8000 fix(budget): bind the worker past a session-context line; seed the story's output.md (run 18) by adeelahmad · Pull Request #29 · adeelahmad/aloop · GitHub
[go: up one dir, main page]

Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,18 @@ tag in lockstep. Tag releases as `vMAJOR.MINOR.PATCH`.
### Added
- `gate-supervisor-scope` now also enforces **the supervisor never commits on main**: a `git commit` from the main agent in the main tree while a sprint is live is blocked (a commit inside a task worktree, the initial commit of an unborn repo, `task-worktree merge` and a stale lock pass). Reason: live e2e run 16's `Track Cargo.lock` commit on main traced to nothing; the rule was prose in SKILL.md only. Test: `scripts/test/supervisor-scope.test.py`.

### Fixed
- `budget hook`: the worker's `TASK_ID` is read from the first transcript line that names one, not
the first `user` line — Claude Code now prepends a session-context attachment, which left the
worker unbound and its first `selfcheck` blocked "STORY_DIR unset" (live run 18).
- `budget hook pre` seeds the story's `output.md` with its `type: output` frontmatter before the
worker's first tool call, so a bare `cat >>` of the report block no longer fails the comms gate
(live run 18: 4 blocks). An existing `output.md` is never touched.

### Changed
- SKILL.md: a RED mandate names `tests/common/mod.rs` as the shims' home, never a `src/` path
(one `gate-red-verify` block per live run 14–18 came from a mandate saying "shim in `src/lib.rs`").

## [0.12.0] - 2026-10-18

The first release of **aloop** (Aladdin's Loop), the plugin formerly published as agentic-agile.
Expand Down
2 changes: 1 addition & 1 deletion docs/OVERVIEW.md
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ The model can ignore a skill; it cannot ignore an exit code.
- The north-star run, `make e2e-live YES=1 [INTENT=wordfreq]`: a one-line intent becomes
planned, test-first, gate-verified, merged code in a real Claude Code session with the
approval given up front. Two intents pass every check (semver parser: 11/11, ~$0.65–1.15,
11–19 min; word frequencies with two dependent stories: 13/13, $0.86–1.56, 13–45 min; the last run 12m58s, $0.95, 2 supervisor wakes, 0 plugin-source reads,
11–19 min; word frequencies with two dependent stories: 13/13, $0.79–1.56, 13–45 min; the last two runs $0.95 and $1.03, 2–6 supervisor wakes, 0–2 plugin-source reads,
every merged commit traced to its task by `events trace`). Every run so far has found a gate false positive or a
dead path that unit tests missed; ROADMAP M0.8 lists them.
- One measured real run (*TheNoteBook*, a Go backend): ~17K LOC, 322 tests, 74 commits in 6
Expand Down
Loading
Loading
0