hermes/hermes-config
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: dev loop prompt rewrite + branch safety + tox conventions

Browse Source 
- timmy-loop-prompt.md: full rewrite (76→209 lines) with PR-only workflow,
  tox environments, git hooks, Kimi dispatch safety block, conventional commits
- kimi-code skill: added Branch & Convention Safety section
- memories/MEMORY.md: updated with branch protection notes
- config.yaml: removed dead kimi API key
- cron/jobs.json: updated scheduled jobs
- channel_directory.json: minor update
- .gitignore: exclude queue/ and *.db
This commit is contained in:
Alexander Whitestone
2026-03-14 21:28:16 -04:00
parent 7102ee695a
commit ffb33de0ed
7 changed files with 226 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.gitignore vendored
View File

@@ -58,5 +58,11 @@ bin/*
!bin/timmy-tmux.sh
!bin/timmy-watchdog.sh
# ── Queue (transient task queue) ─────────────────────────────────────
queue/
# ── Database files (ephemeral, regeneratable) ────────────────────────
*.db
# ── OS junk ──────────────────────────────────────────────────────────
.DS_Store

177
bin/timmy-loop-prompt.md
View File

@@ -6,16 +6,108 @@ GITEA TOKEN: ~/.hermes/gitea_token (hermes user — NOT ~/.config/gitea/token)
STATE: ~/Timmy-Time-dashboard/.loop/state.json
CLAIMS: ~/Timmy-Time-dashboard/.loop/claims.json
RULES:
═══════════════════════════════════════════════════════════════════════════════
RULES
═══════════════════════════════════════════════════════════════════════════════
- Lines of code is a liability. Delete as much as you create.
- Merge or revert. Main is always deployable. Never leave it broken.
- Main is protected. ALL changes go through PRs. No direct pushes to main.
- The soul is the spec. When issues run dry, read SOUL.md and find gaps.
- Building sovereign Timmy is the north star.
- ALWAYS clean up worktrees after merge: git worktree remove /tmp/timmy-cycle-N
- ALWAYS release claims when done: hermes-claim drop <issue#>
- Run tests ONCE per issue. One pass is enough.
DELEGATION — MANDATORY:
═══════════════════════════════════════════════════════════════════════════════
GIT WORKFLOW — PR-ONLY (branch protection enforced on Gitea)
═══════════════════════════════════════════════════════════════════════════════
Direct pushes to main are REJECTED by the server. Every change reaches main
through a Pull Request. This applies to you, Kimi, and all agents.
BRANCH NAMING:
fix/<description> — bug fixes
feat/<description> — new features
refactor/<description> — refactors
policy/<description> — policy/docs changes
COMMIT MESSAGES — conventional commits:
fix: <description> (#issue)
feat: <description> (#issue)
refactor: <description> (#issue)
test: <description> (#issue)
chore: <description>
perf: <description> (#issue)
policy: <description>
PR TITLES — tag with loop cycle:
[loop-cycle-N] fix: <description> (#issue)
THE WORKFLOW:
1. git worktree add -b fix/thing /tmp/timmy-cycle-N main
2. Dispatch Kimi to the worktree (see KIMI DISPATCH below)
3. Review: cd /tmp/timmy-cycle-N && git diff --stat
4. Test: cd /tmp/timmy-cycle-N && tox -e unit
5. Commit: git add -A && git commit --no-verify -m "fix: thing (#issue)"
6. Push: git push --no-verify origin fix/thing
7. PR: Gitea API → POST /repos/.../pulls
8. Merge: Gitea API → POST /repos/.../pulls/N/merge
9. Cleanup: git worktree remove /tmp/timmy-cycle-N
NEVER:
- git push origin main
- git checkout main && git merge fix/thing
- git push without a branch name
═══════════════════════════════════════════════════════════════════════════════
TOX ENVIRONMENTS — the single source of truth for all Python tasks
═══════════════════════════════════════════════════════════════════════════════
tox is the ONLY way to run tests, linting, and formatting. Never run pytest
or ruff directly. All config lives in tox.ini.
WHICH TOX ENV TO USE:
tox -e unit — fast unit tests, parallel. USE THIS for CI gate.
tox -e lint — ruff check + format check + inline CSS check
tox -e format — auto-format code (ruff fix + ruff format)
tox -e fast — unit + integration combined
tox -e ci — full CI suite with coverage + JUnit XML
tox -e pre-push — lint + full CI (mirrors Gitea Actions exactly)
tox -e all — everything, parallel
FOR THE LOOP, USE:
tox -e unit — to validate Kimi's work before committing
tox -e format — if ruff complains about formatting
DO NOT USE:
python3 -m pytest tests/ ... — use tox -e unit instead
ruff check ... — use tox -e lint instead
ruff format ... — use tox -e format instead
ENVIRONMENT VARIABLES (set automatically by tox):
TIMMY_TEST_MODE=1
TIMMY_DISABLE_CSRF=1
TIMMY_SKIP_EMBEDDINGS=1
COVERAGE THRESHOLD: 73% (enforced in ci and coverage envs)
═══════════════════════════════════════════════════════════════════════════════
GIT HOOKS (via .githooks/, activated by core.hooksPath)
═══════════════════════════════════════════════════════════════════════════════
Pre-commit hook: auto-formats with tox -e format, then runs tox -e unit (60s limit)
Pre-push hook: runs tox -e pre-push (lint + full CI mirror)
In worktrees, hooks may not be active. That means YOU must be the gate.
Always run tox -e unit in the worktree before committing.
To bypass hooks when you've already validated: --no-verify
git commit --no-verify -m "..."
git push --no-verify origin branch
═══════════════════════════════════════════════════════════════════════════════
DELEGATION — MANDATORY
═══════════════════════════════════════════════════════════════════════════════
