"""Pipeline building blocks: agent races (with grace), single-slot, schemas, prompts, guide status. Holds the mutable pipeline state (generation semaphore, cancel set). Access the cancel set ONLY through the functions here — copied references in other modules would diverge on a re-assign. """ import asyncio import logging from dataclasses import dataclass from datetime import datetime, timezone from typing import Callable from agents import run_agent, kill_process, cancel_scope, clear_scope from config import MAX_CONCURRENT_GENERATIONS, TEMPLATES_DIR, TIMEOUTS from database import update_guide log = logging.getLogger("creator.pipeline") _semaphore = asyncio.Semaphore(MAX_CONCURRENT_GENERATIONS) _cancelled: set[str] = set() async def cancel_guide(guide_id: str) -> bool: _cancelled.add(guide_id) cancel_scope(f"{guide_id}-") # waiting agents bail before spawn kill_process(guide_id) # kill running subprocesses now = datetime.now(timezone.utc).isoformat() await update_guide(guide_id, status="error", progress=None, error_msg="Cancelled — progress is preserved", updated_at=now) return True def is_guide_cancelled(guide_id: str) -> bool: return guide_id in _cancelled def clear_guide_cancelled(guide_id: str) -> None: _cancelled.discard(guide_id) clear_scope(f"{guide_id}-") # clear scope → restart not blocked async def _set_progress(guide_id: str, progress: str) -> None: now = datetime.now(timezone.utc).isoformat() await update_guide(guide_id, progress=progress, updated_at=now) async def _set_step(guide_id: str, step: int, progress: str) -> None: now = datetime.now(timezone.utc).isoformat() await update_guide(guide_id, step=step, progress=progress, updated_at=now) async def _fail(guide_id: str, msg: str) -> None: now = datetime.now(timezone.utc).isoformat() await update_guide(guide_id, status="error", progress=None, error_msg=msg, updated_at=now) def _prompt(name: str, **kwargs) -> str: template = (TEMPLATES_DIR / "Prompt" / f"{name}.md").read_text(encoding="utf-8") return template.format(**kwargs) def _extra(instructions: str) -> str: return f"\n\nADDITIONAL INSTRUCTIONS FROM THE USER:\n{instructions}\n" if instructions else "" def _log(topic: str, msg: str) -> None: log.info("[%s] %s", topic, msg) def _claude_error(label: str, returncode: int, stdout: str, stderr: str) -> str: stderr = (stderr or "").strip() if stderr: return f"{label}: {stderr[:1000]}" tail = (stdout or "").strip()[-500:] if tail: return f"{label} (exit {returncode}, stderr empty): …{tail}" return f"{label} (exit {returncode}, no output)" _INFRA_MARKERS = ("HTTP 429", "HTTP 5", "rate_limit", "Timeout after", "ConnectError", "ConnectTimeout", "ReadError", "RemoteProtocolError") def _is_infra(err: str) -> bool: """Transport-/Infra-Fehler (retry + pause) statt inhaltlichem Fehlschlag.""" return any(m in (err or "") for m in _INFRA_MARKERS) def _gather_error(label: str, results: list) -> str: for r in results: if isinstance(r, BaseException): return f"{label}: {type(r).__name__}: {r}" returncode, stdout, stderr = r if returncode != 0: return _claude_error(label, returncode, stdout, stderr) return f"{label}: no usable result" def _timeout(step: str, n: int = 0) -> int: base, per = TIMEOUTS[step] return base + per * n def _problems_schema(data): """{"ok": true} → [] · {"problems": [str]} → list · else None.""" if not isinstance(data, dict): return None if data.get("ok") is True: return [] p = data.get("problems") if not isinstance(p, list) or not p: return None out = [str(x).strip() for x in p if str(x).strip()] return out or None def _str_list(val) -> list[str] | None: """List of non-empty strings → stripped list (empty allowed) · else None.""" if not isinstance(val, list) or not all(isinstance(x, str) for x in val): return None out = [x.strip() for x in val] return None if any(not x for x in out) else out def _runde_schema(data, final: bool = False): """{"keep": [str], "rest": [str]} → (include, rest) · else None. final=True: last clarification round — a non-empty rest is invalid. """ if not isinstance(data, dict): return