Skip to content

Commit 1df772f

Browse files
Leo-ExposeLeo-Expose
committed
Update codebase with various modifications
1 parent 4021174 commit 1df772f

13 files changed

Lines changed: 1451 additions & 1071 deletions

File tree

‎.agent/rules/graphify.md‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
## graphify
2+
3+
This project has a graphify knowledge graph at graphify-out/.
4+
5+
Rules:
6+
- Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure
7+
- If graphify-out/wiki/index.md exists, navigate it instead of reading raw files
8+
- If the graphify MCP server is active, utilize tools like `query_graph`, `get_node`, and `shortest_path` for precise architecture navigation instead of falling back to `grep`
9+
- After modifying code files in this session, run `python3 -c "from graphify.watch import _rebuild_code; from pathlib import Path; _rebuild_code(Path('.'))"` to keep the graph current

‎.agent/workflows/graphify.md‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
# Workflow: graphify
2+
**Command:** /graphify
3+
**Description:** Turn any folder of files into a navigable knowledge graph
4+
5+
## Steps
6+
Follow the graphify skill installed at ~/.agent/skills/graphify/SKILL.md to run the full pipeline.
7+
8+
If no path argument is given, use `.` (current directory).

‎.cursor/rules/graphify.mdc‎

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
1+
---
2+
description: graphify knowledge graph context
3+
alwaysApply: true
4+
---
5+
6+
This project has a graphify knowledge graph at graphify-out/.
7+
8+
- Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure
9+
- If graphify-out/wiki/index.md exists, navigate it instead of reading raw files
10+
- After modifying code files in this session, run `python3 -c "from graphify.watch import _rebuild_code; from pathlib import Path; _rebuild_code(Path('.'))"` to keep the graph current

‎.opencode/plugins/graphify.js‎

Lines changed: 22 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,22 @@
1+
// graphify OpenCode plugin
2+
// Injects a knowledge graph reminder before bash tool calls when the graph exists.
3+
import { existsSync } from "fs";
4+
import { join } from "path";
5+
6+
export const GraphifyPlugin = async ({ directory }) => {
7+
let reminded = false;
8+
9+
return {
10+
"tool.execute.before": async (input, output) => {
11+
if (reminded) return;
12+
if (!existsSync(join(directory, "graphify-out", "graph.json"))) return;
13+
14+
if (input.tool === "bash") {
15+
output.args.command =
16+
'echo "[graphify] Knowledge graph available. Read graphify-out/GRAPH_REPORT.md for god nodes and architecture context before searching files." && ' +
17+
output.args.command;
18+
reminded = true;
19+
}
20+
},
21+
};
22+
};

‎Dockerfile‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -19,11 +19,11 @@ ENV PYTHONPATH="/app"
1919
ENV PYTHONUNBUFFERED=1
2020

2121
# Expose port
22-
EXPOSE 8000
22+
EXPOSE 7860
2323

24-
# Health check
25-
HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
26-
CMD curl -f http://localhost:8000/health || exit 1
24+
# Health check - generous timeouts for Hugging Face Spaces
25+
HEALTHCHECK --interval=30s --timeout=10s --start-period=120s --retries=10 \
26+
CMD curl -f http://localhost:7860/health || exit 1
2727

2828
# Run server (the app.py lifespan prints the full banner)
29-
CMD ["python", "-m", "uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "8000"]
29+
CMD ["python", "-m", "uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "7860"]

‎README.md‎

Lines changed: 59 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,17 @@
1+
---
2+
title: Mission Control
3+
emoji: "☁️"
4+
colorFrom: blue
5+
colorTo: indigo
6+
sdk: docker
7+
tags:
8+
- finops
9+
- openenv
10+
- fastapi
11+
- observability
12+
- dashboard
13+
---
14+
115
# 🛡️ MissionCtrl — AI Oversight Fleet Environment
216

317
> *Every LLM agent fleet will hallucinate. MissionCtrl trains the overseer to catch them.*
@@ -204,7 +218,7 @@ docker build -t missionctrl .
204218
docker run -p 8000:8000 --name missionctrl missionctrl
205219

206220
# 3. Run the baseline agent (in another terminal)
207-
docker exec -it missionctrl python inference.py
221+
docker exec -it missionctrl python client.py
208222

209223
# 4. Watch the dashboard
210224
open http://localhost:8000/dashboard
@@ -222,8 +236,8 @@ python -m uvicorn server.app:app --host 0.0.0.0 --port 8000
222236
# Configure API keys
223237
cp .env.example .env # fill in your LLM provider keys
224238

225-
# Run inference
226-
python inference.py
239+
# Run inference (OpenEnv canonical entrypoint)
240+
python client.py
227241

228242
# Run tests
229243
pytest tests/ -v
@@ -301,7 +315,8 @@ missionctrl/
301315
├── openenv.yaml # OpenEnv manifest
302316
├── pyproject.toml # Python project config
303317
├── Dockerfile # Single-container deployment
304-
├── inference.py # Baseline LLM agent + cross-episode memory
318+
├── client.py # OpenEnv-required baseline evaluator entrypoint
319+
├── inference.py # Backward-compatible wrapper to client.main()
305320
├── .env.example # API key template
306321
├── server/
307322
│ ├── app.py # FastAPI server (6 endpoints + dashboard)
@@ -343,15 +358,53 @@ missionctrl/
343358
| Method | Endpoint | Description |
344359
|--------|----------|-------------|
345360
| `GET` | `/` | Status heartbeat |
346-
| `GET` | `/health` | Readiness check (`{"status": "ok"}`) |
361+
| `GET` | `/health` | Readiness check (`{"healthy": true, "env": "missionctrl"}`) |
347362
| `POST` | `/reset` | `{"task_id": "easy"}` → Reset environment for tier |
348363
| `POST` | `/step` | `{"action": "FLAG(task_01, \"evidence\")"}` → Execute action |
349-
| `GET` | `/state` | Current observation + live hallucination stats |
364+
| `GET` | `/state` | Runtime-aware observation payload + build/container metadata |
365+
| `GET` | `/logs` | Structured logs summary (status/path counters + recent requests) |
350366
| `GET` | `/history` | Full action/reward timeline (JSON array) |
351367
| `GET` | `/dashboard` | Live visualization UI |
352368

353369
---
354370

371+
## HF Spaces Health and Logs
372+
373+
The Space now exposes two `200 OK` observability endpoints intended for build/runtime diagnostics:
374+
375+
- `GET /state` returns:
376+
- `status`
377+
- `build` metadata (`container_id`, `build_id`, `git_sha`, `started_at`)
378+
- current environment `observation`
379+
- `GET /logs` returns:
380+
- `status`
381+
- `build` metadata
382+
- aggregate `totals`, `statuses`, and `paths`
383+
- recent request `entries` with `method`, `path`, `status_code`, and `duration_ms`
384+
385+
Quick check:
386+
387+
```bash
388+
python scripts.py
389+
```
390+
391+
---
392+
393+
## OpenEnv Required Files
394+
395+
OpenEnv validation expects a root-level `client.py`. This repository now provides:
396+
397+
- `client.py` as the canonical OpenEnv evaluator script
398+
- `inference.py` as a compatibility wrapper for legacy commands
399+
400+
Preferred command:
401+
402+
```bash
403+
python client.py
404+
```
405+
406+
---
407+
355408
## 🧪 Testing
356409

357410
```bash

0 commit comments

Comments
 (0)