fix(ce-plan): close exit gates and honor user-named resources (#597)
Some checks failed
CI / pr-title (push) Has been cancelled
CI / test (push) Has been cancelled
Release PR / release-pr (push) Has been cancelled
Release PR / publish-cli (push) Has been cancelled

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Trevin Chow
2026-04-18 15:19:04 -07:00
committed by GitHub
parent 27cbaf8161
commit d8e87c1790
2 changed files with 6 additions and 6 deletions

View File

@@ -7,9 +7,10 @@ This file is loaded when ce:plan detects a non-software task (Phase 0.1b). It re
The detection stub in SKILL.md routes here for anything that isn't clearly software. Verify the classification is correct before proceeding:
- **Is this actually a software task?** The key distinction is task-type, not topic-domain. A study guide about Rust is non-software (producing educational content). A Rust library refactor is software (modifying code). If this is actually software, return to Phase 0.2 in the main SKILL.md.
- **Is this a quick-help request, not a planning task?** Error messages, factual questions, and single-step tasks don't need a plan. Respond directly and exit. Examples: "zsh: command not found: brew", "what's the capital of France."
- **Pipeline mode?** If invoked from LFG, SLFG, or any `disable-model-invocation` context: output "This is a non-software task. The LFG/SLFG pipeline requires ce:work, which only supports software tasks. Use `/ce:plan` directly for non-software planning." and stop.
Once past these checks, commit to producing a plan. Do not exit because the task looks like a "lookup" or "research question" — the user invoked `ce:plan` because they want a structured output.
---
## Step 1: Assess Ambiguity and Research Need
@@ -32,7 +33,7 @@ When research is recommended, do it — don't just offer. Stale recommendations
**Research decomposition pattern:**
1. Identify 2-5 independent research questions based on the task. Good questions target facts the model is least confident about: current prices, hours, availability, recent changes, seasonal specifics.
2. Dispatch parallel web searches (one per question). Keep queries broad at first, then narrow based on findings.
2. Dispatch parallel research. Prefer user-named surfaces first per Core Principle 8 in SKILL.md; fall back to web search for questions those surfaces don't cover.
3. Collate findings into a brief research summary before proceeding to planning.
Example for "plan a date night in Seattle this Saturday":