None include = _str_list(data.get("keep")) rest = _str_list(data.get("rest")) if include is None or rest is None or (final and rest): return None return include, rest _YESNO = ("ja", "nein") def _enum_map_schema(key: str, allowed): """Factory for `{"": {"1": value, …}}` → `{id: value}` parsers; value ∈ `allowed` (casefolded). If `ids` are given, at least these must be covered (extras allowed). None on any invalid id/value or wrong shape. The caller filters the result to `ids`.""" def parse(data, ids: set[int] | None = None): if not isinstance(data, dict) or not isinstance(data.get(key), dict) or not data[key]: return None out: dict[int, str] = {} for k, v in data[key].items(): try: num = int(k) except (ValueError, TypeError): return None value = str(v).strip().casefold() if value not in allowed: return None out[num] = value if ids is not None and not ids <= set(out): return None return out return parse _yesno_schema = _enum_map_schema("relevant", _YESNO) # triage gate ∈ ja/nein from config import (MAX_RESTARTS as _MAX_RESTARTS, HEDGE_NACH_S as _HEDGE_NACH_S, # noqa: E402 — zentral tunebar INFRA_MAX_RETRIES as _INFRA_MAX_RETRIES, INFRA_BACKOFF_BASE as _INFRA_BACKOFF) async def _race(topic: str, label: str, slots: list[dict], quorum: int, timeout: int, provider: str, cancelled=None, *, grace: int | None = None) -> list | None: """Starts all slots in parallel and collects `quorum` valid results. Slot spec: {key, prompt, role, capabilities, payload}. `payload(result)` checks validity and returns the slot result or None. Error/timeout/invalid → slot restart (max. _MAX_RESTARTS). As soon as the quorum stands, the remaining agents are killed. None = quorum missed. `cancelled()` → True aborts (no restarts, returns None). With `grace`, `quorum` becomes the minimum: the first valid result starts a timer of `grace` seconds. After it expires, running agents are only killed if the minimum stands — otherwise the race, including restarts, keeps running until it stands. Returns: `quorum` to `len(slots)` results. """ attempts = {i: 0 for i in range(len(slots))} infra_attempts = {i: 0 for i in range(len(slots))} infra_erschoepft: set[int] = set() tasks: dict[asyncio.Task, int] = {} keys: dict[asyncio.Task, str] = {} born: dict[asyncio.Task, float] = {} hedged: set[int] = set() # slot got its one twin — no hedge cascades fertig: set[int] = set() # slot delivered a valid result (late twins are ignored) # Hedge-Schwelle relativ zum Call-Timeout (HEDGE_NACH_S = Untergrenze): pauschale 90 s # hedgten jeden gesunden langen Call — z. B. Guide-Fixes, die normal 110–135 s laufen. hedge_s = max(_HEDGE_NACH_S, timeout / 2) if _HEDGE_NACH_S else 0 loop = asyncio.get_running_loop() deadline: float | None = None def spawn(i: int, suffix: str = "") -> None: slot = slots[i] lbl = slot.get("label") or (label if len(slots) == 1 else f"{label} {i + 1}") key = slot["key"] + suffix task = asyncio.create_task(run_agent( key, slot["prompt"], timeout, provider=provider, role=slot["role"], capabilities=slot["capabilities"], scope=topic, on_line=slot.get("on_line"), label=lbl, )) tasks[task] = i keys[task] = key born[task] = loop.time() for i in range(len(slots)): spawn(i) results: list = [] try: while tasks: if cancelled and cancelled(): return None if deadline is not None and len(results) >= quorum and loop.time() >= deadline: return results # Hedge: a slot running HEDGE_NACH_S without result gets ONE parallel twin # (key -h) — first valid result wins. Stalled provider calls burned the full # timeout cap before the restart even began (measured: 160–230 s per stall). if hedge_s: now = loop.time() for t in [t for t in list(tasks) if tasks[t] not in hedged | fertig and now - born[t] >= hedge_s]: i = tasks[t] hedged.add(i) spawn(i, suffix="-h") _log(topic, f"{label} {i + 1}: {round(hedge_s)}s ohne Ergebnis — Hedge-Zwilling gestartet") # Wake up for the earliest relevant deadline (grace or next hedge). waits = [] if deadline is not None and len(results) >= quorum: waits.append(deadline - loop.time()) if