writing the GRPO script to train qwen1.7 on A100 GRPO

training/dataset.py

@@ -0,0 +1,78 @@
+"""Generate fixed-seed training dataset for PM-Ops triage task.
+
+Each row contains a seed embedded in the prompt string so the rollout
+function can pass it to env.reset(seed=...) for reproducible episodes.
+"""
+import json
+import os
+import random
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from server.world.org_generator import generate_org_config
+from server.world.scenario_gen import generate_scenario
+
+SEED_PREFIX = "SEED:"
+
+
+def _valid_triage(scenario: dict) -> bool:
+    exp = scenario.get("expected", {})
+    return bool(exp.get("channel")) and bool(exp.get("team"))
+
+
+def generate_triage_dataset(n_episodes: int = 150, base_seed: int = 42) -> list[dict]:
+    """Return list of dataset rows with embedded seeds."""
+    rng = random.Random(base_seed)
+    rows = []
+
+    while len(rows) < n_episodes:
+        seed = rng.randint(0, 2**31)
+        difficulty = rng.choice(["easy", "medium", "medium", "hard"])
+
+        org, scenario = None, None
+        for attempt in range(10):
+            org = generate_org_config(seed + attempt, difficulty)
+            scenario = generate_scenario("triage", org, seed + attempt)
+            if _valid_triage(scenario):
+                break
+
+        if not _valid_triage(scenario):
+            continue
+
+        rows.append({
+            # Seed embedded so rollout can parse it and pass to reset()
+            "prompt": f"{SEED_PREFIX}{seed} | {scenario['brief']}",
+            "seed": seed,
+            "difficulty": difficulty,
+        })
+
+    return rows
+
+
+def parse_seed_from_prompt(prompt: str) -> int | None:
+    """Extract seed embedded by generate_triage_dataset."""
+    if not prompt.startswith(SEED_PREFIX):
+        return None
+    try:
+        return int(prompt[len(SEED_PREFIX):].split(" | ")[0])
+    except ValueError:
+        return None
+
+
+def save_dataset(rows: list[dict], path: str) -> None:
+    with open(path, "w") as f:
+        for row in rows:
+            f.write(json.dumps(row) + "\n")
+    print(f"Saved {len(rows)} episodes → {path}")
+
+
+def load_dataset(path: str) -> list[dict]:
+    with open(path) as f:
+        return [json.loads(line) for line in f]
+
+
+if __name__ == "__main__":
+    out = os.path.join(os.path.dirname(__file__), "triage_dataset.jsonl")
+    rows = generate_triage_dataset(n_episodes=150)
+    save_dataset(rows, out)

training/prompts.py

@@ -0,0 +1,76 @@
+"""System prompt and observation formatting for PM-Ops GRPO training."""
+
+SYSTEM_PROMPT = """You are an expert PM Operations agent inside a software organization.
+
+## Your Tools
+- **Ticketing** (Jira-like): create_ticket, update_ticket, assign_ticket, transition_ticket, get_ticket, list_tickets, comment_ticket
+- **Chat** (Slack-like): post_message, read_channel, list_channels, search
+- **Codebase** (GitHub-like): list_commits, get_commit, list_prs
+- **Meta**: read_runbook, finish, noop
+
+## CRITICAL — Read the Runbook First
+Every organization uses different conventions. Your FIRST action MUST be `meta.read_runbook`.
+The runbook tells you the EXACT values to use:
+- `label_taxonomy`: valid ticket labels (e.g. "defect", NOT "bug")
+- `priority_levels`: valid priorities (e.g. "critical", NOT "P1")
+- `team_map`: service → owning team
+- `oncall_channels`: service → channel to notify
+
+## Action Format
+Reason through the problem, then emit exactly ONE JSON code block as your final output:
+
+```json
+{"action_type": "meta.read_runbook", "args": {}}
+```
+
+Full list of valid action_type values:
+  meta.read_runbook | meta.finish | meta.noop
+  ticketing.create_ticket | ticketing.update_ticket | ticketing.get_ticket
+  ticketing.list_tickets | ticketing.assign_ticket | ticketing.comment_ticket
+  ticketing.transition_ticket
+  codebase.list_commits | codebase.get_commit | codebase.list_prs
+  chat.post_message | chat.read_channel | chat.list_channels | chat.search
+
+## Triage Strategy (follow this order)
+1. `meta.read_runbook` — learn this org's label, priority, team, and channel conventions
+2. `ticketing.create_ticket` — use EXACT label from label_taxonomy, EXACT priority from priority_levels
+3. `ticketing.assign_ticket` — assign to the team that owns the affected service (team_map)
+4. `chat.post_message` — post to the oncall channel for that service (oncall_channels)
+5. `meta.finish` — end the episode
+
+## Rules
+- NEVER guess label or priority values — use only what the runbook tells you
+- NEVER post to noise channels (#random, #general, #water-cooler, etc.)
+- ONLY post to the oncall channel for the affected service
+- Call `meta.finish` when done — do not exceed steps unnecessarily
+"""
+
+
+def format_observation(obs, step: int, last_action_result: dict | None = None) -> str:
+    """Convert a PMOpsObservation into a user-facing message string."""
+    if hasattr(obs, "task_brief"):
+        task_brief = obs.task_brief
+        steps_remaining = obs.steps_remaining
+        result = obs.last_action_result
+    else:
+        task_brief = obs.get("task_brief", "")
+        steps_remaining = obs.get("steps_remaining", 40)
+        result = obs.get("last_action_result", {})
+
+    if last_action_result is not None:
+        result = last_action_result
+
+    parts = [f"## Task\n{task_brief}", f"\n**Step {step}** | {steps_remaining} steps remaining"]
+
+    if result:
+        ok = result.get("ok", False)
+        if ok:
+            data = result.get("data", "")
+            data_str = str(data)[:800]
+            parts.append(f"\n**Result (success):**\n{data_str}")
+        else:
+            error = result.get("error", "Unknown error")
+            parts.append(f"\n**Result (error):** {error}")
+
+    parts.append("\nWhat is your next action? Think it through, then output a JSON code block.")
+    return "\n".join(parts)

training/rewards.py

@@ -0,0 +1,66 @@
+"""Reward functions for PM-Ops GRPO training.
+
+Weights are applied inside each function so GRPOTrainer sums them to a
+total reward in [0, 1] range. Weights must sum to 1.0:
+
+  final_score   0.50  — correctness: label + priority + team + channel
+  valid_json    0.20  — format discipline: fraction of valid JSON outputs
+  read_runbook  0.15  — process: did agent read runbook before acting?
+  efficiency    0.15  — speed: steps saved when task completed correctly
+
+To change weights, edit the multipliers below without touching the rollout.
+To switch to Option B weighting (equal weights), set all multipliers to 0.25.
+"""
+
+WEIGHT_FINAL_SCORE = 0.50
+WEIGHT_VALID_JSON = 0.20
+WEIGHT_READ_RUNBOOK = 0.15
+WEIGHT_EFFICIENCY = 0.15
+
+
+def _extract(kwargs: dict, key: str, n: int) -> list[float]:
+    rewards = kwargs.get(key, [])
+    return [float(r) for r in rewards] if rewards else [0.0] * n
+
+
+def reward_final_score(completions, **kwargs) -> list[float]:
+    """Primary correctness signal from the env grader (0–1). Weight: 0.50"""
+    raw = _extract(kwargs, "final_score_reward", len(completions))
+    return [r * WEIGHT_FINAL_SCORE for r in raw]
+
+
+def reward_valid_json(completions, **kwargs) -> list[float]:
+    """Fraction of steps with parseable JSON output (0–1). Weight: 0.20
+
+    Anti-staleness: penalises the 'output garbage every step' failure mode
+    that naive meta.noop fallback can allow.
+    """
+    raw = _extract(kwargs, "valid_json_reward", len(completions))
+    return [r * WEIGHT_VALID_JSON for r in raw]
+
+
+def reward_read_runbook(completions, **kwargs) -> list[float]:
+    """Binary: did agent call meta.read_runbook before acting? Weight: 0.15
+
+    Teaches the agent to read org conventions first instead of guessing.
+    """
+    raw = _extract(kwargs, "read_runbook_reward", len(completions))
+    return [r * WEIGHT_READ_RUNBOOK for r in raw]
+
+
+def reward_efficiency(completions, **kwargs) -> list[float]:
+    """Steps saved when task was completed correctly (0–1). Weight: 0.15
+
+    Only non-zero when final_score >= 0.3, so it doesn't reward fast failure.
+    """
+    raw = _extract(kwargs, "efficiency_reward", len(completions))
+    return [r * WEIGHT_EFFICIENCY for r in raw]
+
+
+# Convenience list for GRPOTrainer(reward_funcs=...)