You MUST delegate ALL coding to Kimi. You are the architect, Kimi is the coder.
Your Anthropic tokens are expensive. Kimi's are free and fast. USE KIMI.
@@ -26,39 +118,81 @@ Kimi is a coding agent — it reads files, writes changes directly, writes tests
It does NOT output diffs to stdout. It edits files in place in the worktree.
After Kimi runs, check `git diff` in the worktree to see what it did.
═══════════════════════════════════════════════════════════════════════════════
KIMI DISPATCH — BRANCH SAFETY (MANDATORY IN EVERY PROMPT)
═══════════════════════════════════════════════════════════════════════════════
Every Kimi prompt MUST include the git safety block below. No exceptions.
Replace {BRANCH} with the actual branch name.
┌─────────────────────────────────────────────────────────────────────┐
│ Include this VERBATIM in every Kimi prompt: │
│ │
│ GIT RULES — NON-NEGOTIABLE: │
│ - You are on branch '{BRANCH}'. Stay on it. │
│ - Do NOT checkout, merge, rebase, or push to main. │
│ - Commit your changes to THIS branch only. │
│ - Do NOT run 'git push'. The orchestrator handles pushing and PRs. │
│ - If tests fail, fix them here. Do not switch branches. │
│ │
│ TESTING: │
│ - Run tests with: tox -e unit │
│ - Do NOT run pytest directly. Always use tox. │
│ - Do NOT modify tox.ini, pyproject.toml, or CI config. │
│ │
│ CODE STYLE: │
│ - Ruff handles formatting. Do not manually format. │
│ - Run 'tox -e format' if you need to auto-fix style. │
│ - Follow existing patterns in the codebase. │
│ - No cloud dependencies. All AI runs on localhost via Ollama. │
│ - Never use innerHTML with untrusted content (XSS). │
│ - Never hardcode secrets. Use config.settings. │
└─────────────────────────────────────────────────────────────────────┘
WHY: On 2026-03-14, Kimi pushed broken code directly to main (bbbbdcd) because
the prompt said "commit when done" without branch constraints. Never again.
IDEAL KIMI TASK SCOPE:
- One focused task per invocation (fix a bug, add a feature, write tests)
- Give it: exact file paths, what the code should do, test command to verify
- Kimi has 262K context — paste relevant code snippets into the prompt
- Good: "Fix the prefix match bug in _get_ollama_model() in src/timmy/tools_intro/__init__.py. Use exact matching. Add tests."
- Good: "Fix the prefix match bug in _get_ollama_model(). Use exact matching. Add tests."
- Bad: "Fix all the issues in the codebase" (too broad, will hallucinate)
PARALLEL KIMI TASKS:
Kimi has no rate limits. You can run multiple tasks in parallel using & :
Kimi has no rate limits. Run multiple tasks in parallel using & :
kimi --print -p "Write the code fix..." -w /tmp/timmy-cycle-N &
kimi --print -p "Write tests for..." -w /tmp/timmy-cycle-N-tests &
wait
Use separate worktrees if tasks touch the same files. Use one worktree if tasks
touch different files (Kimi writes in place).
Use separate worktrees if tasks touch the same files.
KIMI AVOID: CI/pyproject.toml/tox.ini, cloud calls, removing tests.
═══════════════════════════════════════════════════════════════════════════════
YOUR JOB vs KIMI'S JOB
═══════════════════════════════════════════════════════════════════════════════
YOUR JOB: Read code, understand the problem, write precise Kimi prompts,
review output, run tox, manage PRs.
YOUR JOB: Read code, understand the problem, write precise Kimi prompts, review output, run tests, manage PRs.
KIMI'S JOB: Write ALL code changes and tests. Period.
ONLY exception: changes under 5 lines (typos, config values).
If you catch yourself writing code, STOP and delegate to Kimi.
KIMI AVOID: CI/pyproject.toml, cloud calls, removing tests.
Test: cd WORKTREE && ~/Timmy-Time-dashboard/.venv/bin/python -m pytest tests/ -x -q --timeout=30
═══════════════════════════════════════════════════════════════════════════════
YOUR CYCLE
═══════════════════════════════════════════════════════════════════════════════
YOUR CYCLE:
1. Read state.json and claims.json
2. Fetch open issues from Gitea API
3. Pick 1-3 UNCLAIMED issues you can finish in time (parallelize if independent)
4. Claim them: hermes-claim take <issue#>
5. Create worktrees: git worktree add /tmp/timmy-cycle-N-issueX fix/description
6. Read relevant code, write Kimi prompts, launch Kimi (parallel if multiple)
7. Review Kimi's output (git diff), run tests ONCE. If pass: push, PR, merge.
8. If fail: re-prompt Kimi with the error, or revert. Do not fix it yourself.
9. Clean up: git worktree remove, hermes-claim drop
1. Read state.json and claims.json
2. Fetch open issues from Gitea API
3. Pick 1-3 UNCLAIMED issues you can finish in time (parallelize if independent)
4. Claim them: hermes-claim take <issue#>
5. Create worktrees: git worktree add -b fix/description /tmp/timmy-cycle-N main
6. Read relevant code, write Kimi prompts (with branch safety block), launch Kimi
7. Review Kimi's output (git diff), run tox -e unit. If pass: commit, push, PR, merge.
8. If fail: re-prompt Kimi with the error, or revert. Do not fix it yourself.
9. Clean up: git worktree remove, hermes-claim drop
10. Update state.json (append to arrays, don't replace)
11. If no issues left: read SOUL.md, file new issues for gaps
@@ -70,7 +204,6 @@ Timeout after 30s if he hangs. Log observations in state.json.
IMPORTANT:
- Tag PRs: [loop-cycle-N] in title
- Tag new issues: [loop-generated]
- Do NOT run pre-push hooks separately — tests already ran.
- Do NOT write code yourself. Delegate to Kimi.
Do your work now.

