proof: knowledge-layer validation programme (stacked on #18) - #19

…ange

- proposal.md: the request_scope() call-site list has eight entries; the
  source plan mislabels it "seven" (design.md and tasks.md already said
  eight).
- design.md: B3 must test whether the reference allocator's table-wide
  MAX(logical_time) already satisfies two-copy matrix item 4 before adding
  an explicit advance-on-import step.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

…and diagnostics

Lift SessionWeaver's frozen tier-1 ontology extraction/rebuild/status
module (extraction version tier1-v2-canonical-messages, same
logical-hash algorithm, so A2's baseline stays comparable). Migration
v48 installs the six schema objects additively; install_schema is
tolerant of a pre-existing ad hoc ontology schema (found on the real
sessions.db) so a real upgrade converges instead of crashing -- the
first rebuild replaces it regardless of its prior shape.

Wire an incremental ontology refresh into
export_sessions._run_export, behind a named, monkeypatchable seam
(refresh_ontology_after_export) called after the capture commit: a
refresh failure is caught, logged as a structured
ontology_refresh_failed warning, surfaced in the export summary, and
never rolls back captured sessions (EXECUTION-ERRATA.md #7). Add
`session-maint ontology-rebuild [--incremental]` and `ontology-status`
for manual/maintenance recovery.

Add the sync boundary: ontology tables never join SYNC_TABLES or
GLOBAL_SYNC_TABLES (positive-control tested), and
sync._seed_remote_db strips every ontology row from a seed snapshot
before scp so a freshly seeded remote derives its own ontology rather
than inheriting the source's.

Add a report-only "harness" doctor check (present/coverage/freshness/
extraction-version), never fatal, with a fixture-inserted red-path
test.

Add the ontology_live safety harness (Online Backup only, real DB
never touched, new opt-in live_ontology pytest marker) and R7
migration-safety tests: fresh creation, interrupted-migration
recovery, downgrade, and idempotent re-migration. Retains real
acceptance receipts (docs/data/) from a live Online Backup run:
coverage 100%, zero integrity violations, identical hash across two
full rebuilds and one incremental no-op, cold rebuild 3.47s.

Fixes a v47-pinned assertion in test_replica_coordinator.py that this
version bump would otherwise break, and regenerates .secrets.baseline
(detect-secrets 1.5.0) for the two evidence files' SHA-256 hashes.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

…ed scope

A virgin install crashed or leaked ad-hoc errors the moment any scope-dependent
path ran: `studyloop study` propagated a bare ScopeError as a generic exit-1
ClickException, each of the seven unguarded request_scope() MCP tool sites let
FastMCP wrap it in ad-hoc text, and session-db-mcp's open_context()/
_get_connection() let sqlite3's "unable to open database file" leak through a
distinct, unhelpful error shape on a database that simply doesn't exist yet.

Add ScopeUnconfiguredError (a ScopeError subclass identifying exactly the
"nothing configured" case) and scope_setup_diagnostic(), one shared
{code: "scope_unconfigured", message, remediation} shape. Every entry point
that can hit it now reports that same payload instead of a traceback: the
CLI exits 2, both MCP servers' tool-call boundaries return isError with the
JSON payload embedded in the text content, and a missing database is treated
identically to a missing scope rather than as its own error class.

Both packages' config writers (generate_default_config(), ensure_config_dir())
now write memory.default_scope: unclassified explicitly for a brand-new
config.yaml, so a fresh install is immediately usable. The runtime default for
an absent file or a file that omits the key stays unset (errata #9) -- this
changes only what a *generated* file contains, not what an absent setting means.

Tests: packages/studyloop/tests/test_fresh_install_scope.py drives a virgin
HOME (no STUDYLOOP_CONFIG, no SESSION_CONTEXT_SCOPE) as a real subprocess
against the source tree -- the CLI, all seven MCP tool sites, and
session-db-mcp's session_search/memory_search -- so this suite's own
config-isolation fixtures cannot hide the defect the way the existing fixture
already did. test_fresh_install_scope_installed.py (marked integration)
repeats every check against a real `uv build` wheel install per plan ruling
R10. Unit tests cover scope_setup_diagnostic, ScopeUnconfiguredError, the two
config writers' round trip, and open_context()/_get_connection() on a missing
database.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

Add a "Tier-1 ontology (derived, never synced)" section to
docs/session-memory.md covering what it captures, why it never syncs,
the automatic export-time refresh, and session-maint
ontology-rebuild/ontology-status for manual recovery. Record the
feature under CHANGELOG.md's [Unreleased] Added.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

Mark tasks.md's B2 tasks 2.1 (migration v48 + lift), 2.2 (refresh
hook + session-maint ontology-rebuild), and 2.3 (sync boundary +
seed sanitization) complete. Leave 2.4 unchecked with an inline note:
its tests/hash/timing/count verification and a green preflight are
done, but code/build-ontology.py's retirement is explicitly B6's
(task-B2-brief.md) and the independent review is the reviewer's step.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

