claudomator.git/internal/api/elaborate_test.go, branch story/task-project-fk

fix: story tasks get Project field; elaborate reads worklog; deploy chmod scripts

2026-03-26T04:10:35+00:00

- handleApproveStory: set Project = input.ProjectID on tasks and subtasks so the executor can resolve RepositoryURL from the project registry (was causing "task has no repository_url" on every story task) - elaborate.go: read .agent/worklog.md instead of SESSION_STATE.md for project context injected into elaboration prompts - deploy: explicitly chmod +x all scripts before restart (same root cause as the binary execute-bit loss — chown -R was stripping it) Co-Authored-By: Claude Sonnet 4.6

fix: repair test regressions and add pre-commit/pre-push verification gates

2026-03-16T19:46:44+00:00

Fix four pre-existing bugs exposed after resolving a build failure: - sandboxCloneSource: accept any URL scheme for origin remote (was filtering out https://) - setupSandbox callers: fix := shadow variable so sandboxDir is set on BlockedError - parseGeminiStream: parse result lines to return execution errors and cost - TestElaborateTask_InvalidJSONFromClaude: stub Gemini fallback so test is hermetic Add verification infrastructure: - scripts/verify: runs go build + go test -race, used by hooks and deploy - scripts/hooks/pre-commit: blocks commits that don't compile - scripts/hooks/pre-push: blocks pushes where tests fail - scripts/install-hooks: symlinks version-controlled hooks into .git/hooks/ - scripts/deploy: runs scripts/verify before building the binary Co-Authored-By: Claude Sonnet 4.6

fix: only write RAW_NARRATIVE.md when user explicitly provides project_dir

2026-03-13T05:27:58+00:00

Previously appendRawNarrative was called with the server's default workDir (os.Getwd()) when no project_dir was in the request, causing test runs and any elaboration without a project to pollute the repo's own RAW_NARRATIVE.md. The narrative is per-project human input — only write it when the caller explicitly specifies which project they're working in. Co-Authored-By: Claude Sonnet 4.6

feat: post-elaboration sanity check for tools, acceptance criteria, and dev practices

2026-03-13T03:14:53+00:00

Add sanitizeElaboratedTask() called after every elaboration response: - Infers missing allowed_tools from instruction keywords (Write/Edit/Read/Bash/Grep/Glob) - Auto-adds Read when Edit is present - Appends Acceptance Criteria section if none present - Appends TDD reminder for coding tasks without test mention Also tighten buildElaboratePrompt to require acceptance criteria and list concrete tool examples, reducing how often the model omits tools. Fixes class of failures where agents couldn't create files because the elaborator omitted Write from allowed_tools. Co-Authored-By: Claude Sonnet 4.6

feat: append verbatim user input to docs/RAW_NARRATIVE.md

2026-03-10T09:33:55+00:00

The elaborator now logs every user prompt to docs/RAW_NARRATIVE.md within the project directory. This is done in a background goroutine to ensure it doesn't delay the response.

feat: include project context in elaborator prompt

2026-03-10T09:29:02+00:00

The elaborator now reads CLAUDE.md and SESSION_STATE.md from the project directory (if they exist) and prepends their content to the user prompt. This allows the AI to generate tasks that are more context-aware.

merge: pull latest from master and resolve conflicts

2026-03-08T21:03:50+00:00

- Resolve conflicts in API server, CLI, and executor. - Maintain Gemini classification and assignment logic. - Update UI to use generic agent config and project_dir. - Fix ProjectDir/WorkingDir inconsistencies in Gemini runner. - All tests passing after merge.

feat: rename working_dir→project_dir; git sandbox execution

2026-03-08T20:16:00+00:00

- ClaudeConfig.WorkingDir → ProjectDir (json: project_dir) - UnmarshalJSON fallback reads legacy working_dir from DB records - New executions with project_dir clone into a temp sandbox via git clone --local - Non-git project_dirs get git init + initial commit before clone - After success: verify clean working tree, merge --ff-only back to project_dir, remove sandbox - On failure/BLOCKED: sandbox preserved, path included in error message - Resume executions run directly in project_dir (no re-clone) Co-Authored-By: Claude Sonnet 4.6

test(api): update elaborate and validate tests to use AgentConfig

2026-03-08T06:27:34+00:00

Fix working_dir failures: validate path early, remove hardcoded /root

2026-03-03T21:22:30+00:00

executor/claude.go: stat working_dir before cmd.Start() so a missing or inaccessible directory surfaces as a clear error ("working_dir \"/bad/path\": no such file or directory") rather than an opaque chdir failure wrapped in "starting claude". api/elaborate.go: replace the hardcoded /root/workspace/claudomator path with buildElaboratePrompt(workDir) which injects the server's actual working directory (from os.Getwd() at startup). Empty workDir tells the model to leave working_dir blank. Co-Authored-By: Claude Sonnet 4.6