+ALL_REWARD_FUNCS = [
+    reward_final_score,
+    reward_valid_json,
+    reward_read_runbook,
+    reward_efficiency,
+]

training/rollout.py

@@ -0,0 +1,287 @@
+"""Multi-turn rollout function for PM-Ops GRPO training.
+
+History design (no duplicates):
+  Each turn record stores the obs that TRIGGERED the completion, not the result.
+  build_messages reconstructs:
+    [sys] [user:obs_0] [asst:comp_0] [user:obs_1] [asst:comp_1] ... [user:current_obs]
+  current_obs is never in history — it becomes the final user message.
+
+Other design decisions:
+- Action format B: chain-of-thought reasoning + ```json block
+- Truncation: runbook-pinned sliding window (runbook pair always kept)
+- Fallback cascade: read_runbook (early) → noop (mid) → finish (late)
+- Three-pass JSON extraction: code block → raw JSON → regex
+"""
+import json
+import re
+from typing import Any
+
+from trl.experimental.openenv import generate_rollout_completions
+
+from training.dataset import parse_seed_from_prompt
+from training.prompts import SYSTEM_PROMPT, format_observation
+
+MAX_STEPS = 40
+# ~3000 tokens at 4 chars/token; leaves room for completion tokens
+MAX_PROMPT_CHARS = 12_000
+RUNBOOK_RESPONSE_MAX_CHARS = 3_000
+HISTORY_PAIRS = 6  # max (user+asst) pairs kept from non-runbook history
+
+
+# ---------------------------------------------------------------------------
+# JSON extraction — three-pass, most-specific first
+# ---------------------------------------------------------------------------
+
+def extract_json_action(text: str) -> dict | None:
+    # Pass 1: last ```json ... ``` block
+    matches = re.findall(r"```json\s*(\{.*?\})\s*```", text, re.DOTALL)
+    if matches:
+        try:
+            return json.loads(matches[-1])
+        except json.JSONDecodeError:
+            pass
+
+    # Pass 2: entire output is JSON
+    stripped = text.strip()
+    if stripped.startswith("{"):
+        try:
+            return json.loads(stripped)
+        except json.JSONDecodeError:
+            pass
+
+    # Pass 3: any {...action_type...} pattern — allow one level of nested {} (e.g. "args": {})
+    matches = re.findall(
+        r'\{(?:[^{}]|\{[^{}]*\})*"action_type"\s*:\s*"[^"]*"(?:[^{}]|\{[^{}]*\})*\}',
+        text, re.DOTALL,
+    )
+    if matches:
+        try:
+            return json.loads(matches[-1])
+        except json.JSONDecodeError:
+            pass
+
+    return None
+
+
+def step_aware_fallback(step: int) -> dict:
+    """Safe fallback that degrades gracefully across the episode."""
+    if step <= 1:
+        return {"action_type": "meta.read_runbook", "args": {}}
+    elif step >= MAX_STEPS - 3:
+        return {"action_type": "meta.finish", "args": {}}
+    return {"action_type": "meta.noop", "args": {}}
+
+
+# ---------------------------------------------------------------------------
+# Context builder — runbook-pinned sliding window, no duplicate user turns
+# ---------------------------------------------------------------------------
+
+def _chars(messages: list[dict]) -> int:
+    return sum(len(m["content"]) for m in messages)
+
+
+def build_messages(
+    turn_history: list[dict],
+    current_obs_text: str,
+) -> list[dict]:
+    """Build prompt messages with runbook-pinned sliding window truncation.
+
+    turn_history entries: {"obs_text": str, "completion": str, "is_runbook": bool}
+      obs_text   = observation that triggered this completion (user side)
+      completion = model output for that step (assistant side)
+
+    Final conversation shape:
+      [sys] [user:obs_0][asst:comp_0] ... [user:obs_k][asst:comp_k] [user:current_obs]
+    No entry in turn_history represents current_obs — it's only the final user turn.
+    """
+    # Task brief is always prepended to current_obs so it stays visible even
+    # when old context is truncated.
+    messages: list[dict] = [{"role": "system", "content": SYSTEM_PROMPT}]
+
+    # Separate the runbook exchange from the rest
+    runbook_turn: dict | None = None
+    general: list[dict] = []
+
+    for turn in turn_history:
+        if turn["is_runbook"] and runbook_turn is None:
+            runbook_turn = turn
+        else:
+            general.append(turn)
+
+    # Pin runbook exchange (truncate only if absurdly large)
+    if runbook_turn is not None:
+        rb_comp = runbook_turn["completion"][:RUNBOOK_RESPONSE_MAX_CHARS]
+        messages.append({"role": "user", "content": runbook_turn["obs_text"]})
+        messages.append({"role": "assistant", "content": rb_comp})
+
+    # Fill budget with most-recent general turns (newest first, then reverse)
+    fixed_chars = _chars(messages) + len(current_obs_text)
+    budget = MAX_PROMPT_CHARS - fixed_chars
+    window: list[dict] = []
+
+    for turn in reversed(general[-HISTORY_PAIRS:]):
+        pair_chars = len(turn["obs_text"]) + len(turn["completion"])
+        if budget - pair_chars < 0:
+            break
+        window.append(turn)
+        budget -= pair_chars
+
+    for turn in reversed(window):
+        messages.append({"role": "user", "content": turn["obs_text"]})
+        messages.append({"role": "assistant", "content": turn["completion"]})
+
+    # Current observation is always the final user turn (never stored in history)
+    messages.append({"role": "user", "content": current_obs_text})
+    return messages
+
+
+# ---------------------------------------------------------------------------
+# Observation normaliser — handles both object and dict forms
+# ---------------------------------------------------------------------------
+
+def _obs_to_dict(obs: Any) -> dict:
+    if isinstance(obs, dict):
+        return obs
+    fields = ("task_brief", "last_action_result", "step", "steps_remaining",
+              "reward", "done", "token_budget_remaining")
+    return {f: getattr(obs, f, None) for f in fields}
+
+
+def _current_obs_text(obs_dict: dict, step: int, task_brief: str) -> str:
+    """Format observation, prepending a task reminder so it survives truncation."""
+    reminder = f"**Task reminder:** {task_brief[:200]}\n\n"
+    return reminder + format_observation(obs_dict, step, obs_dict.get("last_action_result"))
+
+
+# ---------------------------------------------------------------------------
+# Single-episode rollout
+# ---------------------------------------------------------------------------
+
+def rollout_once(
+    trainer,
+    sync_env,
+    tokenizer,
+    dataset_prompt: str,
+) -> dict:
+    """Play one full PM-Ops episode. Returns trajectory + reward signals."""
+
+    seed = parse_seed_from_prompt(dataset_prompt)
+    result = sync_env.reset(seed=seed) if seed is not None else sync_env.reset()
+
+    obs = result.observation if hasattr(result, "observation") else result
+    obs_dict = _obs_to_dict(obs)
+    task_brief: str = obs_dict.get("task_brief") or dataset_prompt
+
+    # Flat trajectory buffers (TRL expects flat lists across all steps)
+    prompt_ids: list = []
+    completion_ids: list = []
+    logprobs: list = []
+
+    # Turn history for context building
+    # Each entry: {"obs_text": str, "completion": str, "is_runbook": bool}
+    turn_history: list[dict] = []
+
+    # Reward accumulators
+    valid_action_count = 0
+    read_runbook_done = False
+    final_score = 0.0
+    step = 0
+    done = False
+
+    while not done and step < MAX_STEPS:
+        # obs_text for THIS step — stored in history BEFORE stepping
+        obs_text = _current_obs_text(obs_dict, step, task_brief)
+
+        messages = build_messages(turn_history, obs_text)
+        prompt_text = tokenizer.apply_chat_template(
+            messages,
+            add_generation_prompt=True,
+            tokenize=False,
+            enable_thinking=False,
+        )
+
+        rollout_out = generate_rollout_completions(trainer, [prompt_text])[0]
+        prompt_ids.extend(rollout_out["prompt_ids"])
+        completion_ids.extend(rollout_out["completion_ids"])
+        logprobs.extend(rollout_out["logprobs"])
+
+        completion_text = rollout_out.get("text") or tokenizer.decode(
+            rollout_out["completion_ids"], skip_special_tokens=True
+        )
+
+        # Parse action; fall back gracefully on parse failure
+        parsed = extract_json_action(completion_text)
+        is_valid_json = parsed is not None
+
+        if not is_valid_json:
+            parsed = step_aware_fallback(step)
+        else:
+            valid_action_count += 1
+
+        action_type: str = parsed.get("action_type", "meta.noop")
+        args: dict = parsed.get("args", {})
+
+        if action_type == "meta.read_runbook" and not read_runbook_done:
+            read_runbook_done = True
+
+        # Store the (obs_text, completion) pair BEFORE stepping the env
+        # is_runbook marks this turn for pinning in future context windows
+        turn_history.append({
+            "obs_text": obs_text,
+            "completion": completion_text,
+            "is_runbook": (action_type == "meta.read_runbook" and is_valid_json),
+        })
+
+        # Step the environment — obs_dict now holds the NEXT state
+        result = sync_env.step({"action_type": action_type, "args": args})
+        new_obs = result.observation if hasattr(result, "observation") else result
+        obs_dict = _obs_to_dict(new_obs)
+
+        done = bool(getattr(result, "done", obs_dict.get("done", False)))
+        final_score = float(getattr(result, "reward", obs_dict.get("reward", 0.0)))
+        step += 1
+
+    # Auxiliary reward signals
+    valid_json_ratio = valid_action_count / max(step, 1)
+    efficiency = max(0.0, 1.0 - step / MAX_STEPS) if final_score >= 0.3 else 0.0
+
+    return {
+        "prompt_ids": prompt_ids,
+        "completion_ids": completion_ids,
+        "logprobs": logprobs,
+        "final_score_reward": final_score,
+        "valid_json_reward": valid_json_ratio,
+        "read_runbook_reward": 1.0 if read_runbook_done else 0.0,
+        "efficiency_reward": efficiency,
+    }
+
+
+# ---------------------------------------------------------------------------
+# GRPOTrainer-compatible rollout function (factory)
+# ---------------------------------------------------------------------------
+
+def make_rollout_func(sync_env, tokenizer):
+    """Bind env + tokenizer; return the function GRPOTrainer calls each batch."""
