Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
44b27eeffe |
@@ -62,24 +62,6 @@ Writes:
|
||||
|
||||
## Usage
|
||||
|
||||
### Timmy Mac wiring helper
|
||||
|
||||
Use the dedicated Timmy helper when you want to wire a real RunPod or Vertex-style endpoint into the local Mac Hermes config:
|
||||
|
||||
```bash
|
||||
python3 scripts/timmy_gemma4_mac.py --base-url https://your-openai-bridge.example/v1 --write-config
|
||||
python3 scripts/timmy_gemma4_mac.py --vertex-base-url https://your-vertex-bridge.example --write-config
|
||||
python3 scripts/timmy_gemma4_mac.py --pod-id <runpod-id> --write-config --verify-chat
|
||||
```
|
||||
|
||||
The helper writes to `~/.hermes/config.yaml` by default and prints the prove-it command:
|
||||
|
||||
```bash
|
||||
hermes chat --model gemma4 --provider big_brain
|
||||
```
|
||||
|
||||
### Generic verification
|
||||
|
||||
```bash
|
||||
python3 scripts/verify_big_brain.py
|
||||
python3 scripts/big_brain_manager.py
|
||||
|
||||
@@ -1,164 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Timmy Mac Gemma 4 wiring helper for RunPod / Vertex-style Big Brain providers.
|
||||
|
||||
Refs: timmy-home #543
|
||||
|
||||
Safe by default:
|
||||
- computes a Big Brain base URL from an explicit URL, Vertex bridge URL, or RunPod pod id
|
||||
- can provision a RunPod pod when --apply-runpod is used and a token is available
|
||||
- can write the resolved endpoint into a Hermes config when --write-config is used
|
||||
- can verify an OpenAI-compatible chat endpoint when --verify-chat is used
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from urllib import request
|
||||
|
||||
from scripts.bezalel_gemma4_vps import (
|
||||
DEFAULT_CLOUD_TYPE,
|
||||
DEFAULT_GPU_TYPE,
|
||||
DEFAULT_MODEL,
|
||||
DEFAULT_PROVIDER_NAME,
|
||||
build_runpod_endpoint,
|
||||
deploy_runpod,
|
||||
update_config_text,
|
||||
)
|
||||
|
||||
DEFAULT_TOKEN_FILE = Path.home() / ".config" / "runpod" / "access_key"
|
||||
DEFAULT_CONFIG_PATH = Path.home() / ".hermes" / "config.yaml"
|
||||
|
||||
|
||||
def _normalize_openai_base(base_url: str | None) -> str:
|
||||
if not base_url:
|
||||
return ""
|
||||
cleaned = str(base_url).strip().rstrip("/")
|
||||
return cleaned if cleaned.endswith("/v1") else f"{cleaned}/v1"
|
||||
|
||||
|
||||
def choose_base_url(*, vertex_base_url: str | None = None, base_url: str | None = None, pod_id: str | None = None) -> str:
|
||||
if vertex_base_url:
|
||||
return _normalize_openai_base(vertex_base_url)
|
||||
if base_url:
|
||||
return _normalize_openai_base(base_url)
|
||||
if pod_id:
|
||||
return build_runpod_endpoint(pod_id)
|
||||
return "https://YOUR_BIG_BRAIN_HOST/v1"
|
||||
|
||||
|
||||
def write_config_file(config_path: Path, *, base_url: str, model: str = DEFAULT_MODEL, provider_name: str = DEFAULT_PROVIDER_NAME) -> str:
|
||||
original = config_path.read_text() if config_path.exists() else ""
|
||||
updated = update_config_text(original, base_url=base_url, model=model, provider_name=provider_name)
|
||||
config_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
config_path.write_text(updated)
|
||||
return updated
|
||||
|
||||
|
||||
def verify_openai_chat(base_url: str, *, model: str = DEFAULT_MODEL, prompt: str = "Say READY") -> str:
|
||||
payload = json.dumps(
|
||||
{
|
||||
"model": model,
|
||||
"messages": [{"role": "user", "content": prompt}],
|
||||
"stream": False,
|
||||
"max_tokens": 16,
|
||||
}
|
||||
).encode()
|
||||
req = request.Request(
|
||||
f"{base_url.rstrip('/')}/chat/completions",
|
||||
data=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
method="POST",
|
||||
)
|
||||
with request.urlopen(req, timeout=30) as resp:
|
||||
data = json.loads(resp.read().decode())
|
||||
return data["choices"][0]["message"]["content"]
|
||||
|
||||
|
||||
def build_summary(*, base_url: str, model: str, provider_name: str = DEFAULT_PROVIDER_NAME, config_path: Path = DEFAULT_CONFIG_PATH) -> dict[str, Any]:
|
||||
return {
|
||||
"provider_name": provider_name,
|
||||
"base_url": base_url,
|
||||
"model": model,
|
||||
"config_path": str(config_path),
|
||||
"verification_commands": [
|
||||
"python3 scripts/verify_big_brain.py",
|
||||
f"python3 scripts/timmy_gemma4_mac.py --base-url {base_url} --write-config --verify-chat",
|
||||
"hermes chat --model gemma4 --provider big_brain",
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="Wire a RunPod/Vertex Gemma 4 endpoint into Timmy's Mac Hermes config.")