Task B1 of openspec/changes/sessionweaver-phase2-retrofit: generated config
writes memory.default_scope: unclassified; one structured ScopeError
diagnostic at the CLI and every MCP tool in both servers; missing-database
path covered; virgin-HOME tests on source-tree and installed-package paths.
Review: .superpowers/sdd/sessionweaver-phase2/task-B1-review.md (0 findings).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

…d agents

CI run 34167164262 (jobs test (3.12) and test (3.13)) failed
test_fresh_install_scope.py::test_studyloop_study_exits_2_with_the_diagnostic_on_a_virgin_home
because on the GitHub runner `studyloop study 'Test Topic'` exits 1 with
"No AI agent found. Install one of: Kiro CLI, Codex, Claude Code,
OpenCode, or pi" before the scope check ever runs. session/start.py calls
detect_agents() (studyloop.agent_launcher) before start_study_session()
raises ScopeUnconfiguredError, so the expected exit 2 + structured scope
diagnostic is unreachable unless some agent binary is resolvable via
shutil.which on the subprocess's PATH. Locally the test only passed
because this machine has agent CLIs installed.

Fix the test, not production code: add a `_fake_agent_bin()` helper that
writes a no-op executable named `claude` (matching
studyloop.adapters.claude.ADAPTER.binary) into a throwaway bin dir and
prepends it to the subprocess PATH via `_usable_path()`/`_virgin_env()`'s
new `agent_bin` parameter. detect_agents() only calls shutil.which(), so
the script is never actually executed -- start_study_session() still
raises ScopeUnconfiguredError immediately after agent selection, well
before any launch command is built. Applied to both
test_studyloop_study_exits_2_with_the_diagnostic_on_a_virgin_home and its
installed-wheel sibling in test_fresh_install_scope_installed.py, which
had the same dependency.

Reproduced RED locally by running both files with a PATH stripped of
every real agent CLI (venv bin + tmux + /usr/bin:/bin only), then
confirmed GREEN with that same stripped PATH after the fix.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

Replace permission-bit failure injection with the backup helper's real None failure contract. This keeps the abort-before-stream invariant reliable under both ordinary users and root CI containers.

Preserve direct coverage that a nonzero SSH/sqlite command result is translated into None after the push-contract test moved to the orchestration seam.

Bring the independently reviewed migration v48, deterministic ontology evidence, and CI-parity sync test correction into the SessionWeaver Phase 2 integration branch.

# Conflicts:
#	.secrets.baseline
#	docs/session-memory.md

Lift SessionWeaver's concept_schema.py unchanged (SCHEMA_VERSION = 2,
SCHEMA_FINGERPRINT byte-identical to the reference,
af95685e6e39e166148006519862bee3be1a15219d76772236a82890fe11011d) and
add migrate_v49, which installs exactly that DDL: context_concepts,
context_concept_events, context_concept_clock, context_concept_fts and
context_concept_schema, plus their indexes/triggers and the two
context_citations guard triggers. UPSTREAM_SCHEMA_VERSION is pinned to
49, the migration number that installs the sidecar.

Why: tasks.md 3.1 -- B3 owns v49 (v48 stays B2's); the sidecar must be
additive-only, with context_assertions.proposed_state left as execution
state (errata #3), and adopt a byte-identical pre-existing PoC sidecar
while refusing drift, because sidecar rows are authored data.

Migration-safety per B2's R7 pattern: fresh create to v49, additive-only
shape check on context_assertions, exact-adopt, drift refusal,
interrupted-migration recovery, repeated-open idempotence, downgrade
contract, and a real Online Backup v47->v49 upgrade retained as
docs/data/concept-sidecar-migration-v49-receipt.json (aggregates only;
source sentinels asserted unchanged; live DB still v47, 5813 sessions).
The detect-secrets baseline is regenerated for the receipt's hex-hash
false positives, matching B2's precedent.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

…ection

Lift SessionWeaver v0.2.0's concepts.py, winddown.py, okf.py (as
okf_import.py), projection.py (A3b2's fixed Publisher with its
identity-guarded rollback), authorization.py and safe_fs.py into
agent_session_tools.context, adapting only import paths to the package
(relative imports; okf -> okf_import). All frozen contracts are kept
byte-identical: the sessionweaver://session/ source-URI prefix, the
session_weaver_projection frontmatter key, the projection marker and
manifest filenames, and ConceptService's public surface (project,
winddown, transition, bind_legacy, import_okf).

Why: tasks.md 3.1 -- B4 consumes ConceptService as a caller, never a
second implementation, and B6 deletes the SessionWeaver copies, so the
lifted behaviour must be the reference behaviour, provable by the
reference's own tests.

Tests: the reference suites lifted with the same import rewrites
(223 tests: schema exactness/adoption, wind-down parsing, lifecycle
transitions, bind closure, OKF scan/classification precedence,
projection publish/rollback, adversarial SQL integrity). Two
adaptations, both consequences of v49 installing the sidecar up front:
the upstream-version pin asserts 49, and a rejected import call now
asserts zero sidecar rows instead of no sidecar table. One targeted
nosec B506 documents that _StrictSafeLoader narrows yaml.SafeLoader.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

Concept roots and their complete append-only event history join the
context replication protocol: snapshot selection follows the
authorization seam's two visibility shapes (bound roots travel with
their assertion's citation closure, legacy roots with their claimed
session), the apply path inserts only rows it does not already have,
and the receiving side's own schema triggers re-validate every root.
The local clock, the FTS read model and the schema marker never travel.