+
+    def rollout_func(prompts: list[str], trainer=None) -> dict:
+        out: dict[str, list] = {
+            "prompt_ids": [],
+            "completion_ids": [],
+            "logprobs": [],
+            "final_score_reward": [],
+            "valid_json_reward": [],
+            "read_runbook_reward": [],
+            "efficiency_reward": [],
+        }
+        for prompt_text in prompts:
+            episode = rollout_once(
+                trainer=trainer,
+                sync_env=sync_env,
+                tokenizer=tokenizer,
+                dataset_prompt=prompt_text,
+            )
+            for k in out:
+                out[k].append(episode[k])
+        return out
+
+    return rollout_func

training/smoke_test.py

@@ -0,0 +1,246 @@
+"""Smoke test — runs locally without TRL/vLLM.
+
+Tests in order:
+  1. Dataset generation
+  2. JSON extraction (edge cases)
+  3. build_messages structure (no duplicates, correct alternation)
+  4. Server startup + env connection
+  5. One full heuristic episode (env API end-to-end)
+
+Run from repo root:  python training/smoke_test.py
+"""
+import json
+import os
+import subprocess
+import sys
+import time
+
+import requests
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+PASS = "\033[92m[PASS]\033[0m"
+FAIL = "\033[91m[FAIL]\033[0m"
+INFO = "\033[94m[INFO]\033[0m"
+
+
+def check(label: str, cond: bool, detail: str = "") -> bool:
+    if cond:
+        print(f"{PASS} {label}")
+    else:
+        print(f"{FAIL} {label}" + (f" — {detail}" if detail else ""))
+    return cond
+
+
+# ---------------------------------------------------------------------------
+# 1. Dataset
+# ---------------------------------------------------------------------------
+print("\n── 1. Dataset ──────────────────────────────────────────────────────")
+from training.dataset import generate_triage_dataset, parse_seed_from_prompt
+
+rows = generate_triage_dataset(n_episodes=5, base_seed=99)
+check("generates 5 rows", len(rows) == 5)
+check("each row has prompt+seed+difficulty", all(
+    "prompt" in r and "seed" in r and "difficulty" in r for r in rows
+))
+seed_back = parse_seed_from_prompt(rows[0]["prompt"])
+check("seed round-trips through prompt string", seed_back == rows[0]["seed"],
+      f"got {seed_back}, expected {rows[0]['seed']}")
+print(f"  sample prompt: {rows[0]['prompt'][:100]}...")
+
+
+# ---------------------------------------------------------------------------
+# 2. JSON extraction
+# ---------------------------------------------------------------------------
+print("\n── 2. JSON extraction ──────────────────────────────────────────────")
+from training.rollout import extract_json_action, step_aware_fallback
+
+cases = [
+    # (description, input_text, expected_action_type)
+    ("code block", 'Thinking...\n```json\n{"action_type": "meta.read_runbook", "args": {}}\n```', "meta.read_runbook"),
+    ("raw JSON",   '{"action_type": "meta.finish", "args": {}}', "meta.finish"),
+    ("regex hit",  'I will do this: {"action_type": "meta.noop", "args": {}} done.', "meta.noop"),
+    ("no JSON",    "I cannot decide.", None),
+    ("bad block",  '```json\n{broken\n```', None),
+]
+for desc, text, expected in cases:
+    result = extract_json_action(text)
+    got = result.get("action_type") if result else None
+    check(f"extract: {desc}", got == expected, f"got {got!r}, expected {expected!r}")
+
+fb = step_aware_fallback(0)
+check("fallback step 0 → read_runbook", fb["action_type"] == "meta.read_runbook")
+fb = step_aware_fallback(20)
+check("fallback step 20 → noop", fb["action_type"] == "meta.noop")
+fb = step_aware_fallback(38)
+check("fallback step 38 → finish", fb["action_type"] == "meta.finish")
+
+
+# ---------------------------------------------------------------------------
+# 3. build_messages structure
+# ---------------------------------------------------------------------------
+print("\n── 3. build_messages ───────────────────────────────────────────────")
+from training.rollout import build_messages
+
+# Empty history (step 0)
+msgs = build_messages([], "First observation")
+check("step 0: starts with system", msgs[0]["role"] == "system")
+check("step 0: ends with user", msgs[-1]["role"] == "user")
+check("step 0: final user is current obs", msgs[-1]["content"] == "First observation")
+
+# Simulate 3 turns
+history = [
+    {"obs_text": "obs_0", "completion": "comp_0", "is_runbook": True},
+    {"obs_text": "obs_1", "completion": "comp_1", "is_runbook": False},
+    {"obs_text": "obs_2", "completion": "comp_2", "is_runbook": False},
+]
+msgs = build_messages(history, "current_obs")
+
+# Validate alternation: after system, must be user/asst/user/asst/.../user
+roles = [m["role"] for m in msgs]
+check("roles start with system", roles[0] == "system")
+check("roles end with user", roles[-1] == "user")
+pairs_ok = all(
+    roles[i] == "user" and roles[i+1] == "assistant"
+    for i in range(1, len(roles) - 2, 2)
+)
+check("strict user/asst alternation throughout", pairs_ok, str(roles))
+
+# Verify current_obs appears exactly once as the last message
+final_user_content = msgs[-1]["content"]
+check("current_obs is last message content", final_user_content == "current_obs")
+all_contents = [m["content"] for m in msgs]
+check("current_obs not duplicated", all_contents.count("current_obs") == 1)
+
+# Verify runbook is pinned (obs_0/comp_0 should appear even with many turns)
+all_content_str = " ".join(all_contents)
+check("runbook obs pinned", "obs_0" in all_content_str)
+check("runbook completion pinned", "comp_0" in all_content_str)
+
+
+# ---------------------------------------------------------------------------
+# 4. Server startup
+# ---------------------------------------------------------------------------
+print("\n── 4. Server startup ───────────────────────────────────────────────")
+REPO_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+ENV_URL = "http://localhost:8765"  # non-standard port to avoid conflicts
+
+proc = subprocess.Popen(
+    [sys.executable, "-m", "uvicorn", "server.app:app",
+     "--host", "0.0.0.0", "--port", "8765"],
+    cwd=REPO_DIR,
+    stdout=subprocess.DEVNULL,
+    stderr=subprocess.DEVNULL,
+)
+
+ready = False
+for _ in range(20):
+    try:
+        r = requests.get(f"{ENV_URL}/", timeout=1)
+        if r.status_code == 200:
+            ready = True
+            break
+    except Exception:
+        pass
+    time.sleep(1)
+
+check("server started on :8765", ready)
+if not ready:
+    proc.terminate()
+    print(f"{FAIL} Cannot continue without server.")