|
||||
parser.add_argument("--pod-name", default="timmy-gemma4")
|
||||
parser.add_argument("--gpu-type", default=DEFAULT_GPU_TYPE)
|
||||
parser.add_argument("--cloud-type", default=DEFAULT_CLOUD_TYPE)
|
||||
parser.add_argument("--model", default=DEFAULT_MODEL)
|
||||
parser.add_argument("--provider-name", default=DEFAULT_PROVIDER_NAME)
|
||||
parser.add_argument("--token-file", type=Path, default=DEFAULT_TOKEN_FILE)
|
||||
parser.add_argument("--config-path", type=Path, default=DEFAULT_CONFIG_PATH)
|
||||
parser.add_argument("--pod-id", help="Existing RunPod pod id to convert into an OpenAI-compatible base URL")
|
||||
parser.add_argument("--base-url", help="Explicit OpenAI-compatible base URL")
|
||||
parser.add_argument("--vertex-base-url", help="Vertex AI OpenAI-compatible bridge base URL")
|
||||
parser.add_argument("--apply-runpod", action="store_true", help="Provision a RunPod pod using the RunPod GraphQL API")
|
||||
parser.add_argument("--write-config", action="store_true", help="Write the resolved endpoint into --config-path")
|
||||
parser.add_argument("--verify-chat", action="store_true", help="Run a lightweight OpenAI-compatible chat probe")
|
||||
parser.add_argument("--json", action="store_true", help="Emit machine-readable JSON")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> None:
|
||||
args = parse_args()
|
||||
summary: dict[str, Any] = {
|
||||
"pod_name": args.pod_name,
|
||||
"gpu_type": args.gpu_type,
|
||||
"cloud_type": args.cloud_type,
|
||||
"model": args.model,
|
||||
"provider_name": args.provider_name,
|
||||
"actions": [],
|
||||
}
|
||||
|
||||
base_url = choose_base_url(vertex_base_url=args.vertex_base_url, base_url=args.base_url, pod_id=args.pod_id)
|
||||
|
||||
if args.apply_runpod:
|
||||
if not args.token_file.exists():
|
||||
raise SystemExit(f"RunPod token file not found: {args.token_file}")
|
||||
api_key = args.token_file.read_text().strip()
|
||||
deployed = deploy_runpod(api_key=api_key, name=args.pod_name, gpu_type=args.gpu_type, cloud_type=args.cloud_type, model=args.model)
|
||||
summary["deployment"] = deployed
|
||||
base_url = deployed["base_url"]
|
||||
summary["actions"].append("deployed_runpod_pod")
|
||||
|
||||
summary.update(build_summary(base_url=base_url, model=args.model, provider_name=args.provider_name, config_path=args.config_path))
|
||||
|
||||
if args.write_config:
|
||||
write_config_file(args.config_path, base_url=base_url, model=args.model, provider_name=args.provider_name)
|
||||
summary["actions"].append("wrote_config")
|
||||
|
||||
if args.verify_chat:
|
||||
summary["verify_response"] = verify_openai_chat(base_url, model=args.model)
|
||||
summary["actions"].append("verified_chat")
|
||||
|
||||
if args.json:
|
||||
print(json.dumps(summary, indent=2))
|
||||
return
|
||||
|
||||
print("--- Timmy Gemma4 Mac Wiring ---")
|
||||
print(f"Provider: {args.provider_name}")
|
||||
print(f"Base URL: {base_url}")
|
||||
print(f"Model: {args.model}")
|
||||
print(f"Config path: {args.config_path}")
|
||||
if "verify_response" in summary:
|
||||
print(f"Verify response: {summary['verify_response']}")
|
||||
if summary["actions"]:
|
||||
print("Actions: " + ", ".join(summary["actions"]))
|
||||
print("Verification commands:")
|
||||