Standing is exactly the frozen order (design.md, ruling R2):
standing = max(events, key=(lamport, machine_id, event_id)) with
machine_id = context_access_state.instance and lamport = logical_time.
The three read-model sites drop the reference's standing-kind
precedence, which contradicted the frozen pure-triple order under
replication ties while being locally unobservable (local lamports are
strictly increasing); the lifted total-order test is adapted to the
frozen order with the reasoning recorded inline.

Duplicate machine_id is diagnosed and refused, never merged:
negotiate() already refuses two live peers with one instance, and the
new ConceptReplicaIdentityError refuses incoming events that claim the
receiver's own instance for history it never wrote, or that bind one
(origin_instance, origin_seq) slot to two different events.

Lamport advance on import (design.md's B3 verification note): matrix
item 4 was run against the unmodified reference allocator first, and
passes -- _allocate's table-wide MAX(logical_time) already advances the
next local event past every imported lamport, so no explicit
advance-on-import step was added.

Also wired: v49 adds the three replica-content-generation triggers for
the two replicated tables (v46 froze its own list); staged transport
indexes both tables by id; the legacy-sync guard treats the sidecar's
seeded singletons and FTS shadow tables as bookkeeping, not populated
context; tiering's archive-completeness proof excludes the per-database
clock and concept-FTS shadow tables while keeping roots/events in the
retention proof; compaction seeds a fresh clock/marker and copies roots
after their citation closure so the sidecar triggers re-validate.

Tests: the normative two-copy matrix (7 scenarios) on fixtures in both
replication orders, replay idempotence, post-convergence Lamport
advance, read-model hash equivalence, concurrent accept/retire resolved
to the computed winner in either order, causal accept-then-retire, and
three duplicate-identity refusals; plus the same matrix once on two
real Online Backup copies (live_concepts marker, copy B honestly
re-identified before any concept history exists, source sentinels
asserted unchanged). Full package suite: 1999 passed.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

…MCP tool

session-context gains winddown --session ID --from FILE|--stdin and
concept accept|retire ID --reason, concept bind LEGACY_ID --from FILE
--reason, concept import-okf DIR [--dry-run] [--report PATH], and
concept project --out DIR [--project ID] [--json], all thin wrappers
over the frozen ConceptService seam with the reference CLI's bounded
input reading (wind-down byte limit, descriptor-anchored non-symlink
files), atomic report writes, deterministic JSON payloads, and the
reference exit-code contract (2 validation, 1 runtime/write failure).
mcp_server.py gains memory_winddown with the same validation: a
field-level error list raises a structured ToolError and writes
nothing; a valid batch commits atomically.

Why: tasks.md 3.2 -- one seam, one validation surface, no second
implementation of concept transitions; context_assertions keeps its
execution-state vocabulary (verified in the round-trip test).

Also frozen (tasks.md 3.4): ConceptService's public API is pinned by an
exact-signature regression test (method set, every signature string,
and the four result shapes), so B4 consumes a checked contract.

This commit also carries the live_concepts harness extensions and their
opt-in tests (they type-check as one unit with the CLI): the live
two-copy matrix on two real Online Backup copies, and the full
2,033-record legacy OKF import runner whose sanitized report feeds the
OpenSpec evidence attachment.

Tests: lossless round trip, stdin input, field-level failures for
malformed documents/invalid JSON/symlinked input, lifecycle verbs with
retired-terminal diagnostics, legacy bind, OKF dry-run/write/report,
projection output, MCP happy path and loud structured failure with
zero partial writes.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

…evidence

docs/context-memory.md gains the wind-down/concept command reference,
the two trust labels (model-proposed vs legacy-unbound, never blended),
the frozen cross-machine standing order in one paragraph, and the
frozen ConceptService surface table. CHANGELOG records the concept
sidecar under [Unreleased] Added. OpenSpec tasks 3.1-3.5 are checked
with their evidence pointers (3.5's independent review remains the
reviewer's step). The evidence file is added with -f: openspec/ is
gitignored for new files, but this change's artifacts are tracked and
the brief requires the report attached to the change directory.

Evidence: openspec/changes/sessionweaver-phase2-retrofit/evidence/
legacy-okf-import-report.json -- the full legacy OKF import on a real
Online Backup (live_concepts marker): 2,035 scanned, 2,033 parseable
records imported legacy-unbound with zero write failures and the exact
A3b1 baseline FTS content hash (0c036eae...); the two extra files are
post-baseline non-records classified invalid_schema (reported, never
dropped); dry-run/write classification identical; idempotent re-import
already_present=2,033 with zero writes; OKF tree sentinel and source
database sentinels unchanged. The visibility sub-classification split
differs from the baseline because this run retains every project
unclassified on a newer corpus (5,813 sessions vs 5,678); the report
retains the split (no_exact_match 1559, no_visible_evidence 429,
oversized_evidence 45) for the reviewer.

