feat: AutoResearch framework + V2EX test suite (60 tasks, SKILL.md optimization)#717
Merged
feat: AutoResearch framework + V2EX test suite (60 tasks, SKILL.md optimization)#717
Conversation
AutoResearch framework (Karpathy-style autonomous iteration): - engine.ts: 8-phase loop (review → modify → commit → verify → guard → decide → log) - config.ts: typed config + CLI parser + metric extraction - logger.ts: TSV append-only results log - commands/run.ts: main loop spawning Claude Code per iteration - commands/plan.ts: interactive config wizard - commands/fix.ts: auto-detect broken state, iteratively fix - commands/debug.ts: hypothesis-driven debugging for failing tasks V2EX test suite (5 layers, 40 tasks): - L1 Atomic (10): open, state, click, scroll, eval, back, wait - L2 Single Page (10): hot topics, node list, topic meta, pagination - L3 Multi-Step (10): click-read, navigate-node, tab-then-topic, pagination - L4 Write Ops (5): reply typing, favorite detection, form detection - L5 Complex Chain (5): cross-page collect, multi-node compare, full workflow Presets: operate-reliability, skill-quality, v2ex-reliability
- Fix v2ex-collect-hot-authors selector (pathname-based member link detection) - Fix v2ex-wait-text judge (accept "appeared") - Fix trailing commas in eval step strings - Add 20 harder tasks: state+click interaction + long chain workflows - Baseline: 60/60 across all layers
…e turns - Add Rule #7: minimize total tool calls (3-5 per task, not 15-20) - Strengthen Rule #5: chain aggressively with && - Add explicit good/bad chaining examples - Add click+wait+state chaining pattern - Add type+verify chaining pattern Before: 21 turns for complex V2EX reply task After: 12 turns for same task (-43% turns, -28% cost)
just-buer
pushed a commit
to just-buer/opencli
that referenced
this pull request
Apr 8, 2026
…timization) (jackwener#717) * feat: AutoResearch framework + V2EX test suite (40 tasks) AutoResearch framework (Karpathy-style autonomous iteration): - engine.ts: 8-phase loop (review → modify → commit → verify → guard → decide → log) - config.ts: typed config + CLI parser + metric extraction - logger.ts: TSV append-only results log - commands/run.ts: main loop spawning Claude Code per iteration - commands/plan.ts: interactive config wizard - commands/fix.ts: auto-detect broken state, iteratively fix - commands/debug.ts: hypothesis-driven debugging for failing tasks V2EX test suite (5 layers, 40 tasks): - L1 Atomic (10): open, state, click, scroll, eval, back, wait - L2 Single Page (10): hot topics, node list, topic meta, pagination - L3 Multi-Step (10): click-read, navigate-node, tab-then-topic, pagination - L4 Write Ops (5): reply typing, favorite detection, form detection - L5 Complex Chain (5): cross-page collect, multi-node compare, full workflow Presets: operate-reliability, skill-quality, v2ex-reliability * test: V2EX test suite 60/60 — fix selectors, add harder tasks - Fix v2ex-collect-hot-authors selector (pathname-based member link detection) - Fix v2ex-wait-text judge (accept "appeared") - Fix trailing commas in eval step strings - Add 20 harder tasks: state+click interaction + long chain workflows - Baseline: 60/60 across all layers * docs: optimize SKILL.md for efficiency — aggressive chaining, minimize turns - Add Rule jackwener#7: minimize total tool calls (3-5 per task, not 15-20) - Strengthen Rule jackwener#5: chain aggressively with && - Add explicit good/bad chaining examples - Add click+wait+state chaining pattern - Add type+verify chaining pattern Before: 21 turns for complex V2EX reply task After: 12 turns for same task (-43% turns, -28% cost)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
AutoResearch Framework + V2EX/Zhihu Test Suites + 10 Rounds Iteration
AutoResearch Framework (Karpathy-style)
engine.ts— 8-phase autonomous loopconfig.ts+logger.ts— typed config + TSV loggingcommands/run.ts,plan.ts,fix.ts,debug.tsTest Suites — 194 total tasks, 100% pass rate
Layer 2 E2E Results (Claude Code + SKILL.md)
Average: 6.6 turns, $0.27/task (before SKILL.md optimization: 21 turns)
10 Rounds of AutoResearch Iteration
SKILL.md Optimization