feat: M2 AI tips — LiteLLM gateway, context assembler, end-to-end generation pipeline
Issues closed: #86, #87, #88, #89, #90, #91, #79, #80, #82 infra: - docker-compose `ai` profile: Ollama + LiteLLM services - infra/litellm/litellm_config.yaml: tip-generator / embedder / judge aliases - .env.example: LITELLM_URL, LITELLM_MASTER_KEY, OLLAMA_URL ml/serving: - POST /generate: calls LiteLLM tip-generator alias, returns TipCandidate[] - JSON retry loop (2 retries with correction prompt on malformed response) - _parse_llm_json strips markdown fences ml/features: - context.py: build_context() assembles user signals → PromptContext (sorts overdue/high-priority tasks first for LLM prompt quality) shared-types: - TipKind, TipSource, TipCandidate types - Tip gains kind + rationale fields services/api: - recommender: 3-stage pipeline (assemble → score → serve) Stage 1: Todoist tasks + LLM candidates fetched in parallel Stage 2: egreedy bandit scores merged candidate pool Stage 3: serve + log with prompt_version, llm_model, tip_kind - tip_scores: prompt_version, llm_model, tip_kind columns + migrations - config: LITELLM_URL added - integrations: surface token_status in /integrations response tests: - ml/serving/tests/test_generate.py: 13 tests (retry, 502/503, fence variants) - ml/features/test_context.py: 9 tests (sorting, edge cases) - services/api recommender.unit.test.ts: 16 pure-function tests (inferReward, dueAgeDays) - services/api recommender.test.ts: 4 integration tests (tip_scores columns, LLM fallback) - shared-types: TipCandidate, rationale, full TipFeedback action set docs: - ADR-0008: LiteLLM AI gateway decision - overview.md: M2 pipeline description updated - ml/README.md: serving + features roles updated Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -26,12 +26,16 @@ from collections import deque
|
||||
from pathlib import Path
|
||||
from typing import Optional, Deque
|
||||
|
||||
import httpx
|
||||
import numpy as np
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from pydantic import BaseModel
|
||||
|
||||
app = FastAPI(title="oO ML Serving", version="1.0.0")
|
||||
|
||||
LITELLM_URL = os.getenv("LITELLM_URL", "http://localhost:4000")
|
||||
LITELLM_MASTER_KEY = os.getenv("LITELLM_MASTER_KEY", "sk-oo-dev")
|
||||
|
||||
STATE_DIR = Path(os.getenv("STATE_DIR", "/tmp/oo-bandit-state"))
|
||||
STATE_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
@@ -166,6 +170,56 @@ class RewardResponse(BaseModel):
|
||||
ok: bool
|
||||
|
||||
|
||||
class PromptContext(BaseModel):
|
||||
tasks: list[dict] = []
|
||||
hour_of_day: int = 12
|
||||
day_of_week: int = 0
|
||||
extra: dict = {}
|
||||
|
||||
|
||||
class GenerateRequest(BaseModel):
|
||||
user_id: str
|
||||
context: PromptContext = PromptContext()
|
||||
n: int = 3
|
||||
|
||||
|
||||
class TipCandidate(BaseModel):
|
||||
id: str
|
||||
content: str
|
||||
source: str = "llm"
|
||||
rationale: Optional[str] = None
|
||||
|
||||
|
||||
class GenerateResponse(BaseModel):
|
||||
candidates: list[TipCandidate]
|
||||
model: str
|
||||
prompt_tokens: int = 0
|
||||
completion_tokens: int = 0
|
||||
|
||||
|
||||
_GENERATE_SYSTEM = (
|
||||
"You are a personal productivity coach. "
|
||||
"Given the user's current context, generate actionable, specific tips. "
|
||||
"Respond ONLY with a JSON array of objects, each with keys: "
|
||||
'"id" (short slug), "content" (the tip, ≤2 sentences), "rationale" (why now, ≤1 sentence). '
|
||||
"No markdown, no prose outside the JSON array."
|
||||
)
|
||||
|
||||
|
||||
def _build_prompt(ctx: PromptContext, n: int) -> str:
|
||||
lines = [f"Time: {ctx.hour_of_day:02d}:00, day_of_week={ctx.day_of_week}"]
|
||||
if ctx.tasks:
|
||||
overdue = [t for t in ctx.tasks if t.get("is_overdue")]
|
||||
lines.append(f"Tasks: {len(ctx.tasks)} total, {len(overdue)} overdue")
|
||||
for t in ctx.tasks[:5]:
|
||||
due = t.get("due_date", "no due date")
|
||||
lines.append(f" - [{t.get('priority','?')}] {t.get('content','?')} (due: {due})")
|
||||
for k, v in ctx.extra.items():
|
||||
lines.append(f"{k}: {v}")
|
||||
lines.append(f"\nGenerate {n} tips as a JSON array.")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
# ── Endpoints ──────────────────────────────────────────────────────────────
|
||||
|
||||
@app.get("/health")
|
||||
@@ -173,6 +227,97 @@ def health():
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
_RETRY_SUFFIX = (
|
||||
"\n\nYour previous response was not valid JSON. "
|
||||
"Reply ONLY with the JSON array — no prose, no markdown fences."