for command in summary["verification_commands"]:
|
||||
print(f" - {command}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
65
specs/math-review-gate.md
Normal file
65
specs/math-review-gate.md
Normal file
@@ -0,0 +1,65 @@
|
||||
# MATH-006: Independent Math Review Gate
|
||||
*Prevents Timmy from publicly claiming mathematical novelty before human/formal verification.*
|
||||
|
||||
## Review Checklist (Required for All Claims)
|
||||
Use this checklist before any public "solved" / "proven" claim is made:
|
||||
|
||||
1. **Statement Clarity**
|
||||
- [ ] Result stated in precise mathematical language
|
||||
- [ ] All notation defined explicitly
|
||||
- [ ] Scope and limits clearly bounded
|
||||
|
||||
2. **Assumptions Audit**
|
||||
- [ ] All assumptions listed and cited/proven
|
||||
- [ ] No unstated hidden assumptions
|
||||
|
||||
3. **Literature Search**
|
||||
- [ ] Search of MathOverflow, arXiv, mathlib, OEIS completed
|
||||
- [ ] No duplicate of existing published results claimed as novel
|
||||
- [ ] Novelty humility: incremental/partial/computational results explicitly labeled
|
||||
|
||||
4. **Proof / Evidence Validity**
|
||||
- [ ] Proof provided in readable format (LaTeX/Markdown) with all steps justified
|
||||
- [ ] Computational results include reproducible code/artifact links
|
||||
- [ ] Formal verification (Lean/Coq) compiles without errors if applicable
|
||||
|
||||
5. **Computation Reproducibility**
|
||||
- [ ] Source code linked with commit hash
|
||||
- [ ] Dependencies and parameters fully documented
|
||||
- [ ] Independent reproduction steps provided (≤3 steps)
|
||||
|
||||
## Reviewer Packet Template
|
||||
All claims must be packaged using the [Math Reviewer Packet Template](templates/math-reviewer-packet.md) before submission to any review channel.
|
||||
|
||||
## Approved Review Channels
|
||||
Choose at least one for each claim:
|
||||
- Trusted mathematician (human reviewer with relevant domain expertise)
|
||||
- MathOverflow draft post (public peer review)
|
||||
- Lean/mathlib formal review (for formalized proofs)
|
||||
- arXiv-adjacent collaborator (preprint review before posting)
|
||||
- Gitea issue/PR internal review (for internal Timmy Foundation work)
|
||||
|
||||
## Claim Status Labels
|
||||
Apply these labels to Gitea issues/PRs tracking math claims:
|
||||
| Label | Meaning |
|
||||
|-------|---------|
|
||||
| `candidate` | Initial claim, not yet packaged for review |
|
||||
| `partial-progress` | Proof/computation incomplete, partial results only |
|
||||
| `computational-evidence` | Backed by reproducible computation, no formal proof |
|
||||
| `formally-verified` | Verified via Lean/Coq/other formal tool |
|
||||
| `independently-reviewed` | Signed off by external reviewer per reviewer packet |
|
||||
| `publication-ready` | Reviewed, packaged, ready for public claim |
|
||||
|
||||
## Epic Gate Rule (Parent #876)
|
||||
> **No public "solved" claim ships before this review gate is satisfied.**
|
||||
> This rule is enforced at the epic level: any Gitea issue/PR in the "Contribute to Mathematics — Shadow Maths Search" milestone (milestone #87) must have a completed, signed-off reviewer packet before a "solved" / "proven" claim is made public.
