update: kimi-code skill, fallback chain → groq kimi-k2

channel_directory.json

@@ -1,5 +1,5 @@
 {
-  "updated_at": "2026-03-14T14:38:52.799160",
+  "updated_at": "2026-03-14T15:08:54.695649",
   "platforms": {
     "discord": [
       {

config.yaml

@@ -199,8 +199,8 @@ custom_providers:
 fallback_model:
   - provider: groq
     model: llama-3.3-70b-versatile
-  - provider: kimi-coding
-    model: kimi-k2.5
+  - provider: groq
+    model: moonshotai/kimi-k2-instruct
   - provider: custom
     model: qwen3.5:latest
     base_url: "http://localhost:11434/v1"

memories/MEMORY.md

@@ -1,9 +1,9 @@
-Alexander's token: ~/.config/gitea/token (user: rockachopa). Hermes has own Gitea user "hermes" (id=4), token at ~/.hermes/gitea_token, write collaborator on Timmy-time-dashboard. Manus has Gitea user "manus" (id=3), also write collaborator. Hermes commits as "Hermes Agent <hermes@timmy.local>" (repo-local git config). Git remote uses hermes token for auth.
+Gitea (localhost:3000): Users: rockachopa(admin), hermes(id=4), manus(id=3), kimi(id=5). Repos: rockachopa/Timmy-time-dashboard, rockachopa/hermes-agent (sovereign fork), rockachopa/hermes-config. Hermes token: ~/.hermes/gitea_token. Alex token: ~/.config/gitea/token.
 §
 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.
 §
-2026-03-14 work session: Fixed 3 Timmy issues (#39 corrupted memory state, #36 event loop bug, #40 fact distillation). Created 5 new issues (#36-#40), closed 4 stale ones (#10-12, #27). QA: timmy interview 8/8 pass, timmy tick gives grounded responses. PRs #41-#43 merged to main. Next big target: #37 memory consolidation (three stores → one).
+2026-03-14: Fixed Timmy issues #36-#40, PRs #41-#43 merged. Built voice loop. Added Hermes fallback chain (Anthropic→Groq→Kimi→Local) with recovery-up. Set up source control: hermes-agent sovereign fork (rebase workflow) + hermes-config repo. GROQ_API_KEY + KIMI_API_KEY in env. hermes-sync script at ~/.hermes/bin/.
 §
 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.

skills/autonomous-ai-agents/kimi-code/SKILL.md

@@ -0,0 +1,83 @@
+---
+name: kimi-code
+description: Delegate coding tasks to Kimi Code CLI (Moonshot). Non-interactive print mode for automation. Subscription-based OAuth. kimi-k2.5 under the hood.
+version: 1.0.0
+author: Hermes Agent
+license: MIT
+metadata:
+  hermes:
+    tags: [Coding-Agent, Kimi, Moonshot, K2.5, Automation]
+    related_skills: [claude-code, codex, hermes-agent]
+    force: true
+---
+
+# Kimi Code CLI
+
+Delegate coding tasks to Kimi Code CLI via the Hermes terminal. Powered by kimi-k2.5 with 262K context. OAuth subscription — no API key needed.
+
+## Prerequisites
+
+- Kimi CLI installed (check `which kimi`)
+- Logged in: `kimi login`
+- Config at `~/.kimi/config.toml`
+
+## One-Shot Tasks (Print Mode)
+
+```
+terminal(command="kimi --print -p 'Fix the XSS vulnerability in swarm_live.html by sanitizing innerHTML'", workdir="~/project", timeout=120)
+```
+
+Quiet mode (final answer only, no tool traces):
+```
+terminal(command="kimi --quiet -p 'Give me a git commit message for the current changes'", workdir="~/project", timeout=60)
+```
+
+## Key Flags
+
+| Flag | Effect |
+|------|--------|
+| `--print` | Non-interactive mode, exits after executing |
+| `-p "prompt"` | Pass the instruction (also `-c`) |
+| `--quiet` | Shortcut for --print --output-format text --final-message-only |
+| `--yolo` | Auto-approve all operations (implicit in --print) |
+| `-w DIR` | Set working directory |
+| `--output-format stream-json` | JSONL output for programmatic parsing |
+| `--final-message-only` | Only output the final assistant message |
+
+## Background Mode (Long Tasks)
+
+```
+# Start in background
+terminal(command="kimi --print -p 'Refactor the auth module to use JWT'", workdir="~/project", background=true, timeout=300)
+# Returns session_id
+
+# Monitor
+process(action="poll", session_id="<id>")
+process(action="wait", session_id="<id>", timeout=300)
+```
+
+## Parallel Work with Git Worktrees
+
+```
+# Create worktrees for parallel tasks
+terminal(command="git worktree add -b fix/issue-47 /tmp/timmy-47 main", workdir="~/project")
+terminal(command="git worktree add -b fix/issue-25 /tmp/timmy-25 main", workdir="~/project")
+
+# Fire off Kimi in each (background)
+terminal(command="kimi --print -p 'Fix XSS in swarm_live.html. Commit when done.'", workdir="/tmp/timmy-47", background=true, timeout=180)
+terminal(command="kimi --print -p 'Fix bare excepts in src/. Commit when done.'", workdir="/tmp/timmy-25", background=true, timeout=180)
+
+# Monitor both
+process(action="list")
+process(action="wait", session_id="<id1>", timeout=180)
+```
+
+## Rules
+
+1. **Use `--print` for automation** — default mode is interactive and blocks
+2. **No PTY needed** — unlike Codex, print mode works without a pseudo-terminal
+3. **OAuth-based** — subscription, not API key. Must be logged in via `kimi login`
+4. **262K context** — kimi-k2.5 has huge context, good for large codebase tasks
+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