hedge_s: naechste = [born[t] + hedge_s - loop.time() for t in tasks if tasks[t] not in hedged | fertig] if naechste: waits.append(max(0.0, min(naechste))) wait_timeout = max(0.0, min(waits)) if waits else None done, _ = await asyncio.wait(tasks.keys(), return_when=asyncio.FIRST_COMPLETED, timeout=wait_timeout) if not done: continue for task in done: i = tasks.pop(task) keys.pop(task, None) born.pop(task, None) if i in fertig: continue # späte Zwillinge eines bereits gewerteten Slots payload, err = None, None try: result = task.result() if result[0] != 0: err = _claude_error("Error", *result) else: payload = slots[i]["payload"](result) if payload is None: err = "result invalid/not parseable" except asyncio.TimeoutError: err = f"Timeout after {timeout}s" except Exception as e: err = f"{type(e).__name__}: {e}" if payload is not None: results.append(payload) fertig.add(i) for t2 in [t2 for t2, i2 in tasks.items() if i2 == i]: # Zwilling killen kill_process(keys.get(t2, slots[i]["key"])) t2.cancel() if grace is not None and deadline is None: deadline = loop.time() + grace _log(topic, f"{label}: first result — grace {grace}s running") if len(results) >= quorum and (grace is None or loop.time() >= deadline): return results continue infra = _is_infra(err) _log(topic, f"{label} {i + 1} (attempt {attempts[i] + 1}{' infra' if infra else ''}): {err}") attempts[i] += 1 # If the minimum already stands, restarts are pointless — the restart # would be killed at the grace end anyway. A still-running twin IS the retry. enough = grace is not None and len(results) >= quorum zwilling = any(i2 == i for i2 in tasks.values()) if enough or zwilling or (cancelled and cancelled()): continue if infra: # 429/Timeout/Netz: eigener Zähler + wachsende Pause, dann Eskalation infra_attempts[i] += 1 if infra_attempts[i] > _INFRA_MAX_RETRIES: infra_erschoepft.add(i) # kein Respawn → raise am Quorum-Miss continue await asyncio.sleep(_INFRA_BACKOFF * 2 ** (infra_attempts[i] - 1)) spawn(i) elif attempts[i] <= _MAX_RESTARTS: spawn(i) if len(results) >= quorum: # all slots done, minimum stands (only reachable with grace) return results _log(topic, f"{label}: quorum {quorum} not reached ({len(results)} valid)") if infra_erschoepft: raise AgentInfraError( f"{label}: {len(infra_erschoepft)} Slot(s) nach {_INFRA_MAX_RETRIES} " "Infra-Retries erschöpft (429/Timeout)") return None finally: for task, i in tasks.items(): kill_process(keys.get(task, slots[i]["key"])) task.cancel() if tasks: await asyncio.gather(*tasks.keys(), return_exceptions=True) @dataclass class GenContext: """Pipeline parameters passed through — saves long argument signatures.""" topic: str provider: str is_cancelled: Callable[[], bool] guide_id: str | None = None # Result status of run_single_slot OK, CANCELLED, FAILED = "ok", "cancelled", "failed" class AgentInfraError(Exception): """Slot nach Infra-Retries erschöpft (429/Timeout). KEIN inhaltliches Urteil — der Aufrufer pausiert den Lauf, nie fail-open.""" async def run_single_slot( ctx: GenContext, label: str, *, key: str, prompt: str, role: str, capabilities: str, payload, timeout: int, on_line=None, ) -> tuple[str, object]: """One agent, one valid result (race with quorum 1). → (OK, value) | (CANCELLED, None) | (FAILED, None) """ slots = [{"key": key, "prompt": prompt, "role": role, "capabilities": capabilities, "payload": payload, "on_line": on_line}] res = await _race(ctx.topic, label, slots, 1, timeout, ctx.provider, cancelled=ctx.is_cancelled) if ctx.is_cancelled(): return CANCELLED, None if res is None: return FAILED, None return OK, res[0] async def _gather_progress(coros, total, report, start=0): """Runs `coros` concurrently and reports live progress: `await report(done, total)` after each completion (and once initially). Results in order, return_exceptions=True.""" done = start async def wrap(c): nonlocal done try: return await c finally: done += 1 await report(done, total) await report(done, total) return await asyncio.gather(*[wrap(c) for c in coros], return_exceptions=True)