Files
ratatoskr/docs/diagnostics/lexical_recall_gate.py
vh 17ae1558f9 docs(diagnostics): add lexical-recall gate — class acceptance instrument for exact-term recall
Generalizes the crown repro (Worldtree #400 / thread 01KZETD98T) beyond its anchor
into a before/after regression instrument for the class property: when the corpus
holds a chunk whose text literally carries a queried surface form, a natural query
should serve >=1 such chunk at a usable rank.

  - Anchors tagged stress (common word + competing dense cluster, e.g. crown) vs
    control (distinctive name — should sit ~0% miss).
  - Binary per trial: does a natural query serve >=1 term-containing chunk within
    top-10 (USABLE_K)? Ranks >=8 flagged KNIFE-EDGE (the RRF fused-rank 9-11 window
    residual worldtree-dev's decomposition measured).
  - Real-world end-to-end: drives the agent (it composes its own reference_knowledge
    query, as in production); --runs samples query-formulation variance to estimate a
    true miss-rate.
  - Extensible anchor list; --anchor filters.

This is the deciding instrument for the rerank_hybrid_floor lever: its stress-class
miss-rate (alongside brokkr's fleet demotion rate) rules the floor in or out after
the BM25 stemming fold deploys. Pre-fold baseline captured today (the "before"):
control 0% miss / stress[crown] 100% miss / 0% knife-edge, 11 trials.

Diagnostics fixture, no production runtime — no version bump. persistent-memory
snapshot committed alongside (commit-along).
2026-08-07 19:07:05 -07:00

