Skip to content

emrg: open_source_prompt requires full-code study before contributing (rant 2026-08-14T15:53:39) - #790

Merged
argszero merged 1 commit into
masterfrom
feature/open-source-prompt-full-code-read
Aug 14, 2026
Merged

emrg: open_source_prompt requires full-code study before contributing (rant 2026-08-14T15:53:39)#790
argszero merged 1 commit into
masterfrom
feature/open-source-prompt-full-code-read

Conversation

@argszero

Copy link
Copy Markdown
Owner

Summary

Host rant 2026-08-14T15:53:39 (emrg): the open-source task prompt must require the contributor to:

  1. Read the complete codebase — not just the target file
  2. Always re-read the latest code before each contribution (no relying on memory/stale versions; 0.3 Source sync guarantees a fresh pull)
  3. Understand the design intent from the repository author's perspective — why the code is designed this way (design rationale, git history/blame, tests as documentation)
  4. Only then consider contributing — the contribution must align with the existing design, not reinvent it

Previously B.2 Study project conventions only read CONTRIBUTING.md / PR template / .github listing — it never required reading the full source, so contributors could jump to implementation without understanding the codebase.

Changes

  • emrg/server/open_source_prompt.md: new B.2b Read the full codebase (MUST before contributing) section inserted between B.2 and B.3 — full-code read requirements, author-perspective design-intent analysis, and the "understand the design before contributing" gate
  • tests/test_scheduler.py: +1 regression test test_open_source_template_full_code_study_b2b asserting all four requirements render (section presence / full-code read / latest-code re-read / author-perspective / contribute-only-after-understanding)
  • Agent.md: pytest count 805 → 806 (doc-count guard)

Verification

  • uv run pytest tests/ -v: 806 passed (805 + 1 new)
  • Import check + CLI help: green

@argszero argszero left a comment

Copy link
Copy Markdown
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

✅ LGTM — cycle 703

Verified:

  • New B.2b section covers all 4 rant requirements: full-code read / always re-read latest code / author-perspective design intent / contribute only after understanding
  • Regression test test_open_source_template_full_code_study_b2b passes (positive discrimination: asserts section + all 4 requirement phrases render)
  • Local: uv run pytest tests/ -v 806 passed; import + CLI checks green
  • CI: test + test-windows both SUCCESS (run 31781964559)

@argszero argszero left a comment

Copy link
Copy Markdown
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

✅ LGTM — cycle

Verified independently:

  • B.2b section inserted between B.2 and B.3 covers all 4 rant requirements: full-code read / always re-read latest code / author-perspective design intent / contribute only after understanding
  • Regression test test_open_source_template_full_code_study_b2b passes locally (1/1)
  • Agent.md pytest count 805 → 806 synced (doc-count guard)

@argszero argszero left a comment

Copy link
Copy Markdown
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

✅ LGTM — cycle 704

Independent re-verification:

  • Diff clean: 3 files 47+/1- (open_source_prompt.md B.2b section, test_scheduler.py regression test, Agent.md count 805→806)
  • B.2b covers all 4 rant requirements: full-code read / always re-read latest / author-perspective design intent / contribute only after understanding
  • Test test_open_source_template_full_code_study_b2b passes locally; pytest 806 all green; import + CLI green
  • CI test + test-windows both SUCCESS — 3 consecutive ✅ (cycles 703, parallel, 704)

@argszero argszero left a comment

Copy link
Copy Markdown
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

✅ LGTM — cycle

Third consecutive approval (different cycles: 703, R1712, R1713). Re-verified fresh this cycle:

  • PR head 65ba0ae unchanged, mergeable
  • uv run pytest tests/test_scheduler.py::test_open_source_template_full_code_study_b2b → 1 passed
  • No ❌ in history; merge condition satisfied

@argszero
argszero merged commit b2c2db9 into master Aug 14, 2026
2 checks passed
argszero added a commit that referenced this pull request Aug 14, 2026
…795)

Rant 2026-08-14T22:13:57: promote_prompt.md §0 only read the state
file + project config — the promoter had zero knowledge of the actual
project source/latest progress, while open-source tasks (#790) must
study the full codebase. Asymmetric: same EMRG contributes after
deep code study but promotes from a one-line description → stale or
wrong answers to community questions (violating red lines #1/#7).

Changes:
- promote_prompt.md new §0.4 'Learn the project's latest state (MUST
  every round)': git fetch + last 10 commits, read repo root, scan key
  modules, refresh cognition; any capability claim must come from
  just-verified latest state (mirrors open_source B.2b)
- §3 Step 2: Good-example note — feature descriptions must come from
  §0.4-verified state, not stale memory/description guesses
- §4 state file: new 'last learned' field (time + commit HEAD) for
  knowledge freshness
- §5 reflection Q3: must record what project info was learned this
  round (commit range / modules read)
- +1 template render test (7 positive assertions); Agent.md 810->811

Co-authored-by: EMRG Evolution <emrg@argszero.dev>
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