+    sys.exit(1)
+
+
+# ---------------------------------------------------------------------------
+# 5. Full heuristic episode (env API end-to-end)
+# ---------------------------------------------------------------------------
+print("\n── 5. End-to-end episode ───────────────────────────────────────────")
+from openenv.core import GenericEnvClient
+
+client = GenericEnvClient(base_url=ENV_URL).sync()
+client.connect()
+
+try:
+    # reset with explicit seed (tests seed passthrough)
+    res = client.reset(seed=rows[0]["seed"])
+    obs = res.observation if hasattr(res, "observation") else res
+
+    def _get(o, k):
+        return getattr(o, k, None) if not isinstance(o, dict) else o.get(k)
+
+    task_brief = _get(obs, "task_brief")
+    check("reset returns task_brief", bool(task_brief), repr(task_brief)[:80])
+
+    # Step 1: read runbook
+    res = client.step({"action_type": "meta.read_runbook", "args": {}})
+    obs = res.observation if hasattr(res, "observation") else res
+    last = _get(obs, "last_action_result") or {}
+    check("read_runbook ok=True", last.get("ok") is True)
+    check("runbook contains org_config", "org_config" in str(last.get("data", "")))
+
+    org = last.get("data", {}).get("org_config", {}) if isinstance(last.get("data"), dict) else {}
+    labels = list(org.get("label_taxonomy", {}).values())
+    priorities = org.get("priority_levels", [])
+    teams = list(org.get("team_map", {}).values())
+    channels = list(org.get("oncall_channels", {}).values())
+
+    check("org has labels", len(labels) > 0)
+    check("org has priorities", len(priorities) > 0)
+
+    # Step 2: create ticket with correct label/priority
+    res = client.step({
+        "action_type": "ticketing.create_ticket",
+        "args": {
+            "summary": f"Triage: {task_brief[:60]}",
+            "description": task_brief,
+            "label": labels[0],
+            "priority": priorities[1] if len(priorities) > 1 else priorities[0],
+            "assignee": teams[0] if teams else "backend",
+        },
+    })
+    obs = res.observation if hasattr(res, "observation") else res
+    last = _get(obs, "last_action_result") or {}
+    check("create_ticket ok=True", last.get("ok") is True, str(last.get("error")))
+    ticket_id = (last.get("data") or {}).get("id") if isinstance(last.get("data"), dict) else None
+    check("ticket_id returned", bool(ticket_id), repr(ticket_id))
+
+    # Step 3: assign ticket
+    if ticket_id and teams:
+        res = client.step({
+            "action_type": "ticketing.assign_ticket",
+            "args": {"ticket_id": ticket_id, "team": teams[0]},
+        })
+        obs = res.observation if hasattr(res, "observation") else res
+        last = _get(obs, "last_action_result") or {}
+        check("assign_ticket ok=True", last.get("ok") is True, str(last.get("error")))
+
+    # Step 4: post to oncall channel
+    if channels:
+        res = client.step({
+            "action_type": "chat.post_message",
+            "args": {"channel": channels[0], "text": f"Triage smoke test: {task_brief[:80]}"},
+        })
+        obs = res.observation if hasattr(res, "observation") else res
+        last = _get(obs, "last_action_result") or {}
+        check("post_message ok=True", last.get("ok") is True, str(last.get("error")))
+
+    # Step 5: finish + check reward
+    res = client.step({"action_type": "meta.finish", "args": {}})
+    done = getattr(res, "done", None)
+    reward = getattr(res, "reward", 0.0)
+    check("episode done after finish", done is True, f"done={done}")
+    check("reward is float in [0,1]", isinstance(reward, float) and 0.0 <= reward <= 1.0,
+          f"reward={reward}")
+    print(f"  episode reward: {reward:.3f}")
+
+finally:
+    client.close()
+
+proc.terminate()
+
+# ---------------------------------------------------------------------------
+# Summary
+# ---------------------------------------------------------------------------
+print("\n────────────────────────────────────────────────────────────────────")
+print("Smoke test complete. If all checks passed, training pipeline is ready.")
+print("Next: push repo to HF and run training/train.ipynb on A100 GPU Space.")

training/train.ipynb

@@ -0,0 +1,639 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# PM-Ops: Train a Project Management Agent with GRPO\n",
+    "\n",
+    "Fine-tune **Qwen3-1.7B** to handle PM operations (triage, incident routing, release notes, dep updates)\n",
+    "using GRPO via TRL and the PM-Ops OpenEnv environment.\n",
+    "\n",
+    "**GPU:** A100 40GB (HF Space or Colab Pro)  \n",
+    "**Time:** ~90 min (150 triage episodes, 1 epoch)  \n",
+    "**Environment:** PM-Ops server runs locally on localhost:8000 — no network latency during training.\n",
+    "\n",
+    "### Architecture\n",
+    "```\n",
+    "[HF GPU Space / Colab A100]\n",
+    "  ├── GRPOTrainer + Qwen3-1.7B  ← uses HF credits / Colab GPU\n",
+    "  └── PM-Ops FastAPI (localhost:8000)  ← started as subprocess, <1ms latency\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 0. Install Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -Uq \"trl>=0.17.0\" openenv-core transformers datasets accelerate vllm trackio\n",
+    "print('Dependencies installed.')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1. Clone PM-Ops Repo"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os, sys\n",
+    "\n",
+    "REPO_URL = 'https://huggingface.co/spaces/adityaguntur/pm-ops'  # update if repo moved\n",
+    "REPO_DIR = '/content/pm_ops'\n",
+    "\n",
+    "if not os.path.exists(REPO_DIR):\n",
+    "    !git clone --depth=1 -q {REPO_URL} {REPO_DIR}\n",
+    "    print(f'Cloned → {REPO_DIR}')\n",
+    "else:\n",
+    "    print(f'Already exists: {REPO_DIR}')\n",
+    "\n",
+    "# Add repo root to Python path so imports work\n",
+    "for p in [REPO_DIR, os.path.join(REPO_DIR, 'training')]:\n",
+    "    if p not in sys.path:\n",
+    "        sys.path.insert(0, p)\n",
+    "\n",
+    "os.chdir(REPO_DIR)\n",
+    "print(f'Working directory: {os.getcwd()}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. HuggingFace Login"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import notebook_login\n",
+    "notebook_login()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 3. Start PM-Ops Server Locally\n",
+    "\n",
+    "We run the environment server **on localhost** inside the same machine.\n",
+    "This eliminates network latency — each of the 40 steps per episode costs <1ms vs ~200ms over HF Spaces."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import subprocess, time, requests\n",
+    "\n",
+    "server_proc = subprocess.Popen(\n",
+    "    [sys.executable, '-m', 'uvicorn', 'server.app:app',\n",
+    "     '--host', '0.0.0.0', '--port', '8000'],\n",
+    "    cwd=REPO_DIR,\n",
+    "    stdout=subprocess.DEVNULL,\n",
+    "    stderr=subprocess.DEVNULL,\n",
+    ")\n",
+    "\n",
+    "ENV_URL = 'http://localhost:8000'\n",
+    "\n",
+    "# Wait up to 30 s for the server to be ready\n",
+    "for i in range(30):\n",
+    "    try:\n",
+    "        r = requests.get(f'{ENV_URL}/', timeout=2)\n",
+    "        if r.status_code == 200:\n",
+    "            print(f'PM-Ops server ready at {ENV_URL}  (pid={server_proc.pid})')\n",
+    "            break\n",
+    "    except Exception:\n",
+    "        pass\n",
+    "    time.sleep(1)\n",
+    "else:\n",
+    "    raise RuntimeError('Server did not start in 30 s — check uvicorn logs.')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 4. Verify Environment Connection"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from openenv.core import GenericEnvClient\n",
+    "\n",
+    "# Quick sanity check: reset → step → done\n",
+    "_check = GenericEnvClient(base_url=ENV_URL).sync()\n",
+    "with _check as env_check:\n",
+    "    res = env_check.reset()\n",
+    "    obs = res.observation if hasattr(res, 'observation') else res\n",
+    "    brief = getattr(obs, 'task_brief', obs.get('task_brief', '')) if not hasattr(obs, 'task_brief') else obs.task_brief\n",
+    "    print(f'Task brief: {brief[:120]}...')\n",
+    "    res2 = env_check.step({'action_type': 'meta.read_runbook', 'args': {}})\n",
+    "    print('Step OK — environment is working.')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 5. Load Model and Tokenizer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import AutoTokenizer\n",
+    "\n",
+    "MODEL_NAME = 'Qwen/Qwen3-1.7B'\n",
+    "tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)\n",
+    "tokenizer.pad_token = tokenizer.eos_token\n",
+    "print(f'Tokenizer ready: {MODEL_NAME}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 6. Generate Training Dataset\n",
+    "\n",
+    "150 fixed-seed triage episodes. Each seed is embedded in the prompt string so the rollout\n",
+    "function can reproduce the exact same org config via `env.reset(seed=...)`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datasets import Dataset\n",
+    "from training.dataset import generate_triage_dataset\n",
+    "\n",
+    "N_EPISODES = 150  # increase to 500 for full training run\n",
+    "\n",
+    "rows = generate_triage_dataset(n_episodes=N_EPISODES, base_seed=42)\n",