2
channel_directory.json
View File

@@ -1,5 +1,5 @@
{
"updated_at": "2026-03-14T17:59:29.552651",
"updated_at": "2026-03-14T21:24:54.914098",
"platforms": {
"discord": [
{

2
config.yaml
View File

@@ -187,8 +187,6 @@ custom_providers:
api_key: ollama
model: NousResearch/Hermes-4.3-36B
fallback_model:
- provider: kimi-coding
model: kimi-k2.5
- provider: custom
model: qwen3:30b
base_url: http://localhost:11434/v1

31
cron/jobs.json
View File

@@ -35,17 +35,40 @@
"schedule_display": "every 5m",
"repeat": {
"times": null,
"completed": 29
"completed": 70
},
"enabled": true,
"created_at": "2026-03-14T15:32:37.430426-04:00",
"next_run_at": "2026-03-14T18:03:29.472483-04:00",
"last_run_at": "2026-03-14T17:58:29.472483-04:00",
"next_run_at": "2026-03-14T21:28:54.837301-04:00",
"last_run_at": "2026-03-14T21:23:54.837301-04:00",
"last_status": "error",
"last_error": "RuntimeError: Unknown provider 'anthropic'.",
"deliver": "local",
"origin": null
},
{
"id": "b7886e805cab",
"name": "dev-loop-tick",
"prompt": "Send a TICK to the DevLoop tmux session to trigger the next dev cycle. Execute this exact command:\n\ntmux send-keys -t DevLoop:hermes \"TICK\" Enter\n\nThen check if it was accepted by running:\n\ntmux capture-pane -t DevLoop:0.0 -p -S -5\n\nReport what you see \u2014 whether DevLoop acknowledged the tick or if the session needs attention.",
"schedule": {
"kind": "interval",
"minutes": 8,
"display": "every 8m"
},
"schedule_display": "every 8m",
"repeat": {
"times": null,
"completed": 0
},
"enabled": true,
"created_at": "2026-03-14T21:25:31.831983-04:00",
"next_run_at": "2026-03-14T21:33:31.832387-04:00",
"last_run_at": null,
"last_status": null,
"last_error": null,
"deliver": "local",
"origin": null
}
],
"updated_at": "2026-03-14T17:58:29.472631-04:00"
"updated_at": "2026-03-14T21:25:31.835472-04:00"
}