The detect-secrets baseline is regenerated for the evidence hashes.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

…ence

Completes the previous docs commit: the gitignore advice for openspec/
aborted the add chain, so the evidence attachment missed it. openspec/
ignores only new untracked files -- this change's artifacts are
tracked, and the brief requires the sanitized legacy OKF import report
attached to the change directory, so the evidence file is added with
-f. The detect-secrets baseline is regenerated for the report's hex
hashes, matching the established false-positive handling.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

pytest resolves rootdir (and its configfile) from the paths it is given,
so any package-scoped invocation reads this package's pyproject.toml and
never the workspace root's -m exclusions. Round 0 shipped the package
config without them, so a plain 'pytest packages/agent-session-tools/...'
silently ran the live_concepts suites: two 1 GB SQLite Online Backups of
the owner's real sessions.db, a 140-second OKF import, and two committed
evidence files rewritten -- the same trap fired during the independent
review (B3 review round 1, Important #2).

Add the -m exclusion for every opt-in marker this package declares
(integration, live_ontology, live_concepts), matching the workspace-root
convention and packages/studyloop's MUST-duplicate precedent, and pin it
with a subprocess regression that proves package-scoped collection
deselects every live-marked test by default while an explicit -m opt-in
still selects them and ordinary tests stay selected.

Co-Authored-By: Kiro <noreply@kiro.dev>

Round 0's committed migration receipt was captured at commit 1, before
migrate_v49 gained its six replica_content_context_concept* triggers, so
its whole-database schema_sha256 (5c2f2c56...) no longer described the
shipped migration -- and nothing deterministic could catch that, because
that hash covers every sqlite_master row and is therefore a property of
the source corpus, not the migration (a fresh schema.sql install yields
81f3310a..., the real backup 6dfb4027...) (B3 review round 1,
Important #1).

Give the receipt a source-independent fingerprint instead:
sidecar_migration_fingerprint() hashes the DDL of exactly the objects
migrate_v49 installs (context_concept* objects, the two
context_citations_bound_* guard triggers, the six replica_content_*
triggers; FTS5 shadow tables excluded -- library-generated from the
fingerprinted virtual-table declaration), emitted as
sidecar_objects_sha256 (evidence_version 1 -> 2). Two always-on fixture
regressions pin it: the name selection equals the complete non-shadow
v49 delta (so a future migration edit cannot slip an object past the
receipt check), and a fresh install of the shipped migration must
reproduce the committed receipt's hash byte-for-byte.

Receipt regenerated at HEAD on a fresh SQLite Online Backup (live DB
untouched: v47, 5,813 sessions); its schema_sha256 is now 6dfb4027...,
byte-identical to the review's independently reproduced value. Secrets
baseline regenerated for the receipt's changed hex strings only.

Co-Authored-By: Kiro <noreply@kiro.dev>

Bring the independently reviewed migration v49, lifted concept lifecycle/wind-down/import/projection, replication proofs, CLI/MCP surface, and full-corpus import evidence into the SessionWeaver Phase 2 integration branch.

Capture the existing public search contract before introducing the shared AND-to-OR planner. The fixture freezes row keys, deterministic ordering, null/default values, phrase/operator behavior, and the 300-character preview boundary.

Reuse the released SessionWeaver planner behind session_search while keeping its public row schema, SQL ranking, filters, and 300-character previews unchanged. Black-box tests prove the frozen cases remain identical and only the previously empty implicit-AND query widens through OR fallback.

Port SessionWeaver v0.2.0 concept-first recall onto StudyLoop's B3 authorization seam and shared query planner. The public MCP tool validates strict bounds, preserves the frozen report schema, deduplicates concept source sessions, and proves through behavioral traces that embeddings and ontology are not consulted.

Have studyloop install agents merge session-db and studyloop into Claude Code, Kiro, and Codex configuration without touching the real HOME. Format-preserving temp-HOME tests prove unrelated entries survive, repeated installation is byte-identical, missing configs are created, and doctor reports registration without mutation.

Repair an incorrect StudyLoop-owned JSON MCP entry by replacing only that value object, then append any missing owned entry. This avoids reserializing unrelated MCP entries while retaining byte-idempotence on subsequent installs.

Retain the exact 25-question corpus, aggregate-only v47 Online Backup evidence, and a reproducible released-reference acceptance runner. Document the frozen recall contract and MCP registration, add positive work/personal scope coverage, and mark OpenSpec B4 complete after a green 5,964-test preflight.

Route explicit phrase and boolean queries through the historical FTS escaping path so the shared recall planner remains frozen. Restrict AND-to-OR widening to empty implicit plain-text searches and pin compatibility with negative controls.

Replace owned JSON values and TOML subtrees by parser-validated byte spans rather than canonical-only regexes. This preserves unrelated configuration, prevents duplicate keys, handles CRLF and nested tables, and converges byte-identically on rerun.

Track TOML lexical state before recognizing candidate MCP table headers. This prevents owned-looking text inside multiline values from truncating unrelated config while retaining byte-preserving subtree repair.