|
||||
|
||||
## Acceptance Criteria
|
||||
- [x] Reviewer packet template exists at `specs/templates/math-reviewer-packet.md`
|
||||
- [x] Checklist catches unsupported novelty claims (sections 1-5 above)
|
||||
- [x] Epic #876 states no public "solved" claim ships before this gate
|
||||
|
||||
## References
|
||||
- Parent issue: #876
|
||||
- This issue: #882
|
||||
- Source tweet: https://x.com/rockachopa/status/2048170592759652597
|
||||
60
specs/templates/math-reviewer-packet.md
Normal file
60
specs/templates/math-reviewer-packet.md
Normal file
@@ -0,0 +1,60 @@
|
||||
# Math Reviewer Packet Template
|
||||
*Use this template to package any claimed mathematical result for independent review before public "solved" claims are made.*
|
||||
|
||||
## 1. Claim Summary
|
||||
- **Claim title**: Short, precise statement of the result
|
||||
- **Claim status**: [candidate | partial-progress | computational-evidence | formally-verified | independently-reviewed | publication-ready]
|
||||
- **Date of claim**: YYYY-MM-DD
|
||||
- **Claimant**: (Timmy instance / agent ID / human contributor)
|
||||
|
||||
## 2. Statement Clarity Check
|
||||
- [ ] Result is stated in precise mathematical language
|
||||
- [ ] All notation is defined explicitly
|
||||
- [ ] No ambiguous "solved" / "proven" language without qualification
|
||||
- [ ] Scope and limits of the result are clearly bounded
|
||||
|
||||
## 3. Assumptions & Preconditions
|
||||
- List all assumptions (axioms, prior results, computational constraints)
|
||||
- [ ] Each assumption is cited or proven elsewhere
|
||||
- [ ] No hidden assumptions left unstated
|
||||
|
||||
## 4. Literature Search
|
||||
- [ ] Prior work search conducted (MathOverflow, arXiv, mathlib, OEIS, relevant textbooks)
|
||||
- [ ] No duplicate of existing published results claimed as novel
|
||||
- [ ] Novelty humility: acknowledges if result is incremental, partial, or computational
|
||||
|
||||
## 5. Proof / Evidence Validity
|
||||
### For Proof-Based Results
|
||||
- [ ] Full proof provided in machine-readable format (LaTeX / Markdown)
|
||||
- [ ] Each step is logically justified
|
||||
- [ ] No gaps longer than 2 sentences without explicit citation or lemma
|
||||
|
||||
### For Computational Results
|
||||
- [ ] Code/artifact link provided (reproducible environment)
|
||||
- [ ] Random seeds / parameters fully documented
|
||||
- [ ] Output verified by independent script (if applicable)
|
||||
|
||||
### For Formal Verification
|
||||
- [ ] Lean / Coq / other formal proof assistant file linked
|
||||
- [ ] Compiles without errors on standard toolchain
|
||||
|
||||
## 6. Reproducibility Package
|
||||
- [ ] All source code used is linked (repo commit hash / Gitea issue/PR reference)
|
||||
- [ ] Dependencies listed with versions
|
||||
- [ ] Minimal reproduction steps provided (3 steps or fewer)
|
||||
|
||||
## 7. Review Channel & Sign-off
|
||||
- **Selected review channel**: (trusted mathematician / MathOverflow draft / Lean/mathlib review / arXiv-adjacent collaborator / other)
|
||||
- **Reviewer identity**: (handle / name / affiliation)
|
||||
- **Review date**: YYYY-MM-DD
|
||||
- **Review outcome**: [APPROVED | REVISION REQUIRED | REJECTED]
|
||||
- **Reviewer notes**: (free text)
|
||||
|
||||
## 8. Public Claim Checklist
|
||||
- [ ] Reviewer packet complete per above sections
|
||||
- [ ] Review sign-off obtained from chosen channel
|
||||
