Commit Graph

6848 Commits

Author SHA1 Message Date
YeonGyu-Kim 8f09c02cc0 docs: scrub remaining references to migrated files
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 19:16:03 +09:00
YeonGyu-Kim d18cadb1ab test(ultrawork): add byte-exact characterization test
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 19:16:03 +09:00
YeonGyu-Kim e0b37b46d5 test(prometheus): add byte-exact characterization test
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 19:16:03 +09:00
YeonGyu-Kim 9d204250ee docs(keyword-detector): rewrite AGENTS.md for prompts-core migration
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 19:16:02 +09:00
YeonGyu-Kim 87e28d2607 docs(prometheus): rewrite AGENTS.md for thin-loader structure
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 19:16:02 +09:00
YeonGyu-Kim 2ea7c49208 Merge pull request #4390 from code-yeongyu/refactor/prometheus-to-prompts-core
refactor(prometheus): extract agent prompt sections to packages/prompts-core (PR4)
2026-05-24 18:47:07 +09:00
YeonGyu-Kim 1f32b885d8 refactor(prometheus): remove migrated section TypeScript files 2026-05-24 18:44:46 +09:00
YeonGyu-Kim 8fc429a5de refactor(prometheus): load prompt variants from prompts-core 2026-05-24 18:44:24 +09:00
YeonGyu-Kim 3806d93dbc feat(prompts-core): wire Prometheus variant table 2026-05-24 18:44:24 +09:00
YeonGyu-Kim fa0500e970 feat(prompts-core): add Prometheus prompt markdown variants 2026-05-24 18:44:24 +09:00
YeonGyu-Kim 4749eab203 Merge pull request #4389 from code-yeongyu/refactor/mode-prompts-to-prompts-core
refactor(mode-prompts): extract search/analyze/team/hyperplan to packages/prompts-core (PR3)
2026-05-24 18:38:03 +09:00
YeonGyu-Kim 803f030b5b Merge remote-tracking branch 'origin/dev' into refactor/mode-prompts-to-prompts-core
# Conflicts:
#	packages/prompts-core/src/index.ts
2026-05-24 18:35:36 +09:00
YeonGyu-Kim 528f083f5a Merge pull request #4388 from code-yeongyu/refactor/atlas-to-prompts-core
refactor(atlas): extract agent prompt variants to packages/prompts-core with runtime injection (PR5)
2026-05-24 18:33:07 +09:00
YeonGyu-Kim 63ef72d1b9 docs(agents): document prompts-core mode prompts
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:33:00 +09:00
YeonGyu-Kim 80361c05ab chore(prompts-core): wire markdown prompt packaging
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:32:53 +09:00
YeonGyu-Kim 2c8e2dac41 refactor(mode-prompts): migrate hyperplan prompt
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:32:45 +09:00
YeonGyu-Kim e79baf5910 refactor(mode-prompts): migrate team prompt
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:32:35 +09:00
YeonGyu-Kim 3b7f51d568 refactor(mode-prompts): migrate analyze prompt
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:32:19 +09:00
YeonGyu-Kim 5cefbdbb6d refactor(mode-prompts): migrate search prompt
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:31:17 +09:00
YeonGyu-Kim c187dba56b test(keyword-detector): capture mode prompt baselines
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:30:53 +09:00
YeonGyu-Kim 8451ecd15e docs(atlas): document prompts-core prompt ownership
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:29:36 +09:00
YeonGyu-Kim 582c768b94 refactor(atlas): remove migrated TypeScript prompts
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:29:25 +09:00
YeonGyu-Kim 4975c354b2 refactor(atlas): load prompt variants from prompts-core
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:29:12 +09:00
YeonGyu-Kim 96a9365044 build(prompts-core): bundle markdown prompt variants
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:29:05 +09:00
YeonGyu-Kim 91351d73fd feat(prompts-core): support bundled prompt sources
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:28:57 +09:00
YeonGyu-Kim b77fed28ef feat(prompts-core): add Atlas Opus 4.7 prompt markdown
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:28:49 +09:00
YeonGyu-Kim 2adcec8f2d feat(prompts-core): add Atlas Kimi prompt markdown
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:28:49 +09:00
YeonGyu-Kim d5995b385a feat(prompts-core): add Atlas Gemini prompt markdown
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:28:49 +09:00
YeonGyu-Kim 1923761166 feat(prompts-core): add Atlas GPT prompt markdown
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:28:49 +09:00
YeonGyu-Kim 565d099495 feat(prompts-core): add Atlas default prompt markdown
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:28:49 +09:00
YeonGyu-Kim a92e25a196 test(atlas): add prompt byte preservation baselines
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:28:35 +09:00
YeonGyu-Kim 66445241fe Merge pull request #4386 from code-yeongyu/refactor/ultrawork-to-prompts-core
refactor(ultrawork): extract ultrawork prompts to packages/prompts-core (PR2)
2026-05-24 18:27:11 +09:00
YeonGyu-Kim 79beeeee1f docs: document ultrawork prompt markdown location
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:20:33 +09:00
YeonGyu-Kim d217efc195 build(prompts): inline markdown prompt imports
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:20:27 +09:00
YeonGyu-Kim e772c46819 refactor(ultrawork): move planner prompt to prompts-core
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:20:18 +09:00
YeonGyu-Kim e51acd0ad3 refactor(ultrawork): move gemini prompt to prompts-core
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:20:11 +09:00
YeonGyu-Kim a818bbd99c refactor(ultrawork): move gpt prompt to prompts-core
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:20:04 +09:00
YeonGyu-Kim 9c366cce3a refactor(ultrawork): move default prompt to prompts-core
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:19:56 +09:00
YeonGyu-Kim 39b3cbcbb5 chore(ultrawork): capture prompt baseline hashes
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 18:19:49 +09:00
YeonGyu-Kim 46ad6bfdb4 Merge pull request #4385 from code-yeongyu/refactor/prompts-core-foundation
refactor(prompts-core): add packages/prompts-core foundation with model-family detector relocation
2026-05-24 17:55:32 +09:00
YeonGyu-Kim 436c618706 fix(prompts-core): block prompt path traversal
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 17:50:18 +09:00
YeonGyu-Kim 74d5f7018d chore(prompts-core): wire package typecheck
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 17:28:09 +09:00
YeonGyu-Kim da0fa83f6c test(prompts-core): audit opencode coupling
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 17:28:09 +09:00
YeonGyu-Kim c44a6bdb2a feat(prompts-core): add prompt loader
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 17:28:09 +09:00
YeonGyu-Kim 6301bcf059 feat(prompts-core): add variant resolver
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 17:17:08 +09:00
YeonGyu-Kim 4338ddb898 feat(prompts-core): add package skeleton
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 17:16:49 +09:00
YeonGyu-Kim 87de056308 refactor(model-core): move model family detectors
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-24 17:16:40 +09:00
YeonGyu-Kim e1e9f348f0 Merge pull request #4382 from code-yeongyu/feat/ultrawork-prompt-tdd-evidence-tightening
feat(ultrawork): enforce TDD, scenario contract, durable notepad, reviewer gate
2026-05-24 15:55:43 +09:00
YeonGyu-Kim d073bf1bdf feat(ultrawork): enforce TDD, scenario contract, durable notepad, reviewer gate
Closes five gaps in the ultrawork prompt versus codex-plugins' parallel
directive, applied to all three model variants (default/Claude, GPT, Gemini)
with prompt-engineering entropy gate (each addition encodes a distinct
binding boolean, not narrative reinforcement):