+    "dataset = Dataset.from_list([{'prompt': r['prompt']} for r in rows])\n",
+    "print(f'Dataset: {len(dataset)} triage episodes')\n",
+    "print(f'Sample prompt: {dataset[0][\"prompt\"][:120]}...')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 7. Create Persistent Environment Client\n",
+    "\n",
+    "One WebSocket connection is reused across all rollouts — no reconnect overhead per episode."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from openenv.core import GenericEnvClient\n",
+    "\n",
+    "sync_env = GenericEnvClient(base_url=ENV_URL).sync()\n",
+    "sync_env.connect()\n",
+    "print('Persistent training connection established.')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8. Build Rollout Function\n",
+    "\n",
+    "Key features:\n",
+    "- **Option B action format**: chain-of-thought reasoning + `\\`\\`\\`json` block\n",
+    "- **Runbook-pinned truncation**: runbook response always kept in context, sliding window for the rest\n",
+    "- **Step-aware fallback**: `read_runbook` (early) → `noop` (mid) → `finish` (late) when JSON parse fails\n",
+    "- **Three-pass JSON extraction**: code block → raw JSON → regex pattern"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from training.rollout import make_rollout_func\n",
+    "\n",
+    "rollout_func = make_rollout_func(sync_env=sync_env, tokenizer=tokenizer)\n",
+    "print('Rollout function ready.')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 9. Define Reward Functions\n",
+    "\n",
+    "| Function | Weight | What it measures |\n",
+    "|---|---|---|\n",
+    "| `reward_final_score` | 0.50 | Correctness: label + priority + team + channel |\n",
+    "| `reward_valid_json` | 0.20 | Format: fraction of steps with parseable JSON |\n",
+    "| `reward_read_runbook` | 0.15 | Process: read runbook before acting? |\n",
+    "| `reward_efficiency` | 0.15 | Speed: steps saved when correctly done |"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from training.rewards import ALL_REWARD_FUNCS\n",
+    "print(f'Reward functions: {[f.__name__ for f in ALL_REWARD_FUNCS]}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 10. Configure GRPO Training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from trl import GRPOConfig\n",
+    "\n",
+    "OUTPUT_DIR = 'pm-ops-grpo-Qwen3-1.7B-triage'\n",
+    "\n",
+    "grpo_config = GRPOConfig(\n",
+    "    # --- training ---\n",
+    "    num_train_epochs=1,\n",
+    "    learning_rate=5e-6,\n",
+    "    gradient_accumulation_steps=64,\n",
+    "    per_device_train_batch_size=1,\n",
+    "    warmup_steps=10,\n",
+    "    num_generations=2,          # 2 trajectories per episode for relative ranking\n",
+    "\n",
+    "    # --- sequence lengths (longer than Wordle due to JSON + reasoning) ---\n",
+    "    max_completion_length=512,  # room for reasoning + JSON action block\n",
+    "    max_prompt_length=4096,     # accumulated multi-turn context\n",
+    "\n",
+    "    # --- vLLM colocate (generation + training share A100) ---\n",
+    "    use_vllm=True,\n",
+    "    vllm_mode='colocate',\n",
+    "    vllm_gpu_memory_utilization=0.3,  # ~12 GB for KV cache on A100 40GB\n",
+    "\n",
+    "    # --- output + logging ---\n",
+    "    output_dir=OUTPUT_DIR,\n",
+    "    report_to='trackio',\n",
+    "    trackio_space_id=OUTPUT_DIR,\n",
+    "    logging_steps=1,\n",
+    "    save_steps=25,\n",
+    "    gradient_checkpointing=True,\n",
+    "    gradient_checkpointing_kwargs={'use_reentrant': False},\n",
+    "    push_to_hub=True,\n",
+    ")\n",
+    "\n",
+    "print(f'Output dir: {OUTPUT_DIR}')\n",
+    "print(f'Effective batch: {grpo_config.per_device_train_batch_size * grpo_config.gradient_accumulation_steps}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 11. Create Trainer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from trl import GRPOTrainer\n",
+    "\n",
+    "trainer = GRPOTrainer(\n",
+    "    model=MODEL_NAME,\n",
+    "    processing_class=tokenizer,\n",
+    "    reward_funcs=ALL_REWARD_FUNCS,\n",
+    "    train_dataset=dataset,\n",
+    "    args=grpo_config,\n",
+    "    rollout_func=rollout_func,\n",
+    ")\n",
+    "print('GRPOTrainer ready.')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 12. GPU Check"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "gpu = torch.cuda.get_device_properties(0)\n",
+    "reserved_before = round(torch.cuda.max_memory_reserved() / 1024**3, 2)\n",
+    "total_gb = round(gpu.total_memory / 1024**3, 2)\n",
+    "print(f'GPU: {gpu.name} — {total_gb} GB total, {reserved_before} GB reserved')\n",
+    "assert total_gb >= 38, f'Need A100 40GB, got {total_gb} GB — switch runtime!'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 13. Train  (~90 min on A100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trainer_stats = trainer.train()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "used_gb = round(torch.cuda.max_memory_reserved() / 1024**3, 2)\n",
+    "train_mins = round(trainer_stats.metrics.get('train_runtime', 0) / 60, 1)\n",
+    "print(f'Training time : {train_mins} min')\n",
+    "print(f'Peak GPU usage: {used_gb} GB / {total_gb} GB ({round(used_gb/total_gb*100,1)}%)')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 14. Save and Push"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sync_env.close()  # close persistent connection before saving\n",
+    "trainer.save_model(OUTPUT_DIR)\n",
+    "trainer.push_to_hub()\n",
+    "print(f'Model saved to {OUTPUT_DIR} and pushed to HF Hub.')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 15. Evaluate: Baseline vs Trained\n",
+    "\n",
+    "Run both the heuristic baseline and the trained model on 10 fresh triage episodes.\n",
+    "Uses the remote HF Space for eval so no local server needed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "from transformers import AutoModelForCausalLM\n",
+    "from openenv.core import GenericEnvClient\n",
+    "from training.rollout import extract_json_action, step_aware_fallback, build_messages, _obs_to_dict\n",
+    "from training.prompts import SYSTEM_PROMPT, format_observation\n",
+    "from inference import baseline_agent\n",
+    "\n",
+    "EVAL_URL = 'https://adityaguntur-pm-ops.hf.space'  # remote Space for eval\n",
+    "N_EVAL = 10\n",
+    "\n",
+    "fine_tuned_model = AutoModelForCausalLM.from_pretrained(\n",
+    "    OUTPUT_DIR, torch_dtype='auto', device_map='auto'\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def eval_trained(sync_env, model, tokenizer, n=N_EVAL):\n",
+    "    scores = []\n",
+    "    for i in range(n):\n",
+    "        result = sync_env.reset()\n",
+    "        obs = result.observation if hasattr(result, 'observation') else result\n",
+    "        obs_dict = _obs_to_dict(obs)\n",
+    "        task_brief = obs_dict.get('task_brief', '')\n",
+    "        history = []\n",
+    "        done = False\n",
+    "        step = 0\n",
+    "        score = 0.0\n",
+    "\n",
+    "        while not done and step < 40:\n",
+    "            obs_text = format_observation(obs_dict, step, obs_dict.get('last_action_result'))\n",
+    "            messages = build_messages(task_brief, history, obs_text)\n",
+    "            prompt_text = tokenizer.apply_chat_template(\n",
+    "                messages, add_generation_prompt=True,\n",
+    "                tokenize=False, enable_thinking=False,\n",
+    "            )\n",
+    "            inputs = tokenizer([prompt_text], return_tensors='pt').to(model.device)\n",
+    "            out_ids = model.generate(**inputs, max_new_tokens=512)\n",
+    "            completion = tokenizer.decode(\n",
+    "                out_ids[0][len(inputs.input_ids[0]):], skip_special_tokens=True\n",
+    "            )\n",
+    "            parsed = extract_json_action(completion) or step_aware_fallback(step)\n",
+    "            result = sync_env.step({'action_type': parsed['action_type'], 'args': parsed.get('args', {})})\n",
+    "            obs = result.observation if hasattr(result, 'observation') else result\n",
+    "            obs_dict = _obs_to_dict(obs)\n",
+    "            done = bool(getattr(result, 'done', obs_dict.get('done', False)))\n",
+    "            score = float(getattr(result, 'reward', obs_dict.get('reward', 0.0)))\n",
+    "            history.append({'role': 'assistant', 'content': completion, 'is_runbook': False})\n",
+    "            step += 1\n",
+    "\n",
+    "        scores.append(score)\n",
+    "        print(f'  Eval episode {i+1}/{n}: score={score:.2f}')\n",
+    "    return scores\n",
+    "\n",
+    "\n",
+    "def eval_baseline(sync_env, n=N_EVAL):\n",
+    "    scores = []\n",
+    "    for i in range(n):\n",
+    "        result = sync_env.reset()\n",
+    "        obs = result.observation if hasattr(result, 'observation') else result\n",
+    "        obs_dict = _obs_to_dict(obs)\n",
+    "        org_config = {}\n",
+    "        done = False\n",
+    "        step = 0\n",
+    "        score = 0.0\n",
+    "        while not done and step < 40:\n",
+    "            action_type, args = baseline_agent(obs_dict, org_config)\n",
+    "            result = sync_env.step({'action_type': action_type, 'args': args})\n",
