refactor(retrieval): the completion-report preferences run through the pipeline (milestone 456 step 3, #4905)
CI & Build / Python lint (push) Successful in 2s
CI & Build / Plugin hooks (push) Successful in 13s
CI & Build / TypeScript typecheck (push) Successful in 53s
CI & Build / integration (push) Successful in 53s
CI & Build / Python tests (push) Successful in 1m45s
CI & Build / Build & push image (push) Successful in 28s

reply_preferences.completion_preferences was the last hand-written
rule search + record_retrieval + record_rule_surfaced triple outside the
pipeline. It is now REPORT_PREFERENCE, a RuleArm with kind="preference"
over COMPLETION_QUERY, read back as records rather than as lines.

- RuleArm gains `kind`. _ranked asks the ranker for that kind and drops
  anything else on the way out, before the row is logged.
- RuleResult gains `shown`, the (score, rule) pairs behind the lines, for
  callers that return records.
- RuleMoment.project_id may be None: logged as given, searched as
  `project_id or None`. report_preference rows keep their NULL project.
- Guards: reply_preferences now has 0 direct rule searches. The registry
  constant-source example moves from report_preference to preference_slot,
  the pipeline slot that records through a module constant.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-05 08:38:05 -04:00
co-authored by Claude Opus 5.5
parent b72c9a92e2
commit 0720ab6dcf
5 changed files with 61 additions and 35 deletions
+31 -4
View File
@@ -351,6 +351,9 @@ class RuleArm:
preference_slot: bool
"""Reserve one line for a preference that lost the ranking (#3894)."""
kind: str | None = None
"""Ask the ranker for one record kind only ("preference"), or every kind."""
# Today's differences, reproduced exactly (milestone 456 step 2). Whether the
# prompt arm should band, and whether the act arms should reserve a
@@ -367,7 +370,16 @@ WRITE_PATH_RULE = RuleArm(
"write_path_rule", band=True, compact_tail=True, checkpoint=True,
preference_slot=False,
)
RULE_ARMS: tuple[RuleArm, ...] = (WRITE_PATH_RULE, PRE_TOOL_RULE, PROMPT_RULE)
# The completion report's preferences (milestone 409 step 4): a FIXED query,
# preferences only, read by update_task as records rather than as lines. Its
# query is `reply_preferences.COMPLETION_QUERY`.
REPORT_PREFERENCE = RuleArm(
"report_preference", band=False, compact_tail=False, checkpoint=False,
preference_slot=False, kind="preference",
)
RULE_ARMS: tuple[RuleArm, ...] = (
WRITE_PATH_RULE, PRE_TOOL_RULE, PROMPT_RULE, REPORT_PREFERENCE,
)
PREFERENCE_SLOT_SOURCE = "preference_slot"
@@ -396,8 +408,11 @@ class RuleMoment:
user_id: int
query: str
project_id: int
where: str
project_id: int | None
"""The bound project, 0 or None when unbound. Logged as given, searched as
`project_id or None` — global rules plus that project's own (milestone 414)."""
where: str = ""
"""How a line names the moment: "here", "to this Bash call", …"""
checkpoint_where: str = ""
@@ -419,6 +434,10 @@ class RuleResult:
shown_rule_ids: list[int] = field(default_factory=list)
"""Every rule LINE, repeats and the reserved slot included."""
shown: list = field(default_factory=list)
"""The (score, rule) pairs behind those lines, best first — for a caller
that hands back records rather than lines (the completion report)."""
checkpoint: dict = field(default_factory=dict)
@@ -462,6 +481,13 @@ async def _ranked(
# slot on it, indistinguishable from a line that earned its place.
kwargs["kind"] = kind
hits = await io.search(moment.user_id, moment.query, **kwargs)
if kind:
# And checked on the way out: a record of another kind that slipped
# through must not be logged, shown or counted under a source whose
# name claims the kind — a rule handed back as "how the operator likes
# this done" asserts a force the record does not have.
hits = [(score, rule) for score, rule in hits
if getattr(rule, "kind", None) == kind]
kept = _rule_band(hits) if band else hits
fresh = [(score, rule) for score, rule in kept if rule.id not in moment.exclude]
try:
@@ -578,7 +604,7 @@ async def run_rule_arm(
try:
_hits, kept, fresh = await _ranked(
io, moment, source=arm.source, floor=floor, limit=budget,
band=arm.band,
band=arm.band, kind=arm.kind,
)
shown = kept
if arm.preference_slot:
@@ -631,6 +657,7 @@ async def run_rule_arm(
lines=lines, rule_ids=rule_ids,
shown_rule_ids=[rule.id for _score, rule in shown],
checkpoint=checkpoint,
shown=list(shown),
)
except Exception: # noqa: BLE001 - a recall aid never breaks its act
logger.debug("%s arm failed", arm.source, exc_info=True)