1. TDD-MANDATORY (was conditional "when test infrastructure exists"):
   every production change follows RED -> GREEN -> SURFACE. Failing test
   first, capture assertion msg, smallest change to flip green, exercise
   real surface, capture artifact. Exemption whitelist: formatting /
   comment-only / version bump / rename-only, each must be justified
   in writing; unjustified exemption = rejection.

2. Scenario contract (was free-form Test Plan Template): require 3+
   scenarios upfront covering happy path, edge (boundary / empty /
   malformed / concurrent), adjacent-surface regression. Each scenario
   binds a binary pass condition, a real-surface artifact source, and
   a test file + test id written test-first.

3. RED->GREEN evidence capture (was "all tests pass"): every scenario
   requires TWO captured artifacts -- RED assertion msg before the
   change AND GREEN assertion msg after -- alongside the real-surface
   artifact (tmux / curl / browser / Playwright / computer-use /
   CLI stdout / parsed config / DB diff). Tests are the floor (always
   required); surface artifact is the ceiling (also required).

4. Durable notepad: mktemp -t ulw-*.md with append-only sections
   (Plan, Scenarios, Now, Todo, Findings, Learnings). Survives context
   loss; resume by re-reading.

5. Reviewer gate: trigger when user said strictly / rigorously /
   "deeply", or task touches 3+ files / 20+ turns / 30+ min, or it is
   refactor / migration / perf / security work. Reviewer verdict is
   binding ("looks good but..." = rejection). Loop until unconditional
   approval.

Plus: TODO format upgraded from vague "track every step" to atomic
`path: <action> for <scenario-id> -- verify by <check>` with a GOOD
test-first / impl pair example and a BAD list including
"production code before its failing test".

Per-variant adaptation:
- default.ts (Claude): full structured sections.
- gpt.ts (GPT-5.x): outcome-first prose, shorter prose per gpt-5.5 guide.
- gemini.ts: explicit enforcement framing + anti-optimism checkpoint
  upgraded with a TDD-violation question (#7).

Verified by:
- bun test src/hooks/keyword-detector/ (119 pass / 0 fail).
- lsp_diagnostics clean on all three files.
- Module-load smoke test confirms each exported message string parses
  and contains the new section anchors (TDD MANDATORY, SCENARIO
  CONTRACT, DURABLE NOTEPAD, REVIEWER GATE).

Char deltas (directive body only):
- default 13646 -> 17144 (+26%)
- gpt     6740  -> 9215  (+37%, was the leanest start)
- gemini  14196 -> 16136 (+14%)

Existing tests only assert presence of "ULTRAWORK MODE ENABLED!" which
is preserved verbatim in every variant.
2026-05-24 15:48:59 +09:00
YeonGyu-Kim 39a549a3df Merge pull request #4381 from code-yeongyu/fix/team-mode-closure-prompts
fix(team-mode): make lead close teams on its own initiative
2026-05-24 15:37:28 +09:00