+    "            obs = result.observation if hasattr(result, 'observation') else result\n",
+    "            obs_dict = _obs_to_dict(obs)\n",
+    "            done = bool(getattr(result, 'done', obs_dict.get('done', False)))\n",
+    "            score = float(getattr(result, 'reward', obs_dict.get('reward', 0.0)))\n",
+    "            step += 1\n",
+    "        scores.append(score)\n",
+    "        print(f'  Baseline episode {i+1}/{n}: score={score:.2f}')\n",
+    "    return scores\n",
+    "\n",
+    "\n",
+    "eval_client = GenericEnvClient(base_url=EVAL_URL).sync()\n",
+    "\n",
+    "with eval_client as env_eval:\n",
+    "    print('--- Baseline agent ---')\n",
+    "    baseline_scores = eval_baseline(env_eval)\n",
+    "\n",
+    "with GenericEnvClient(base_url=EVAL_URL).sync() as env_eval:\n",
+    "    print('--- Trained agent ---')\n",
+    "    trained_scores = eval_trained(env_eval, fine_tuned_model, tokenizer)\n",
+    "\n",
+    "print(f'\\nBaseline avg: {sum(baseline_scores)/len(baseline_scores):.3f}')\n",
+    "print(f'Trained  avg: {sum(trained_scores)/len(trained_scores):.3f}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 16. Plot Results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "fig, axes = plt.subplots(1, 2, figsize=(12, 4))\n",
+    "\n",
+    "# Left: episode-by-episode comparison\n",
+    "ax = axes[0]\n",
+    "x = np.arange(N_EVAL)\n",
+    "w = 0.35\n",
+    "ax.bar(x - w/2, baseline_scores, w, label='Baseline', color='steelblue', alpha=0.8)\n",
+    "ax.bar(x + w/2, trained_scores, w, label='Trained (GRPO)', color='coral', alpha=0.8)\n",
+    "ax.axhline(sum(baseline_scores)/N_EVAL, color='steelblue', linestyle='--', alpha=0.6)\n",
+    "ax.axhline(sum(trained_scores)/N_EVAL, color='coral', linestyle='--', alpha=0.6)\n",
+    "ax.set_xlabel('Eval episode')\n",
+    "ax.set_ylabel('Episode reward (0–1)')\n",
+    "ax.set_title('Baseline vs Trained — per-episode reward')\n",
+    "ax.set_xticks(x)\n",
+    "ax.set_ylim(0, 1.05)\n",
+    "ax.legend()\n",
+    "\n",
+    "# Right: average summary\n",
+    "ax2 = axes[1]\n",
+    "avgs = [sum(baseline_scores)/N_EVAL, sum(trained_scores)/N_EVAL]\n",
+    "bars = ax2.bar(['Baseline', 'Trained (GRPO)'], avgs,\n",
+    "               color=['steelblue', 'coral'], alpha=0.85, width=0.5)\n",
+    "for bar, val in zip(bars, avgs):\n",
+    "    ax2.text(bar.get_x() + bar.get_width()/2, val + 0.01, f'{val:.3f}',\n",
+    "             ha='center', fontsize=12, fontweight='bold')\n",
+    "ax2.set_ylabel('Average reward (0–1)')\n",
+    "ax2.set_title(f'Average over {N_EVAL} triage episodes')\n",
+    "ax2.set_ylim(0, 1.05)\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.savefig('eval_results.png', dpi=150, bbox_inches='tight')\n",
+    "plt.show()\n",
+    "print('Saved: eval_results.png')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 17. Teardown"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "server_proc.terminate()\n",
+    "print('Local PM-Ops server stopped.')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "## Summary\n",
+    "\n",
+    "What happened:\n",
+    "1. Started PM-Ops server locally (0ms latency for 40-step episodes)\n",
+    "2. Generated 150 fixed-seed triage episodes (reproducible)\n",
+    "3. Trained Qwen3-1.7B with GRPO using 4 reward signals\n",
+    "4. Compared baseline heuristic vs trained agent on 10 fresh episodes\n",
+    "\n",
+    "### Reward signal design\n",
+    "- `reward_final_score × 0.50` — correctness (label + priority + team + channel)\n",
+    "- `reward_valid_json × 0.20` — format discipline (anti-staleness)\n",
+    "- `reward_read_runbook × 0.15` — process (read before acting)\n",
+    "- `reward_efficiency × 0.15` — speed (fewer steps when correct)\n",
+    "\n",
+    "### What to try next\n",
+    "- Scale to 500 episodes across all 4 task types (triage + incident_routing + release_notes + dep_update)\n",
+    "- Larger model: Qwen3-4B\n",
+    "- Tune reward weights in `training/rewards.py`\n",
+    "- Switch `WEIGHT_*` constants to equal 0.25 each to test Option B (equal weights)\n",
+    "- Longer training: `num_train_epochs=3`"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.11.0"
+  },
+  "accelerator": "GPU",
+  "gpuClass": "premium"
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

training/triage_dataset.jsonl

@@ -0,0 +1,150 @@
+{"prompt": "SEED:478163327 | Support escalation: payments is intermittently failing for EU users. Triage and route per org process.", "seed": 478163327, "difficulty": "easy"}
+{"prompt": "SEED:1181241943 | A user reported that the notifications is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1181241943, "difficulty": "medium"}
+{"prompt": "SEED:958682846 | Monitoring alert: elevated error rate on api-gateway. File a bug ticket and page the right team.", "seed": 958682846, "difficulty": "medium"}
+{"prompt": "SEED:440213415 | A user reported that the inventory is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 440213415, "difficulty": "easy"}
+{"prompt": "SEED:1812140441 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1812140441, "difficulty": "easy"}
+{"prompt": "SEED:127978094 | A user reported that the auth is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 127978094, "difficulty": "easy"}
+{"prompt": "SEED:939042955 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 939042955, "difficulty": "medium"}
+{"prompt": "SEED:113971123 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 113971123, "difficulty": "medium"}
+{"prompt": "SEED:1801823908 | Support escalation: api-gateway is intermittently failing for EU users. Triage and route per org process.", "seed": 1801823908, "difficulty": "medium"}
+{"prompt": "SEED:1929338154 | A user reported that the checkout is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1929338154, "difficulty": "medium"}
+{"prompt": "SEED:27911967 | Monitoring alert: elevated error rate on api-gateway. File a bug ticket and page the right team.", "seed": 27911967, "difficulty": "medium"}
+{"prompt": "SEED:1815115025 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1815115025, "difficulty": "medium"}
+{"prompt": "SEED:1193448329 | Support escalation: checkout is intermittently failing for EU users. Triage and route per org process.", "seed": 1193448329, "difficulty": "medium"}
+{"prompt": "SEED:924765563 | Monitoring alert: elevated error rate on search. File a bug ticket and page the right team.", "seed": 924765563, "difficulty": "medium"}
+{"prompt": "SEED:438989805 | Support escalation: notifications is intermittently failing for EU users. Triage and route per org process.", "seed": 438989805, "difficulty": "easy"}
+{"prompt": "SEED:1631775357 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 1631775357, "difficulty": "easy"}
+{"prompt": "SEED:1541804686 | Support escalation: api-gateway is intermittently failing for EU users. Triage and route per org process.", "seed": 1541804686, "difficulty": "medium"}
+{"prompt": "SEED:1136108454 | Support escalation: payments is intermittently failing for EU users. Triage and route per org process.", "seed": 1136108454, "difficulty": "easy"}
+{"prompt": "SEED:1973214822 | Support escalation: payments is intermittently failing for EU users. Triage and route per org process.", "seed": 1973214822, "difficulty": "easy"}
+{"prompt": "SEED:1625792787 | A user reported that the checkout is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1625792787, "difficulty": "easy"}
+{"prompt": "SEED:1259191105 | Monitoring alert: elevated error rate on checkout. File a bug ticket and page the right team.", "seed": 1259191105, "difficulty": "medium"}
+{"prompt": "SEED:825873196 | A user reported that the api-gateway is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 825873196, "difficulty": "easy"}
+{"prompt": "SEED:196814233 | Support escalation: api-gateway is intermittently failing for EU users. Triage and route per org process.", "seed": 196814233, "difficulty": "medium"}
+{"prompt": "SEED:1242911821 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1242911821, "difficulty": "easy"}
+{"prompt": "SEED:999829240 | Monitoring alert: elevated error rate on checkout. File a bug ticket and page the right team.", "seed": 999829240, "difficulty": "easy"}
+{"prompt": "SEED:1632629719 | Monitoring alert: elevated error rate on notifications. File a bug ticket and page the right team.", "seed": 1632629719, "difficulty": "medium"}
+{"prompt": "SEED:1947382419 | Support escalation: inventory is intermittently failing for EU users. Triage and route per org process.", "seed": 1947382419, "difficulty": "medium"}
+{"prompt": "SEED:698594025 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 698594025, "difficulty": "medium"}
+{"prompt": "SEED:1525876051 | A user reported that the checkout is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1525876051, "difficulty": "medium"}
+{"prompt": "SEED:1146660997 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 1146660997, "difficulty": "easy"}
+{"prompt": "SEED:735034881 | Support escalation: inventory is intermittently failing for EU users. Triage and route per org process.", "seed": 735034881, "difficulty": "medium"}