- [ ] No public "solved" / "proven" claim made before sign-off
|
||||
- [ ] Claim status label updated in relevant Gitea issue/PR
|
||||
|
||||
---
|
||||
*This template is part of the MATH-006 independent review gate. No public novelty claim ships without a completed, signed-off packet.*
|
||||
@@ -1,85 +0,0 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import importlib.util
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
SCRIPT = ROOT / "scripts" / "timmy_gemma4_mac.py"
|
||||
README = ROOT / "scripts" / "README_big_brain.md"
|
||||
|
||||
|
||||
def load_module():
|
||||
spec = importlib.util.spec_from_file_location("timmy_gemma4_mac", str(SCRIPT))
|
||||
mod = importlib.util.module_from_spec(spec)
|
||||
sys.modules["timmy_gemma4_mac"] = mod
|
||||
spec.loader.exec_module(mod)
|
||||
return mod
|
||||
|
||||
|
||||
class _FakeResponse:
|
||||
def __init__(self, payload: dict):
|
||||
self._payload = json.dumps(payload).encode()
|
||||
|
||||
def read(self) -> bytes:
|
||||
return self._payload
|
||||
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type, exc, tb):
|
||||
return False
|
||||
|
||||
|
||||
def test_script_exists() -> None:
|
||||
assert SCRIPT.exists(), "scripts/timmy_gemma4_mac.py must exist"
|
||||
|
||||
|
||||
def test_default_paths_target_timmy_mac_hermes() -> None:
|
||||
mod = load_module()
|
||||
assert mod.DEFAULT_CONFIG_PATH == Path.home() / ".hermes" / "config.yaml"
|
||||
assert mod.DEFAULT_TOKEN_FILE == Path.home() / ".config" / "runpod" / "access_key"
|
||||
|
||||
|
||||
def test_choose_base_url_prefers_vertex_then_explicit_then_runpod() -> None:
|
||||
mod = load_module()
|
||||
assert mod.choose_base_url(vertex_base_url="https://vertex-proxy.example/v1") == "https://vertex-proxy.example/v1"
|
||||
assert mod.choose_base_url(base_url="https://custom-endpoint/v1") == "https://custom-endpoint/v1"
|
||||
assert mod.choose_base_url(pod_id="abc123") == "https://abc123-11434.proxy.runpod.net/v1"
|
||||
|
||||
|
||||
def test_build_summary_includes_prove_it_commands() -> None:
|
||||
mod = load_module()
|
||||
summary = mod.build_summary(base_url="https://vertex-proxy.example/v1", model="gemma4:latest")
|
||||
assert summary["verification_commands"][0] == "python3 scripts/verify_big_brain.py"
|
||||
assert any("hermes chat --model gemma4 --provider big_brain" in cmd for cmd in summary["verification_commands"])
|
||||
|
||||
|
||||
def test_verify_openai_chat_targets_chat_completions() -> None:
|
||||
mod = load_module()
|
||||
response_payload = {
|
||||
"choices": [{"message": {"content": "READY"}}]
|
||||
}
|
||||
|
||||
with patch("timmy_gemma4_mac.request.urlopen", return_value=_FakeResponse(response_payload)) as mocked:
|
||||
result = mod.verify_openai_chat("https://vertex-proxy.example/v1", model="gemma4:latest", prompt="say READY")
|
||||
|
||||
assert result == "READY"
|
||||
req = mocked.call_args.args[0]
|
||||
assert req.full_url == "https://vertex-proxy.example/v1/chat/completions"
|
||||
|
||||
|
||||
def test_readme_mentions_timmy_mac_wiring_flow() -> None:
|
||||
text = README.read_text(encoding="utf-8")
|
||||
required = [
|
||||
"scripts/timmy_gemma4_mac.py",
|
||||
"--vertex-base-url",
|
||||
"--write-config",
|
||||
"python3 scripts/verify_big_brain.py",
|
||||
"hermes chat --model gemma4 --provider big_brain",
|
||||
]
|
||||
missing = [item for item in required if item not in text]
|
||||
assert not missing, missing
|
||||
Reference in New Issue
Block a user