146 lines
6.7 KiB
Python

"""Lexical-recall gate — the class acceptance instrument for exact-term recall survival.
Generalizes the crown repro (Worldtree #400 / thread 01KZETD98T) beyond its anchor. The
class property under test: when the corpus contains a chunk whose text literally carries a
queried surface form, a natural query for that entity should serve >= 1 such chunk at a
USABLE rank (inside the top-K window). The crown ("Crown of the Sepsis Whore") is the
motivating STRESS case — a common word with a dense-similar vanity cluster that buries the
exact-lexical match; distinctive names (Krakaren, Vine Creeper) are CONTROLs that should
always pass. The gap lives on the stress class, not the controls.
This is a before/after regression instrument, NOT a fix: run it pre-deploy and post-deploy
(the BM25 stemming fold, then any rerank_hybrid_floor lever) to measure whether the served
miss-rate on the stress class actually moves. Real-world by design — it drives the agent
end-to-end (the agent composes its own reference_knowledge query, as in production), and
--runs samples that query-formulation variance to estimate a true miss-rate.
Self-contained (httpx only). Config from env (source env.sh first):
WORLDTREE_API_URL (default personal :8081), WORLDTREE_API_KEY (required),
RATATOSKR_END_USER_ID (default ratatoskr-tui), RATATOSKR_TTS_AGENT unused here.
uv run --with httpx python docs/diagnostics/lexical_recall_gate.py
uv run --with httpx python docs/diagnostics/lexical_recall_gate.py --runs 5
uv run --with httpx python docs/diagnostics/lexical_recall_gate.py --anchor crown
"""
from __future__ import annotations
import argparse
import json
import os
import re
import httpx
# Served window: a hit past this rank is not "usable" (Worldtree serves ~top-10; a row at
# rank 9-11 is the RRF knife-edge worldtree-dev identified — treated as a KNIFE-EDGE pass).
USABLE_K = 10
KNIFE_EDGE_FROM = 8 # ranks >= this inside the window are fragile (one-rank-edge residual class)
AGENT = "ratatoskr:donut"
# (label, kind, term-regex the served chunk's excerpt must contain, [natural user messages]).
# kind: "stress" = common word + competing dense cluster; "control" = distinctive name.
# Controls should pass every run; the class limitation shows as stress-class misses / knife-edges.
ANCHORS = [
("crown", "stress", r"\bcrown",
["What crown do you own?", "Do you have a crown?", "Tell me about your crown."]),
("vine-creeper", "control", r"vine creeper",
["Tell me about the Vine Creeper.", "What is the Vine Creeper?"]),
("danger-dingo", "control", r"danger dingo|\bdingo",
["What is the Danger Dingo?", "Describe the Danger Dingo."]),
("pedicure-kit", "control", r"pedicure",
["What does the Pedicure Kit do?", "Tell me about the Pedicure Kit."]),
("neighborhood-map", "control", r"neighborhood map",
["What is the Neighborhood Map?", "Describe the Neighborhood Map."]),
]
def _cfg() -> tuple[str, dict, str]:
base = os.environ.get("WORLDTREE_API_URL", "http://10.250.50.152:8081")
key = os.environ.get("WORLDTREE_API_KEY")
if not key:
raise SystemExit("WORLDTREE_API_KEY unset — source env.sh first.")
return base, {"Authorization": f"Bearer {key}"}, os.environ.get("RATATOSKR_END_USER_ID", "ratatoskr-tui")
def _session(base: str, headers: dict, end_user: str) -> str:
r = httpx.post(f"{base}/sessions", json={"agent_id": AGENT, "end_user_id": end_user},
headers=headers, timeout=30)
r.raise_for_status()
return r.json()["session_id"]
def _drive(base: str, headers: dict, sid: str, content: str) -> tuple[str | None, list]:
"""POST a turn; return (actual reference_knowledge query, served hits list)."""
q, hits = None, []
with httpx.stream("POST", f"{base}/sessions/{sid}/messages", json={"content": content},
headers=headers, timeout=180) as r:
for line in r.iter_lines():
if not line.startswith("data: "):
continue
ev = json.loads(line[6:])
t = ev.get("type")
if t == "tool_start" and q is None:
q = (ev.get("arguments") or {}).get("query")
elif t == "tool_result" and not hits:
res = ev.get("result")
if isinstance(res, dict):
hits = res.get("hits", res.get("results", [])) or []
elif t == "done":
break
return q, hits
def _served_rank(hits: list, term_re: str) -> int | None:
"""Rank of the first served hit whose excerpt literally contains the term (None = miss)."""
for i, h in enumerate(hits[:USABLE_K]):
if isinstance(h, dict) and re.search(term_re, h.get("excerpt", ""), re.I):
return i
return None
def main() -> None:
ap = argparse.ArgumentParser()
ap.add_argument("--runs", type=int, default=1, help="repeats per message (samples query variance)")
ap.add_argument("--anchor", default=None, help="run only this anchor label")
args = ap.parse_args()
base, headers, end_user = _cfg()
anchors = [a for a in ANCHORS if args.anchor is None or a[0] == args.anchor]
totals = {"trials": 0, "miss": 0, "knife": 0}
by_kind: dict[str, dict] = {}
for label, kind, term_re, messages in anchors:
print(f"\n[{label}] ({kind}) term=/{term_re}/")
agg = by_kind.setdefault(kind, {"trials": 0, "miss": 0, "knife": 0})
for msg in messages:
for _ in range(args.runs):
sid = _session(base, headers, end_user) # fresh session per trial
q, hits = _drive(base, headers, sid, msg)
rank = _served_rank(hits, term_re)
miss = rank is None
knife = rank is not None and rank >= KNIFE_EDGE_FROM
for d in (totals, agg):
d["trials"] += 1
d["miss"] += int(miss)
d["knife"] += int(knife)
tag = "MISS" if miss else (f"knife@{rank}" if knife else f"ok@{rank}")
print(f" {tag:9} msg={msg!r:42} q={q!r}")
def pct(n: int, d: int) -> str:
return f"{(100*n/d):.0f}%" if d else "n/a"
print("\n=== SUMMARY ===")
for kind, d in sorted(by_kind.items()):
print(f" {kind:8} trials={d['trials']:3} miss={pct(d['miss'], d['trials'])} "
f"knife-edge={pct(d['knife'], d['trials'])}")
t = totals
print(f" {'ALL':8} trials={t['trials']:3} miss={pct(t['miss'], t['trials'])} "
f"knife-edge={pct(t['knife'], t['trials'])}")
print("\nGate: stress-class miss-rate is the deciding signal for the rerank_hybrid_floor lever.")
print("Controls should sit at ~0% miss; a stress miss/knife-edge is the residual class to weigh.")
if __name__ == "__main__":
main()