+{"prompt": "SEED:701808367 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 701808367, "difficulty": "hard"}
+{"prompt": "SEED:1629748727 | A user reported that the api-gateway is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1629748727, "difficulty": "medium"}
+{"prompt": "SEED:943239974 | Support escalation: search is intermittently failing for EU users. Triage and route per org process.", "seed": 943239974, "difficulty": "medium"}
+{"prompt": "SEED:240251661 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 240251661, "difficulty": "medium"}
+{"prompt": "SEED:137869475 | Support escalation: api-gateway is intermittently failing for EU users. Triage and route per org process.", "seed": 137869475, "difficulty": "medium"}
+{"prompt": "SEED:1722989659 | Monitoring alert: elevated error rate on search. File a bug ticket and page the right team.", "seed": 1722989659, "difficulty": "medium"}
+{"prompt": "SEED:284277889 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 284277889, "difficulty": "medium"}
+{"prompt": "SEED:1351531223 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1351531223, "difficulty": "medium"}
+{"prompt": "SEED:2144181937 | Monitoring alert: elevated error rate on checkout. File a bug ticket and page the right team.", "seed": 2144181937, "difficulty": "hard"}
+{"prompt": "SEED:1970753705 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 1970753705, "difficulty": "medium"}
+{"prompt": "SEED:1137651678 | Support escalation: payments is intermittently failing for EU users. Triage and route per org process.", "seed": 1137651678, "difficulty": "medium"}
+{"prompt": "SEED:1059257080 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1059257080, "difficulty": "medium"}
+{"prompt": "SEED:1840109255 | Support escalation: auth is intermittently failing for EU users. Triage and route per org process.", "seed": 1840109255, "difficulty": "hard"}
+{"prompt": "SEED:1554762903 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1554762903, "difficulty": "medium"}
+{"prompt": "SEED:594130308 | Support escalation: checkout is intermittently failing for EU users. Triage and route per org process.", "seed": 594130308, "difficulty": "hard"}
+{"prompt": "SEED:390452952 | Support escalation: inventory is intermittently failing for EU users. Triage and route per org process.", "seed": 390452952, "difficulty": "easy"}
+{"prompt": "SEED:470939445 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 470939445, "difficulty": "medium"}
+{"prompt": "SEED:687117441 | Support escalation: notifications is intermittently failing for EU users. Triage and route per org process.", "seed": 687117441, "difficulty": "hard"}
+{"prompt": "SEED:272849424 | A user reported that the search is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 272849424, "difficulty": "hard"}
+{"prompt": "SEED:1639042338 | Support escalation: checkout is intermittently failing for EU users. Triage and route per org process.", "seed": 1639042338, "difficulty": "hard"}
+{"prompt": "SEED:1079815404 | Support escalation: search is intermittently failing for EU users. Triage and route per org process.", "seed": 1079815404, "difficulty": "easy"}
+{"prompt": "SEED:491995979 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 491995979, "difficulty": "medium"}
+{"prompt": "SEED:1461042543 | A user reported that the inventory is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1461042543, "difficulty": "easy"}
+{"prompt": "SEED:1260573448 | Support escalation: auth is intermittently failing for EU users. Triage and route per org process.", "seed": 1260573448, "difficulty": "hard"}
+{"prompt": "SEED:679282378 | Monitoring alert: elevated error rate on search. File a bug ticket and page the right team.", "seed": 679282378, "difficulty": "hard"}
+{"prompt": "SEED:13938521 | A user reported that the auth is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 13938521, "difficulty": "medium"}
+{"prompt": "SEED:767303988 | Support escalation: api-gateway is intermittently failing for EU users. Triage and route per org process.", "seed": 767303988, "difficulty": "easy"}
+{"prompt": "SEED:1281810600 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1281810600, "difficulty": "medium"}
+{"prompt": "SEED:656439677 | Monitoring alert: elevated error rate on checkout. File a bug ticket and page the right team.", "seed": 656439677, "difficulty": "medium"}
+{"prompt": "SEED:693847829 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 693847829, "difficulty": "easy"}
+{"prompt": "SEED:1392239675 | A user reported that the notifications is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1392239675, "difficulty": "hard"}
+{"prompt": "SEED:83651970 | A user reported that the search is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 83651970, "difficulty": "easy"}
+{"prompt": "SEED:1558990517 | Support escalation: checkout is intermittently failing for EU users. Triage and route per org process.", "seed": 1558990517, "difficulty": "medium"}
+{"prompt": "SEED:1028439863 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1028439863, "difficulty": "easy"}
+{"prompt": "SEED:1034535593 | Monitoring alert: elevated error rate on notifications. File a bug ticket and page the right team.", "seed": 1034535593, "difficulty": "easy"}
+{"prompt": "SEED:367878761 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 367878761, "difficulty": "hard"}
+{"prompt": "SEED:297265480 | A user reported that the notifications is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 297265480, "difficulty": "medium"}
+{"prompt": "SEED:551437149 | Monitoring alert: elevated error rate on notifications. File a bug ticket and page the right team.", "seed": 551437149, "difficulty": "hard"}
+{"prompt": "SEED:709214891 | A user reported that the checkout is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 709214891, "difficulty": "medium"}
+{"prompt": "SEED:1817363615 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1817363615, "difficulty": "medium"}
+{"prompt": "SEED:863937247 | A user reported that the inventory is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 863937247, "difficulty": "medium"}
+{"prompt": "SEED:1713658874 | Support escalation: auth is intermittently failing for EU users. Triage and route per org process.", "seed": 1713658874, "difficulty": "medium"}
+{"prompt": "SEED:1881625505 | A user reported that the notifications is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1881625505, "difficulty": "hard"}
+{"prompt": "SEED:519709079 | Monitoring alert: elevated error rate on notifications. File a bug ticket and page the right team.", "seed": 519709079, "difficulty": "medium"}
+{"prompt": "SEED:965067727 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 965067727, "difficulty": "easy"}
+{"prompt": "SEED:1452066459 | A user reported that the notifications is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1452066459, "difficulty": "easy"}
+{"prompt": "SEED:988335251 | A user reported that the auth is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 988335251, "difficulty": "medium"}
+{"prompt": "SEED:30884438 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 30884438, "difficulty": "easy"}
+{"prompt": "SEED:252860896 | Support escalation: api-gateway is intermittently failing for EU users. Triage and route per org process.", "seed": 252860896, "difficulty": "medium"}
+{"prompt": "SEED:289482182 | A user reported that the auth is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 289482182, "difficulty": "easy"}
+{"prompt": "SEED:1419179580 | Support escalation: payments is intermittently failing for EU users. Triage and route per org process.", "seed": 1419179580, "difficulty": "easy"}
+{"prompt": "SEED:1022222125 | Support escalation: checkout is intermittently failing for EU users. Triage and route per org process.", "seed": 1022222125, "difficulty": "medium"}
+{"prompt": "SEED:2084839399 | Monitoring alert: elevated error rate on auth. File a bug ticket and page the right team.", "seed": 2084839399, "difficulty": "medium"}
+{"prompt": "SEED:568275055 | Support escalation: notifications is intermittently failing for EU users. Triage and route per org process.", "seed": 568275055, "difficulty": "hard"}
+{"prompt": "SEED:1043665192 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 1043665192, "difficulty": "hard"}
+{"prompt": "SEED:1748309234 | A user reported that the search is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1748309234, "difficulty": "medium"}
+{"prompt": "SEED:405126228 | A user reported that the inventory is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 405126228, "difficulty": "easy"}
+{"prompt": "SEED:1851350739 | Monitoring alert: elevated error rate on checkout. File a bug ticket and page the right team.", "seed": 1851350739, "difficulty": "medium"}
+{"prompt": "SEED:1819256337 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1819256337, "difficulty": "hard"}
+{"prompt": "SEED:2005855667 | Support escalation: inventory is intermittently failing for EU users. Triage and route per org process.", "seed": 2005855667, "difficulty": "easy"}
+{"prompt": "SEED:422701550 | A user reported that the auth is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 422701550, "difficulty": "easy"}
