Commit Graph

4 Commits

Author SHA1 Message Date
kami 597a26d551 feat(validation): auto build-gate on terminal freestyle stage (Gate 4 floor)
Closes the COMPLETED-lie where a freestyle stage passes by producing a
schema-valid artifact regardless of whether its build actually succeeded:
a verify stage could run 'npm run build', watch it fail, then self-attest a
build_verified artifact and transition to done. Tool failures never failed
the stage.

The compiler now flags the terminal stage autoBuildGate=true when no stage
declares an explicit build_expectation. Code-ness is decided at runtime, not
compile time (the declared kind is always the generic file_written; only the
written paths reveal code): runExecutionGate folds the FileWritten manifest via
sessionProducedBuildTarget() and promotes to a PROJECT build when a build
manifest (package_json/gradle_module) or an imports_resolve-bearing path was
written, then runs the real command from .correx/project.toml [commands]. A
non-clean exit fails the stage retryably; a docs-only plan is left untouched.

Live-proven (run 3, session 28812b44): gate fired on the real
'npm --prefix frontend run build', exit 2 on a bad tsconfig, RetryAttempted
instead of a false COMPLETED.

Modules green: transitions+workflow 67, kernel 60.
2026-07-07 01:01:12 +04:00
kami 21e01da3ac feat(tasks): task_decompose splits a goal into a dependency-linked graph in one approval
The freestyle analyst can now break a large goal with dependency seams or
independent review/handoff points into a parent epic + DEPENDS_ON-linked children
in a single T2 approval, instead of N separate task_create calls. Parent
DEPENDS_ON every child (completes last); each child IMPLEMENTS parent. Resolves
depends_on by ref or index; rejects cycles, unresolved refs, missing title/goal,
and empty batches; same batch dedup + force_reason convention as task_create.

A session works one active task, so multi-task work is multi-session by
construction: the analyst names the single ready task this run works, the architect
threads only that one, and siblings are claimed by later runs via task_ready
(claim-driven; no scheduler, /tasks/next stays rejected).

Doctrine: analyst_freestyle.md picks one-task-vs-decompose and names the ready
task; architect_freestyle.md threads only that one; plus the L0 policy line.
freestyle_planning.toml analyst gains task_decompose (pinned by
FreestylePlanningWorkflowTest).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-25 10:39:03 +00:00
kami 06c225e3bd feat(tasks): teach agents when to use the task tools
The task tools were registered but had only mechanical descriptions and no
standing policy, so agents knew the tools existed but not when to reach for
them. Lead each of the five descriptions with its trigger (when to use, when
not to) and add a task-tracking convention to .correx/project.toml, which is
rendered into every stage's L0 context.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-24 09:40:44 +00:00
kami 8bf56604c7 chore(examples): root-level workflow descriptions + curated .correx project profile 2026-06-11 21:47:39 +04:00