Skip to content

fix(orch): make /goal availability an empirical check, not predictive - #282

Merged
Data-Wise merged 4 commits into
devfrom
feature/goal-engine-detection
Jul 14, 2026
Merged

fix(orch): make /goal availability an empirical check, not predictive#282
Data-Wise merged 4 commits into
devfrom
feature/goal-engine-detection

Conversation

@Data-Wise

Copy link
Copy Markdown
Owner

Summary

/craft:orch:drive's precondition table listed "/goal available (Claude Code >= v2.1.139)"
as a checkable precondition, alongside a remedy of "Upgrade Claude Code". Live use this session
(driving an approved savant SPEC from a non-CLI harness) showed this check has no way to
actually run: /goal is a native slash command, not an introspectable tool, so no prose
instruction can predict its absence ahead of time — and the remedy shown was actively wrong
advice for that failure class (upgrading Claude Code CLI version does nothing for a session
that isn't running Claude Code CLI at all).

  • Removed the unpredictable precondition-table row.
  • Step 6's real /goal emission now doubles as the availability check: no separate probe (which
    would either be redundant or set a real goal state), just observe the actual attempt.
  • Corrected remedy: assess scope, implement directly by default (matches most single-scope
    specs); --swarm only for specs that genuinely decompose into independent parallel work —
    replacing a bare "use --swarm" pointer that this same session's own grill had already found
    to be an over-broad recommendation.
  • Confirmed via a repo-wide sweep that no sibling /goal-dependent surface (workflow-engine,
    plan-orchestrator) has the same gap — only orch:drive/drive-engine depend on /goal.

Full trace: docs/specs/INVESTIGATE-goal-engine-detection-2026-07-14.md +
docs/specs/GRILL-goal-engine-detection-2026-07-14.md (5 grilled branches, 2 of which
overturned the initial fix idea before landing on this one).

Test plan

  • python3 -m pytest tests/test_craft_plugin.py -k "drive or orch" → 3/3 pass (pre-check,
    targeted)
  • python3 -m pytest tests/test_craft_plugin.py → 25/25 pass (full unit suite, no regressions)
  • Prose-only change (no code/schema touched) — per this repo's tiered testing strategy, unit
    suite is the appropriate tier for a docs/command-instruction change; no e2e/dogfood run needed.

Closes the live gap hit this session driving savant issue #198's SPEC through orch:drive.

…ve one

/goal is a native slash command, not an introspectable tool -- no prose
instruction can reliably predict its absence ahead of time (see
GRILL-goal-engine-detection-2026-07-14.md). Step 6's real condition
emission now doubles as the availability check: no observable effect
means the harness doesn't support /goal, reported with a corrected
remedy (assess scope, implement directly by default; --swarm only for
genuinely parallelizable specs) rather than the old 'Upgrade Claude Code'
advice, which was actively wrong for this failure class.
…eck fix

PR #283 landed on dev after this branch was created, adding a new Step 2
(issue-premise pre-filter) and renumbering every subsequent step. Reconciled
by adopting dev's numbering and re-anchoring this branch's precondition-table
caveat and Step 7 emission-check language at their new positions.
@Data-Wise
Data-Wise merged commit 80013db into dev Jul 14, 2026
5 of 6 checks passed
@Data-Wise
Data-Wise deleted the feature/goal-engine-detection branch July 24, 2026 17:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant