<feed xmlns='http://www.w3.org/2005/Atom'>
<title>claudomator.git/internal/executor/stream_test.go, branch story/task-project-fk</title>
<subtitle>claudomator — task automation server
</subtitle>
<id>https://git.terst.org/claudomator.git/atom?h=story%2Ftask-project-fk</id>
<link rel='self' href='https://git.terst.org/claudomator.git/atom?h=story%2Ftask-project-fk'/>
<link rel='alternate' type='text/html' href='https://git.terst.org/claudomator.git/'/>
<updated>2026-03-18T07:55:27+00:00</updated>
<entry>
<title>fix: address round 3 review feedback for container execution</title>
<updated>2026-03-18T07:55:27+00:00</updated>
<author>
<name>Peter Stone</name>
<email>thepeterstone@gmail.com</email>
</author>
<published>2026-03-18T07:24:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.terst.org/claudomator.git/commit/?id=e1be377c851f1e7ce594fa3de6c429354bcedcce'/>
<id>urn:sha1:e1be377c851f1e7ce594fa3de6c429354bcedcce</id>
<content type='text'>
- Fix push failure swallowing and ensure workspace preservation on push error
- Fix wrong session ID in --resume flag and BlockedError
- Implement safer shell quoting for instructions in buildInnerCmd
- Capture and propagate actual Claude session ID from stream init message
- Clean up redundant image resolution and stale TODOs
- Mark ADR-005 as Superseded
- Consolidate RepositoryURL to Task level (removed from AgentConfig)
- Add unit test for session ID extraction in parseStream
</content>
</entry>
<entry>
<title>executor: detect stream-level failures when claude exits 0</title>
<updated>2026-03-05T22:53:02+00:00</updated>
<author>
<name>Peter Stone</name>
<email>thepeterstone@gmail.com</email>
</author>
<published>2026-03-05T22:53:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.terst.org/claudomator.git/commit/?id=4c0ee5c215b6b1965ee2ac30d9341f5e8fb6f569'/>
<id>urn:sha1:4c0ee5c215b6b1965ee2ac30d9341f5e8fb6f569</id>
<content type='text'>
Rename streamAndParseCost → parseStream (returns float64, error).
Detect two failure modes that claude reports via exit 0:
- result message with is_error:true
- tool_result permission denial ("haven't granted it yet")

Also fix cost extraction to read total_cost_usd from the result
message (the actual field name), keeping cost_usd as legacy fallback.

Co-Authored-By: Claude Sonnet 4.6 &lt;noreply@anthropic.com&gt;
</content>
</entry>
</feed>