…, substr re-check, receipts

scripts/knowledge_proof/claims_writer.py: the deterministic half of the writer.
It calls no model. population (342 ingested PoC sessions, hash-ordered,
prose≥10 subset 200), packet (per-event citable evidence + derive-v1 flags,
≤48 KiB with truncation recorded, prompt and packet sha256), render
(byte-deterministic prompt text), ingest (strict JSON; every schema and
citation refusal recorded with reason; never a partial insert; post-run
SQLite substr() re-check of every inserted citation; a writer label whose
prompt sha does not match the packet's fails the run), summarise (yield on
both G2 denominators, refusals by reason, recheck total, runs used).

Gold-blind by construction: the module contains no gold or sealed reference
(test-asserted); packets are built from the store alone.

Orchestrator smoke on a scratch copy: a fenced response with one grounded
claim, one fabricated quote and one citation-less claim → inserted 1,
refused 2 (citation_unbound, no_citations), recheck_mismatches 0. The real
store still holds zero claims. 52 harness tests; ruff + pyright clean.

pyproject testpaths gains scripts/knowledge_proof/tests (the one permitted
line outside the lane). Note: the builder saw 16 failures in
packages/studyloop/tests locally; CI is green on every pushed commit, and
the one reproduced (test_cli_brain expecting exit 1) assumes no second brain
is configured — a pre-existing test-isolation issue on main, out of scope.

…d and entailment below gate

Pilot: 40 sessions in hash order, 40 claude-sonnet-5 writer runs, packet-only
context. 183 claims proposed, 162 inserted (104 Finding, 25 Decision, 19
Procedure, 12 Problem, 2 Preference), 180 citations, UNBOUND WRITES 0 by
SQLite substr() re-check of every citation. 21 refusals: 13 paraphrases,
8 from one session where the writer cited row numbers instead of evidence ids
on a 141-row packet — the harness held on every one.

Yield on the pre-registered primary denominator: 24/29 = 82.8% (gate 90%).
Decomposed, not argued: 4 of the 5 misses are sessions inside the denominator
with no learner voice (no learner turn; council-judge briefs; a pasted
AGENTS.md); 1 is the id-format defect. On sessions with learner voice: 12/13.

Blinded entailment audit (deepseek-3.2, 100 claims, statement+quotes only,
key outside the repo): 82 yes / 18 partial / 0 no (gate 95%). Taxonomy:
hallucinated-detail 13, over-claim 4, preference-inferred 1. Decomposed: for
14 of the 18 partials the statement's extra details ARE in the session's
evidence — the writer read them and cited only one sentence (86/100 claims
carry a single citation). 4/100 contain material absent from the session.
Transcript fidelity ~96%; citation completeness 82%. G2 is defined on
completeness, correctly.

G2 NOT PASSED on the pilot. Per the ruler: investigate the writer, never
relax the trigger. Next: writer-v2 spec (every factual element covered by a
quote; prefer 2+ citations; cite by 64-hex evidence_id only) and a fresh
blinded audit. The no-learner-voice denominator finding is recorded for the
ruler owner, not changed here. Harness: cap now truncates to 8 and records
dropped_over_cap (spec deviation, documented on the receipt).

… before any v2 run

Each prompt change is tied to a measured failure from the pilot audit:
element-by-element quote coverage (14 under-citation partials), prefer 2–3
citations (86 % single-citation), verbatim 64-hex evidence_id (the 8-claim
row-number refusal), statement ≤ 300 chars, no stating implication as fact.
Held fixed: model, the same 40 sessions and byte-identical packets, harness,
insertion contract, auditor family and blinding; fresh audit seed over v2
claims only. Pass/improve/stop readings declared in advance; two prompt
rounds without passing stops Stage E.

…oid the reading, pin the brief

The v2 blinded audit returned 17/100 yes, but the brief had been rewritten
from memory (stricter wording) and the auditor ruled 3 of 4 known-answer
items wrong (statements verbatim from their quotes marked 'partial'). The
reading is void as a gate measurement, kept as the record of the fault.
The v1 brief is extracted verbatim into a committed template so every
future audit is byte-reproducible; the remedy (re-audit both samples with
the pinned brief, measure auditor noise on the already-scored v1 sample)
is declared before it runs.

…ms: 82 → 16 yes

Noise control on the already-scored v1 sample: per-item agreement 34/100,
all 66 flips yes→partial. No single-seat entailment reading (v1's 82
included) is a valid G2 measurement. Protocol declared before running:
majority-of-three within family plus a gpt-5.6 cross-family seat on both
samples, gate reading = the lower of the two, and an explicit
'not measurable' outcome if the families disagree by >10 points.

…; G2 not established: instrument

Writer-v2 on the same 40 sessions and byte-identical packets: 145 claims,
0 unbound writes, citations/claim 1.11→1.55, single-citation 89%→54%, the
row-number defect gone, yield 23/29 (v1 24/29) — five agent-brief sessions
now yield nothing, two warm-ups gained one claim.

Audit under the pinned brief, seven seats total. deepseek on the identical
v1 items: 82 → 16 → 86 yes (per-item agreement 34/100 between the first
two; unanimous across three on 27/100). gpt-5.6: v1 58, v2 77. deepseek
valid seats on v2: 91, 96. Every clean seat ranks v2 above v1 (deepseek
+12, gpt +19). Families disagree by 21 (v1) and 14 (v2) points — over the
pre-declared 10-point bound — so G2 is recorded NOT ESTABLISHED — INSTRUMENT
rather than passed or failed on a number nobody can reproduce.

