Jonathan KirkwoodandClaude Fable 5
1dde915540
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
89 lines
3.7 KiB
Python
89 lines
3.7 KiB
Python
"""Local lead-reviewer synthesis — no frontier model.
|
|
|
|
After the panel finishes, one more hardened container (the "lead reviewer") reads
|
|
all the individual reports (mounted read-only at /reports) plus the documents
|
|
(/docs), runs a configured local model, and writes a single consolidated report
|
|
to /out/CONSOLIDATED_REPORT.md: shared themes, where reviewers disagree, the
|
|
consensus, and an overall recommendation.
|
|
|
|
It reuses the same one-shot reviewer image, switched to BM_ROLE=synthesizer.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import shlex
|
|
|
|
import spark_client as sc
|
|
import serving
|
|
|
|
DEFAULT_LEAD_PERSONA = (
|
|
"You are the lead reviewer chairing the panel. You did not read the documents "
|
|
"first-hand for a fresh opinion — your job is to CONSOLIDATE the panel's "
|
|
"individual reports into one authoritative report. Identify the findings the "
|
|
"reviewers agree on, surface and adjudicate where they conflict, note anything "
|
|
"only one reviewer caught, and end with a prioritized recommendation. Attribute "
|
|
"points to the reviewer(s) who raised them. Do not invent findings."
|
|
)
|
|
|
|
|
|
def pick_model(cfg: dict) -> str:
|
|
alias = (cfg.get("synthesisModel") or "").strip()
|
|
if alias:
|
|
return alias
|
|
models = cfg.get("models") or []
|
|
return models[0]["alias"] if models else ""
|
|
|
|
|
|
def run_synthesis(cfg: dict, jobdir: str, rubric: str, log, wait_timeout: int = 1800) -> dict:
|
|
"""Launch the lead-reviewer container and wait for the consolidated report."""
|
|
head = sc.head(cfg)
|
|
q = shlex.quote
|
|
model = pick_model(cfg)
|
|
if not model:
|
|
raise RuntimeError("no model available for synthesis (configure a model catalog)")
|
|
|
|
persona = (cfg.get("synthesisPersona") or "").strip() or DEFAULT_LEAD_PERSONA
|
|
net = serving.net_name(cfg)
|
|
base = serving.reviewer_proxy_base(cfg)
|
|
rid = "lead-reviewer"
|
|
|
|
sc.run(head,
|
|
f"mkdir -p {q(jobdir)}/personas {q(jobdir)}/synth-out && "
|
|
f"printf '%s' {q(persona)} > {q(jobdir)}/personas/{rid}.md && "
|
|
f"printf '%s' {q(rubric)} > {q(jobdir)}/RUBRIC.md",
|
|
timeout=30)
|
|
|
|
env = (
|
|
f"-e BM_REVIEWER_ID={q(rid)} -e BM_REVIEWER_NAME=lead-reviewer -e BM_ROLE=synthesizer "
|
|
f"-e BM_MODEL={q(model)} -e BM_LLM_BASE={q(base)} -e BM_LLM_KEY=sk-local "
|
|
f"-e BM_MAX_MODEL_LEN={q(str(int(cfg.get('maxModelLen', 32768))))} -e HOME=/home/rev "
|
|
)
|
|
harden = (
|
|
"--user 1000:1000 --security-opt no-new-privileges --cap-drop ALL "
|
|
"--read-only --tmpfs /tmp:size=256m --tmpfs /home/rev:size=128m "
|
|
"--pids-limit 256 --memory 6g --cpus 4"
|
|
)
|
|
mounts = (
|
|
f"-v {q(jobdir)}/docs:/docs:ro "
|
|
f"-v {q(jobdir)}/out:/reports:ro "
|
|
f"-v {q(jobdir)}/synth-out:/out "
|
|
f"-v {q(jobdir)}/personas/{rid}.md:/persona/PERSONA.md:ro "
|
|
f"-v {q(jobdir)}/RUBRIC.md:/RUBRIC.md:ro "
|
|
)
|
|
cname = f"bm-grader-{rid}"
|
|
cmd = (
|
|
f"docker rm -f {cname} >/dev/null 2>&1; "
|
|
f"docker run -d --name {cname} --network {q(net)} {harden} {env} {mounts} {q(cfg['graderImage'])}"
|
|
)
|
|
log(f"[synthesis] lead reviewer up -> {model}")
|
|
r = sc.run(head, cmd, timeout=120)
|
|
if r.returncode != 0:
|
|
raise RuntimeError(f"synthesis launch failed: {r.stderr or r.stdout}")
|
|
|
|
w = sc.run(head, f"docker wait {cname}", timeout=wait_timeout)
|
|
code = (w.stdout or "").strip()
|
|
chk = sc.run(head, f"test -s {q(jobdir)}/synth-out/CONSOLIDATED_REPORT.md && echo OK || echo MISSING", timeout=30)
|
|
wrote = "OK" in (chk.stdout or "")
|
|
sc.run(head, f"docker rm -f {cname} 2>/dev/null; true", timeout=30)
|
|
log(f"[synthesis] lead reviewer exited (code={code or '?'}), report={'written' if wrote else 'MISSING'}")
|
|
return {"model": model, "exit": code, "report": wrote}
|