout" --yes --json \
--allow-tools --write-paths internal/example.go --request-key my-unique-task
pipelines run "bug fix" "Fix the layout" --json
pipelines run "bug fix" "Fix the layout" --json --wait --timeout 10m
pipelines run "bug fix" "Fix the layout" --json --request-key my-unique-task
```
Runs default to the client's current directory and latest accepted version.
The server resolves that directory without a repository allowlist. `--version` chooses
an immutable version in JSON mode. `--yes` never grants tools implicitly.
Go-specific file editing and restricted Go shell checks remain in effect.
an immutable version in JSON mode. Starting a run enables its stage-declared tools
without a second approval. Editing supports all file types and new files within
the run directory; no file list is required. Shell commands use the repository's
actual tooling. `--write-paths` is an optional narrower scope, not a prerequisite.
`--yes` and `--allow-tools` remain compatibility flags but are not required.
`--wait` polls until terminal status, returns nonzero on failure/cancellation,
and does not cancel a run when waiting times out. Reuse `--request-key` to prevent
duplicate work. Without JSON, `run` opens the existing interactive composer and
live inspector; Enter inserts a newline, Ctrl+S continues.
duplicate work. A supplied pipeline/task starts immediately with a live inspector.
When a task is omitted, Enter inserts a newline and Ctrl+S runs the composed task.
There is no file-list question or typed RUN confirmation. Shell runs with your
user's authority: the run directory and tool policy are not an OS sandbox.
JSON results go to stdout, errors to stderr (JSON error envelopes when requested),
and failures exit nonzero. Export/template `--source` deliberately prints raw
+9
View File
@@ -56,3 +56,12 @@ reopened the same file through a mock OpenCode executable, and explicitly submit
it while retaining the draft. Plain unnamed CLI creation invoked the mock exactly
once. Real model-driven authoring/questions and native skill loading during a
model turn remain **not tested**; global skill discovery was tested without inference.
An installed-binary integration check executed a Bash/QML fixture through a mock
OpenCode backend: it changed README/QML, created a new text file, and actually ran
`bash -n install.sh`. Both JSON and PTY supplied-task runs started without approval
flags, file lists, or typed confirmation, in the invocation directory rather than
the server directory. Permission regression tests cover language-neutral shell,
project file types/new files, optional narrower scopes, and outside-edit denials.
Real model/tool-permission enforcement remains **not tested**. Shell uses the host
user's authority; these policies are not an OS sandbox.
+2 -2
View File
@@ -45,8 +45,8 @@ artifacts=markdown,files
receipts/failures appear in the selected run stage's **Metadata**, separately
from output. They do not change routing or convert a successful stage into a
failed run. A crash can leave a `sending` receipt with uncertain delivery;
notifications are not replayed during recovery. Go checks/file edits still
require manual approval; this setting does not grant extra tool access.
notifications are not replayed during recovery. Tool access follows the stage's
declared tools; notification settings do not grant additional tools.
## Explicit delivery stage (optional)