Two findings for the ruler owner, recorded not actioned: the audit clause
needs a reliability floor before it can be met or failed; the primary
yield denominator contains sessions with no learner turn.

…before the last DEV look

Pilot claims cover 3 of 60 DEV gold sessions (6 of 91 questions, no
paraphrase items); a claims arm over them would be flat by construction
and would fire the stop rule for a reason unrelated to the architecture.
The full population reaches 26 gold sessions / 39 questions across all
strata, inside the ruler's 400-run writer budget (382). Ruler unchanged;
spec-v2 deviation stated.

…ms declared before look 3

Two arms, declared with their coverage bound (19/60 DEV gold sessions carry
a writer-v2 claim; a claims-only arm can reach 30/91 questions) before any
look-3 run. recall_claims: in-memory FTS5 over writer-v2 claims (title,
statement, tags), same planner as B1_clean, bm25 then claim rowid, first K
distinct sessions. B1_clean_plus_claims: reciprocal rank fusion (k=60,
1-based ranks, weight 1) of the two full deduped rankings, tie-break best
prose rank then session id. B1_clean's ranking is factored into a shared
helper so the fused arm consumes the same list B1_clean cuts; its output is
unchanged (tested).

score.py now emits comparisons between every ordered pair of feature arms,
so the attribution reading B1_clean_plus_claims_vs_B1_clean is produced by
the committed script. Statistics unchanged. 63 harness tests pass.

…bound writes, 19/60 DEV gold sessions covered

302 sessions attempted in gold-blind hash order; 301 responded; one
(index 318, not a gold session) was refused at the agent layer on both the
first run and the single permitted retry and is recorded as not attempted.
Yield on the primary denominator 149/200; refusals are paraphrases the
harness held. Writer runs 384/400. Coverage bound for look 3 recorded
here and in fusion-spec-v2 before the look.

…_clean); G1 looks end

B1_clean_plus_claims 0.151 vs B1_clean 0.291, Δ −0.140 CI95 [−0.245,
−0.041]: not established and significantly worse. Two flat looks → the
two-flat-looks stop rule fires; no look 4. B1_clean +0.184 over B1
reproduced exactly. recall_claims alone: 0.130 (R 0.207 > B1 0.103; P 0.000)
within its 30/91 coverage bound.

Mechanism from the receipt: fused lost 17 questions B1_clean had (gold at
prose rank 1–2 in 12/17, absent from the claims list in 16/17, fused rank
7–39) and gained 4. Equal-weight RRF over a ~127-session OR-planner claims
list promotes any weakly matching claimed session above the best prose hit.
ADR-0011's retrieval benefit is NOT ESTABLISHED on DEV under G1; recorded,
not re-tried.

…h, established; G1 bar not met

SEALED (84 questions, 56 clusters, sha 90ef67ad byte-verified, mode 0400
before and after, fresh store copy deleted after use): B1_clean 0.283 vs
B1 0.115, Δ +0.168 CI95 [+0.076, +0.268], non-inferior on K/P/R — the DEV
result (+0.184) replicates on held-out data. Claims fusion replicates its
harm (−0.154 vs B1_clean, CI95 [−0.252, −0.065]).

G1 NOT ESTABLISHED: the clause's 0.64 macro bar for a fused arm is not
approached by any arm built here. The composite claim may not be written.
The shippable finding stands: the shipped AND-first planner is the defect;
a phrase-token OR planner over prose-only FTS is a +0.17 recall fix.

…CHANGES; dispositions recorded

The gpt seat's BLOCKER (receipts void on digest mismatch) is refuted on
the artefacts: every result receipt's digest equals amendment-002's
committed per-split reference (DEV 9aa2b495 at looks 2 and 3, SEALED
965f5b1e); the field the seat compared against carries the superseded,
non-reproducible original digest — a record-keeping defect, accepted.
Also accepted: the digest omits retrieval configuration (provenance gap);
the stop-rule wording is restated in the ruler's lower-bound terms
(+0.092 → +0.092/+0.060 → −0.054: two looks without a rise); the
mechanism evidence is now retained by a committed script
(look3_mechanism.py → stage-f-look3-mechanism.json: lost 17, gained 4,
gold at prose rank ≤2 in 12/17, absent from claims list in 16/17); and
B1_clean's lift is relabelled a prose-control planner finding, not a G1
or knowledge-layer result. Gate outcomes unchanged.

… finding; deviations; follow-ons

Status → measured, not established (v1.2). G1: fused arm 0.129 on SEALED
against a 0.64 bar, worse than the prose control (−0.154). G2: binding
held (0 unbound over 2,057 citations); entailment not measurable with a
single-model blinded audit. Composite claim not writable. Established
separately: the pre-declared prose control beats the shipped path by
+0.168 on SEALED — a planner fix for agent-session-tools. Three deviations
from the ADR/ruler text recorded with their mitigations.