|
||||
)
|
||||
|
||||
_MAX_GENERATE_RETRIES = 2
|
||||
|
||||
|
||||
def _parse_llm_json(raw: str) -> list[dict]:
|
||||
"""Strip markdown fences and parse JSON array. Raises ValueError on failure."""
|
||||
text = raw.strip()
|
||||
if text.startswith("```"):
|
||||
parts = text.split("```")
|
||||
text = parts[1] if len(parts) > 1 else text
|
||||
if text.startswith("json"):
|
||||
text = text[4:]
|
||||
return json.loads(text)
|
||||
|
||||
|
||||
@app.post("/generate", response_model=GenerateResponse)
|
||||
async def generate(req: GenerateRequest) -> GenerateResponse:
|
||||
"""Generate tip candidates via LiteLLM → tip-generator alias.
|
||||
|
||||
Retries up to _MAX_GENERATE_RETRIES times on malformed JSON, appending
|
||||
a correction hint to the conversation so the model can self-correct.
|
||||
"""
|
||||
prompt = _build_prompt(req.context, req.n)
|
||||
messages: list[dict] = [
|
||||
{"role": "system", "content": _GENERATE_SYSTEM},
|
||||
{"role": "user", "content": prompt},
|
||||
]
|
||||
headers = {"Authorization": f"Bearer {LITELLM_MASTER_KEY}"}
|
||||
last_parse_error: str = ""
|
||||
last_raw: str = ""
|
||||
total_usage: dict = {"prompt_tokens": 0, "completion_tokens": 0}
|
||||
model_used = "tip-generator"
|
||||
|
||||
async with httpx.AsyncClient(timeout=30.0) as client:
|
||||
for attempt in range(1 + _MAX_GENERATE_RETRIES):
|
||||
payload = {"model": "tip-generator", "messages": messages, "temperature": 0.7}
|
||||
try:
|
||||
resp = await client.post(
|
||||
f"{LITELLM_URL}/chat/completions",
|
||||
json=payload,
|
||||
headers=headers,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise HTTPException(status_code=502, detail=f"LiteLLM error: {e.response.text}")
|
||||
except httpx.RequestError as e:
|
||||
raise HTTPException(status_code=503, detail=f"LiteLLM unreachable: {e}")
|
||||
|
||||
data = resp.json()
|
||||
usage = data.get("usage", {})
|
||||
total_usage["prompt_tokens"] += usage.get("prompt_tokens", 0)
|
||||
total_usage["completion_tokens"] += usage.get("completion_tokens", 0)
|
||||
model_used = data.get("model", "tip-generator")
|
||||
|
||||
last_raw = data["choices"][0]["message"]["content"]
|
||||
try:
|
||||
items = _parse_llm_json(last_raw)
|
||||
break
|
||||
except (json.JSONDecodeError, ValueError) as e:
|
||||
last_parse_error = str(e)
|
||||
# Feed the bad reply back so the model can self-correct
|
||||
messages.append({"role": "assistant", "content": last_raw})
|
||||
messages.append({"role": "user", "content": _RETRY_SUFFIX})
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=502,
|
||||
detail=f"LLM returned invalid JSON after {_MAX_GENERATE_RETRIES} retries: "
|
||||
f"{last_parse_error}\n{last_raw[:200]}",
|
||||
)
|
||||
|
||||
candidates = [
|
||||
TipCandidate(
|
||||
id=item.get("id", f"tip-{i}"),
|
||||
content=item.get("content", ""),
|
||||
rationale=item.get("rationale"),
|
||||
)
|
||||
for i, item in enumerate(items)
|
||||
]
|
||||
|
||||
return GenerateResponse(
|
||||
candidates=candidates,
|
||||
model=model_used,
|
||||
prompt_tokens=total_usage["prompt_tokens"],
|
||||
completion_tokens=total_usage["completion_tokens"],
|
||||
)
|
||||
|
||||
|
||||
@app.post("/score", response_model=ScoreResponse)
|
||||
def score(req: ScoreRequest) -> ScoreResponse:
|
||||
if not req.candidates:
|
||||
|
||||
Reference in New Issue
Block a user