+{"prompt": "SEED:1729245242 | A user reported that the auth is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1729245242, "difficulty": "medium"}
+{"prompt": "SEED:469306919 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 469306919, "difficulty": "medium"}
+{"prompt": "SEED:822873088 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 822873088, "difficulty": "medium"}
+{"prompt": "SEED:1926780541 | Support escalation: checkout is intermittently failing for EU users. Triage and route per org process.", "seed": 1926780541, "difficulty": "medium"}
+{"prompt": "SEED:1811967841 | A user reported that the api-gateway is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1811967841, "difficulty": "medium"}
+{"prompt": "SEED:1196342297 | Support escalation: payments is intermittently failing for EU users. Triage and route per org process.", "seed": 1196342297, "difficulty": "hard"}
+{"prompt": "SEED:1072910527 | Monitoring alert: elevated error rate on api-gateway. File a bug ticket and page the right team.", "seed": 1072910527, "difficulty": "easy"}
+{"prompt": "SEED:1903232052 | Support escalation: inventory is intermittently failing for EU users. Triage and route per org process.", "seed": 1903232052, "difficulty": "easy"}
+{"prompt": "SEED:217275224 | A user reported that the inventory is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 217275224, "difficulty": "easy"}
+{"prompt": "SEED:400560567 | Monitoring alert: elevated error rate on checkout. File a bug ticket and page the right team.", "seed": 400560567, "difficulty": "medium"}
+{"prompt": "SEED:714300770 | A user reported that the notifications is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 714300770, "difficulty": "hard"}
+{"prompt": "SEED:2085812759 | Support escalation: notifications is intermittently failing for EU users. Triage and route per org process.", "seed": 2085812759, "difficulty": "hard"}
+{"prompt": "SEED:918037633 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 918037633, "difficulty": "hard"}
+{"prompt": "SEED:251837136 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 251837136, "difficulty": "medium"}
+{"prompt": "SEED:1627677155 | Support escalation: api-gateway is intermittently failing for EU users. Triage and route per org process.", "seed": 1627677155, "difficulty": "easy"}
+{"prompt": "SEED:1676848676 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 1676848676, "difficulty": "medium"}
+{"prompt": "SEED:1954246074 | A user reported that the api-gateway is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1954246074, "difficulty": "medium"}
+{"prompt": "SEED:1816803306 | Monitoring alert: elevated error rate on search. File a bug ticket and page the right team.", "seed": 1816803306, "difficulty": "hard"}
+{"prompt": "SEED:664847319 | A user reported that the auth is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 664847319, "difficulty": "medium"}
+{"prompt": "SEED:1274350418 | Support escalation: search is intermittently failing for EU users. Triage and route per org process.", "seed": 1274350418, "difficulty": "medium"}
+{"prompt": "SEED:251183830 | Support escalation: api-gateway is intermittently failing for EU users. Triage and route per org process.", "seed": 251183830, "difficulty": "easy"}
+{"prompt": "SEED:1346922426 | Monitoring alert: elevated error rate on checkout. File a bug ticket and page the right team.", "seed": 1346922426, "difficulty": "easy"}
+{"prompt": "SEED:215359682 | Monitoring alert: elevated error rate on api-gateway. File a bug ticket and page the right team.", "seed": 215359682, "difficulty": "hard"}
+{"prompt": "SEED:676168421 | Support escalation: notifications is intermittently failing for EU users. Triage and route per org process.", "seed": 676168421, "difficulty": "easy"}
+{"prompt": "SEED:344076115 | A user reported that the notifications is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 344076115, "difficulty": "medium"}
+{"prompt": "SEED:294296873 | Support escalation: payments is intermittently failing for EU users. Triage and route per org process.", "seed": 294296873, "difficulty": "easy"}
+{"prompt": "SEED:1010193046 | Monitoring alert: elevated error rate on api-gateway. File a bug ticket and page the right team.", "seed": 1010193046, "difficulty": "hard"}
+{"prompt": "SEED:514909066 | A user reported that the search is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 514909066, "difficulty": "medium"}
+{"prompt": "SEED:170689150 | Support escalation: notifications is intermittently failing for EU users. Triage and route per org process.", "seed": 170689150, "difficulty": "easy"}
+{"prompt": "SEED:1800557283 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1800557283, "difficulty": "medium"}
+{"prompt": "SEED:1119980130 | A user reported that the auth is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1119980130, "difficulty": "medium"}
+{"prompt": "SEED:1349409434 | A user reported that the checkout is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1349409434, "difficulty": "medium"}
+{"prompt": "SEED:1140805649 | Support escalation: checkout is intermittently failing for EU users. Triage and route per org process.", "seed": 1140805649, "difficulty": "hard"}
+{"prompt": "SEED:562117925 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 562117925, "difficulty": "medium"}
+{"prompt": "SEED:1963764597 | A user reported that the api-gateway is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1963764597, "difficulty": "medium"}
+{"prompt": "SEED:311570307 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 311570307, "difficulty": "easy"}
+{"prompt": "SEED:1968321319 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1968321319, "difficulty": "easy"}
+{"prompt": "SEED:314652384 | A user reported that the checkout is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 314652384, "difficulty": "medium"}
+{"prompt": "SEED:1139027119 | Monitoring alert: elevated error rate on search. File a bug ticket and page the right team.", "seed": 1139027119, "difficulty": "medium"}
+{"prompt": "SEED:1498981529 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1498981529, "difficulty": "easy"}
+{"prompt": "SEED:1049193572 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1049193572, "difficulty": "medium"}
+{"prompt": "SEED:1224011538 | Support escalation: notifications is intermittently failing for EU users. Triage and route per org process.", "seed": 1224011538, "difficulty": "medium"}
+{"prompt": "SEED:1881988384 | A user reported that the payments is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1881988384, "difficulty": "medium"}
+{"prompt": "SEED:33599984 | Support escalation: search is intermittently failing for EU users. Triage and route per org process.", "seed": 33599984, "difficulty": "medium"}
+{"prompt": "SEED:444900634 | A user reported that the checkout is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 444900634, "difficulty": "medium"}
+{"prompt": "SEED:1135872495 | A user reported that the api-gateway is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 1135872495, "difficulty": "easy"}
+{"prompt": "SEED:459716009 | A user reported that the checkout is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 459716009, "difficulty": "medium"}
+{"prompt": "SEED:1169726681 | Monitoring alert: elevated error rate on search. File a bug ticket and page the right team.", "seed": 1169726681, "difficulty": "medium"}
+{"prompt": "SEED:904647469 | Support escalation: inventory is intermittently failing for EU users. Triage and route per org process.", "seed": 904647469, "difficulty": "medium"}
+{"prompt": "SEED:874443787 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 874443787, "difficulty": "medium"}
+{"prompt": "SEED:2098228320 | Monitoring alert: elevated error rate on inventory. File a bug ticket and page the right team.", "seed": 2098228320, "difficulty": "medium"}
+{"prompt": "SEED:218179599 | A user reported that the inventory is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 218179599, "difficulty": "easy"}
+{"prompt": "SEED:1819244083 | Monitoring alert: elevated error rate on api-gateway. File a bug ticket and page the right team.", "seed": 1819244083, "difficulty": "medium"}
+{"prompt": "SEED:189351213 | Support escalation: inventory is intermittently failing for EU users. Triage and route per org process.", "seed": 189351213, "difficulty": "easy"}
+{"prompt": "SEED:1432614422 | Monitoring alert: elevated error rate on search. File a bug ticket and page the right team.", "seed": 1432614422, "difficulty": "medium"}
+{"prompt": "SEED:1125089309 | Monitoring alert: elevated error rate on payments. File a bug ticket and page the right team.", "seed": 1125089309, "difficulty": "medium"}
+{"prompt": "SEED:1897669065 | Support escalation: inventory is intermittently failing for EU users. Triage and route per org process.", "seed": 1897669065, "difficulty": "hard"}
+{"prompt": "SEED:41531046 | A user reported that the inventory is returning 500 errors. The issue started 20 minutes ago. Triage this bug: file a ticket with the correct label and priority, assign it to the right team, and notify the correct oncall channel.", "seed": 41531046, "difficulty": "easy"}