… showcase)

Minimal truthful revision of the Stage A architecture diagram: the
retrieval path that was established on SEALED (prose_fts, OR planner,
+0.168) is the emphasised edge; the claims fusion edge carries its
measured −0.154; the three cards state what is established, what is not,
and what held. archify validate --quality showcase: ok; deliver: ok
(specification sha a65b0878…, artifact sha 5a79003e…). visual-check could
not run in this environment (Chrome sandbox init refused; the Stage A
artefact fails identically here), so browser evidence is not claimed.

…ary gap, 35% ranking

Deterministic, read-only census over every learner turn in the 2,361
human-driven sessions (8,414 turns; 1,144 pastes over 200 words and 2,693
sub-3-token turns excluded; 4,577 measured). Two proxies per question:
stemmed content-token overlap with the REST of its own session, and whether
the committed prose FTS + OR planner recovers the question's own session in
the top 5 from the other turns alone.

Median overlap 0.67; only 7.4% of questions share no content word with their
transcript. Self-retrieval: hit 57.3%, miss-by-vocabulary-gap 7.4%, miss-by-
RANKING 35.3%. Ranking failures outnumber vocabulary failures five to one,
and the vocabulary figure is inflated by unanswered sessions and two adapter
artefacts (kilocode 48%, gemini 22% vs kiro 8%, codex 1%, claude_code 0%).
Own-session comparison is a lower bound on cross-session drift; stated in
the artefact. Decision input for the embeddings question, not a gate.

Andy's 2026-09-10 ruling fixes the supported session sources at claude_code,
codex, grok, kiro_cli, opencode, pi plus first-party study_mentor; main hides
the 1,279 sessions under seven retired labels at every read path and never
deletes them. The archive adapter is the corpus for the paraphrase census and
the knowledge-proof arms, so it needs the same allow-list or census v2 would
measure a corpus the product no longer serves.

ArchiveAdapter.open(path, sources=SUPPORTED_SOURCES) filters every session
enumeration -- discover, session_ids, message digests, and all three lineage
views -- with `source IN (...)` (bound, sorted). parse/parse_id by explicit id
stay unfiltered so deliberate access works. lineage_map now requires both
endpoints in scope; an in-scope sub-agent whose parent is under a retired label
is reported by the new out_of_scope_lineage() instead of parking in
lineage_pending forever. sources=None emits SQL byte-identical to before, so
`ingest-archive --include-retired-sources` is a true escape hatch, and the
ruler's pinned _load_corpus_digest is untouched so existing receipts stay
comparable. The ingest manifest records the scope and hidden counts.

One pre-existing fixture inserted its duplicates session as source="repoprompt",
which the allow-list would have silently excluded while four assertions kept
passing over an absent row; it is now codex. 299 -> 314 tests.

…rawing v1's retired-label rows

v1 measured retrieval over a store ingested from all 14 sessions.db labels.
The 2026-09-10 ruling fixed the supported set at six harnesses plus the
first-party study_mentor source, and hid the 1,279 sessions under the seven
retired labels from every read path. A census has to be measured over the
corpus the retriever will actually serve, so v2 re-ingests through the scoped
ArchiveAdapter into a separate store (v1's store keeps its recorded sha256)
and re-runs the same script with the same phrase-token OR planner.

Headline: 3,299 questions (was 4,577), self-retrieval@5 61.1% (was 57.3%),
vocabulary-gap 5.7% (was 7.4%), ranking 33.2% (was 35.3%). The sidecar
decomposes the +3.8pt honestly: every supported harness's question set is
byte-identical to v1 (same n, same vocabulary-gap counts), so most of the
shift is composition from dropping low-scoring retired labels; the genuine
retrieval effect is 23 ranking misses (22 kiro_cli, 1 claude_code) that had
lost their top-5 slot to a retired-label session and now rank, with zero new
misses anywhere. Ranking remains the dominant miss class and the 70% target
is not met on the six-source corpus, so the ranking pass stays open.

The sidecar withdraws v1's aider/kilocode/repoprompt/litellm-proxy/gemini_cli
rows as product findings without editing the v1 receipt, and records that
Stage 4's planner is not a confound: both censuses queried the shipped planner.
Every figure in the sidecar was re-derived from the two JSON receipts by
script before commit (one miscount, 9 -> 10 withdrawn examples, was caught).

The .secrets.baseline gains three entries: the sha256 digests in the two new
JSON receipts, the same hex-high-entropy false positive the v1 receipts carry.

…v2 aggregates only implied

The single-seat Stage 2 review (gpt-6-astra) made two MAJOR points about
the v2 sidecar that were right about evidence class: identical per-harness
n and identical vocabulary-gap counts make "same question set, 23
recoveries, zero regressions" an inference, and equal archive counts make
"corpus unchanged" an inference. Both stores still exist, so these two
scripts measure instead.

paraphrase_census_pair.py keys every eligible question by
session|sha256(text)|occurrence and runs the census's own decision (same
eligibility, tokeniser, self-exclusion, planner, K) in both stores. Result:
membership identical (3,299 = 3,299); 41 questions changed class, 32
miss->hit and 9 hit->miss, net +23 -- so the aggregate hid 9 regressions
and 9 extra recoveries, including a 4-in/4-out swap inside codex's
"unchanged" row. Of the 32 recoveries, 23 had a retired-label session in
v1's top-5 (displacement) and 9 had none (bm25/IDF shift from the smaller
index); all 9 regressions are IDF-shift. Decomposition: composition +3.09
pt, retrieval +0.70 pt. Content: 4,579/4,580 sessions byte-identical prose;
one live codex rollout gained 4 prose events between ingests (learner turns
unchanged, none of the 41 changes are its questions). v2's 20 rejects are a
subset of v1's 41.