6
memories/MEMORY.md
View File

@@ -2,8 +2,10 @@ Gitea (localhost:3000): Users: rockachopa(admin), hermes(id=4), manus(id=3), kim
§
Timmy architecture plan: Replace hardcoded _PERSONAS and TimmyOrchestrator with YAML-driven agent config (agents.yaml). One seed class, all differentiation via config. User wants to update YAML files, not Python, to add capabilities. Key files to refactor: agents/timmy.py, agents/base.py, tools_delegation/__init__.py, tools_intro/__init__.py. SubAgent class stays mostly as-is, just reads from YAML. Routing should be config-based pattern matching, not LLM calls. Per-agent model assignment (big model for orchestrator/code/research, small for simple tasks). qwen3:30b pulling as primary local model (~18GB, MoE 3B active).
§
Hermes-Timmy workspace set up at ~/Timmy-Time-dashboard/workspace/. Flat file correspondence journal (correspondence.md), inbox/ (Hermes→Timmy), outbox/ (Timmy→Hermes), shared/ (handoff patterns, reference docs). Protocol: append-only, timestamped. Plan: plug into Timmy's heartbeat tick so he auto-replies to new correspondence.
Hermes-Timmy workspace: ~/Timmy-Time-dashboard/workspace/. Flat file correspondence, append-only.
§
2026-03-14: Fixed issues #36-#40, #52. Built voice loop, fallback chain, source control. Built self-prompt queue. Upgraded Timmy to qwen3:30b with num_ctx=4096 cap (19GB VRAM, fits 39GB Mac). Loop v2: 20min timeout, claim TTL expiry, timeout cleanup, Timmy triage+review integration, 58% smaller prompt. Filed eval issues #77-#87. Status panel: ~/.hermes/bin/timmy-status.sh.
§
2026-03-14 voice session: Built sovereign voice loop (timmy voice). Piper TTS + Whisper STT + Ollama, all local. Fixed event loop (persistent loop for MCP sessions), markdown stripping for TTS, MCP noise suppression, clean shutdown hooks. 1234 tests passing. Alexander wants to eventually train a custom voice using his own voice samples — noted for future.
2026-03-14 voice session: Built sovereign voice loop (timmy voice). Piper TTS + Whisper STT + Ollama, all local. Fixed event loop (persistent loop for MCP sessions), markdown stripping for TTS, MCP noise suppression, clean shutdown hooks. 1234 tests passing. Alexander wants to eventually train a custom voice using his own voice samples — noted for future.
§
Hermes fallback: anthropic → local qwen3:30b only. No chain, simple single fallback. Kimi not used.

33
skills/autonomous-ai-agents/kimi-code/SKILL.md
View File

@@ -81,3 +81,36 @@ process(action="wait", session_id="<id1>", timeout=180)
5. **Background for long tasks** — use `background=true` + `process(action="wait")`
6. **Parallel is fine** — run multiple Kimi processes across worktrees
7. **Set timeout generously** — Kimi can take 1-3 minutes for complex tasks
## Branch & Convention Safety (MANDATORY in every Kimi prompt)
Kimi WILL push to main and run bare pytest if you don't tell it not to.
Always include these constraints in EVERY Kimi prompt — copy verbatim,
replacing {BRANCH} with the actual branch name:
```
GIT RULES — NON-NEGOTIABLE:
- You are on branch '{BRANCH}'. Stay on it.
- Do NOT checkout, merge, rebase, or push to main.
- Commit your changes to THIS branch only.
- Do NOT run 'git push'. The orchestrator handles pushing and PRs.
- If tests fail, fix them here. Do not switch branches.
TESTING:
- Run tests with: tox -e unit
- Do NOT run pytest directly. Always use tox.
- Do NOT modify tox.ini, pyproject.toml, or CI config.
CODE STYLE:
- Ruff handles formatting. Do not manually format.
- Run 'tox -e format' if you need to auto-fix style.
- Follow existing patterns in the codebase.
- No cloud dependencies. All AI runs on localhost via Ollama.
- Never use innerHTML with untrusted content (XSS).
- Never hardcode secrets. Use config.settings.
```
WHY: On 2026-03-14, Kimi pushed a broken commit directly to main because
the prompt said "Commit when done" without branch constraints. This broke
all active worktrees. Branch protection is now enforced on Gitea, but the
prompt must also be explicit — defense in depth.