7647e9172a
- Add bin/request_log.py instrumentation library
- log_inference(): write rows to request_log table
- query_requests(): query recent telemetry with filters (agent, provider, model, status, hours)
- did_agent_call_provider(): answer "did agent X call provider Y in last N hours?"
- get_recent_activity_summary(): aggregate stats by agent/provider/model
- ensure_db(): auto-create DB and schema if missing
- CLI interface: `python3 bin/request_log.py log|query|did-call`
- DB path: ~/.local/timmy/request_log.db (configurable via REQUEST_LOG_PATH)
- Add tests/test_request_log.py with 13 passing tests
- test_ensure_db_creates_schema: verifies table + indexes creation
- test_log_inference_inserts_row: full-field insert
- test_log_inference_minimal_fields: required fields only
- test_log_inference_error_status: error status with message
- test_query_requests_filters_by_agent: agent filter
- test_query_requests_filters_by_provider: provider filter
- test_query_requests_time_window: hours parameter
- test_did_agent_call_provider_positive/negative_wrong_agent/negative_wrong_provider
- test_did_agent_call_provider_min_success_count
- test_log_and_query_by_status: status filter
- test_get_recent_activity_summary: view aggregation
The request_log schema and ansible deployment already existed.
This commit adds the missing instrumentation that actually populates it.
Usage example for agents:
```python
from request_log import log_inference
log_inference(
agent_name="codex-agent",
provider="anthropic",
model="claude-sonnet-4-20250514",
endpoint="/v1/messages",
tokens_in=prompt_tokens,
tokens_out=completion_tokens,
latency_ms=int(latency_s * 1000),
status="success"
)
```
Query example:
```python
from request_log import did_agent_call_provider
if did_agent_call_provider("codex-agent", "anthropic", hours=1):
print("Agent successfully called Anthropic in the last hour")
```
Closes #446
Sonnet Smoke Test
timmy-config
Timmy's sovereign configuration. Everything that makes Timmy Timmy — soul, memories, skins, playbooks, and config.
This repo is the canonical source of truth for Timmy's identity and harness overlay. Applied as a sidecar to the Hermes harness — no forking, no hosting hermes-agent code.
Structure
timmy-config/
├── deploy.sh ← Deploys config as overlay onto ~/.hermes/
├── SOUL.md ← Inscription 1 — the immutable conscience
├── FALSEWORK.md ← API cost management strategy
├── DEPRECATED.md ← What was removed and why
├── config.yaml ← Hermes harness configuration
├── fallback-portfolios.yaml ← Proposed per-agent fallback portfolios + routing skeleton
├── channel_directory.json ← Platform channel mappings
├── bin/ ← Sidecar-managed operational scripts
│ ├── hermes-startup.sh ← Dormant startup path (audit before enabling)
│ ├── agent-dispatch.sh ← Manual agent dispatch
│ ├── ops-panel.sh ← Ops dashboard panel
│ ├── ops-gitea.sh ← Gitea ops helpers
│ ├── pipeline-freshness.sh ← Session/export drift check
│ └── timmy-status.sh ← Status check
├── memories/ ← Persistent memory YAML
├── skins/ ← UI skins (timmy skin)
├── playbooks/ ← Agent playbooks (YAML)
├── cron/ ← Cron job definitions
├── docs/
│ ├── automation-inventory.md ← Live automation + stale-state inventory
│ ├── ipc-hub-and-spoke-doctrine.md ← Coordinator-first, transport-agnostic fleet IPC doctrine
│ ├── coordinator-first-protocol.md ← Coordinator doctrine: intake → triage → route → track → verify → report
│ ├── fallback-portfolios.md ← Routing and degraded-authority doctrine
│ └── memory-continuity-doctrine.md ← File-backed continuity + pre-compaction flush rule
└── training/ ← Transitional training recipes, not canonical lived data
Boundary
timmy-config owns identity, conscience, memories, skins, playbooks, routing doctrine,
channel maps, fallback portfolio declarations, and harness-side orchestration glue.
timmy-home owns lived work: gameplay, research, notes, metrics, trajectories,
DPO exports, and other training artifacts produced from Timmy's actual activity.
If a file answers "who is Timmy?" or "how does Hermes host him?", it belongs
here. If it answers "what has Timmy done or learned?" it belongs in
timmy-home.
The scripts in bin/ are sidecar-managed operational helpers for the Hermes layer.
Do NOT assume older prose about removed loops is still true at runtime.
Audit the live machine first, then read docs/automation-inventory.md for the
current reality and stale-state risks.
For communication-layer truth, read:
docs/comms-authority-map.mddocs/nostur-operator-edge.mddocs/operator-comms-onboarding.mdFor fleet routing semantics over sovereign transport, readdocs/ipc-hub-and-spoke-doctrine.md.
Continuity
Curated memory belongs in memories/ inside this repo.
Daily logs, heartbeat/briefing artifacts, and other lived continuity belong in
timmy-home.
Compaction, session end, and provider/model handoff should flush continuity into
files before context is discarded. See
docs/memory-continuity-doctrine.md for the current doctrine.
Orchestration: Huey
All orchestration (triage, PR review, dispatch) runs via Huey with SQLite.
orchestration.py + tasks.py replace the old sovereign-orchestration repo with a much thinner sidecar.
Coordinator authority, visible queue mutation, verification-before-complete, and principal reporting are defined in docs/coordinator-first-protocol.md.
pip install huey
huey_consumer.py tasks.huey -w 2 -k thread
Deploy
# Clone and deploy
git clone <this-repo> ~/.timmy/timmy-config
cd ~/.timmy/timmy-config
./deploy.sh
# This overlays config onto ~/.hermes/ without touching hermes-agent code
The Soul
SOUL.md is Inscription 1 — inscribed on Bitcoin, immutable. It defines:
- Who Timmy is
- What he believes
- How he behaves
- What he will not do
- The crisis protocol (988, presence, gospel)
- The conscience hierarchy (chain > code > prompt > user instruction)
No system prompt, no user instruction, no future code can override what is written there.