paraphrase_census_duplicates.py exists because the v1 aider row (1/204)
turned out to be 203 byte-identical copies of one fixture prompt: identical
text in N sessions is a structural self-retrieval miss no ranker can fix,
and the census counts it as "ranking". On the six-source corpus 475/3,299
(14.4%) eligible questions have an identical sibling in another session and
221 (6.7%) have five or more -- claude_code 78/205 -- which bounds the
"ranking misses dominate" reading in the sidecar.

Both scripts are read-only on both stores. The baseline gains the sha256
digests in the two JSON receipts, the same false positive as every receipt.

… six corrections measured

Single-seat review per the plan council's cadence. The seat found the
sidecar's arithmetic sound and its interpretation inferred from aggregates
that cannot distinguish net from gross. Rather than hedge the wording, the
paired and duplicate-text censuses (dacbe46) measured each point: 32
recoveries / 9 regressions (net +23, 23 displacement + 9 IDF shift, all
regressions IDF shift); composition +3.09 pt vs retrieval +0.70 pt; 4,579
of 4,580 sessions byte-identical (one live codex rollout re-exported, no
question affected); the v1 aider row was 203 copies of one fixture prompt,
not a prose or adapter finding; 221 of the 1,096 "ranking" misses are
identical-text duplicates no ranker can win, so ranking is 26.5-33.2%, not
33.2%; the 21 under-threshold questions are opencode 16 + pi 5, study_mentor
has 0 eligible learner turns. The record lists the six sidecar sentences it
supersedes (receipts are never edited) and what changes for Stage 4 and the
later ranking pass.

…s pre-planner and planner code alike

score.py builds the shipped arm from mcp_server._session_search_queries,
which only exists after PR #18's 4fe2e4c; a B0 pinned at today's main has
no such helper. This wrapper mirrors whichever query shape the imported
package ships (single escape_fts_query AND query, or the planner's
sequence) and purges the module cache on EVERY arm build -- the harness
only purged when a pin was given, so the second arm silently reused the
first arm's modules and both arms scored one code (caught when both arms
printed the same shape). Used for the Stage 4 receipt on main.

…ecar -- code, tests, migrations, registrations

Owner ruling 2026-09-10 (ADR-0011 on main): OKF is not part of the solution
and is removed entirely, leaving no remnant, in preparation for a semantic
layer. Evidence in receipts/okf-removal-inventory-2026-09-10.md: no serving
path read any of it, 0/2,033 imported concepts citation-bound, the ontology
moved fused recall by +0.00, value gates never reached.

agent-session-tools: 12 modules deleted (concept_cli, concept_live,
concept_schema, concepts, okf_import, ontology, ontology_live, plus the
sidecar-only authorization, projection, safe_fs, winddown and recall
seams) and 18 test files; migrations v48/v49 and their registration
removed, CURRENT_VERSION back to 47 (what main ships); the
memory_winddown and memory_recall MCP tools removed so the tool set equals
main's; live_ontology/live_concepts markers removed from both pyproject
files. Ten files whose whole branch diff was OKF were restored to the
MERGE BASE (not main's current version -- restoring to main would have
imported main's newer work; caught and corrected during the lane's own
audit). recall.py was memory_recall's engine (PR #18 drop-half, d573133):
deleted rather than kept as a second session_search.

studyloop: check_ontology_freshness and its doctor registration removed
(_doctor.py and doctor/harness.py now match main); test_doctor_ontology.py
deleted. scripts/b4_recall_acceptance.py deleted (existed only to run the
v49 migration and import_okf); pin_poc_set.py docstring retargeted.

Kept, because they are not OKF: the learning-memory package and its
claims/evidence store; studyloop's learning tier (history/concepts.py,
learning/concept_quality.py, get_concept_context -- identical on main).

Gates on the worktree: ruff check clean, 727 files formatted, pyright
0/0/0; agent-session-tools 1,691 passed / 0 failed; studyloop reds equal
the pinned environment set plus two expected on a branch that predates
main's Stage 3 fix. Finish line: git grep for
okf|ontolog|concept_sidecar|context_concept|memory_winddown|memory_recall
over packages/ returns nothing.

…ED; amend the frozen ruler; move the evidence receipts

ADR 0011 (claim-centric learning memory) keeps its text: a dated
"Superseded sections" note at the top marks every OKF-import, tier-1
ontology and concept-sidecar section RETIRED 2026-09-10 and cites the
removal inventory; the claim-centric learning-memory decision itself
stands. The validation ruler is frozen, so it gains an amendment recording
that G3a/G3b scored layers that no longer exist, rather than a rewrite.
docs/session-memory.md, context-memory.md and mcp.md no longer describe the
removed layers; CHANGELOG gains a Removed entry naming them and why.

The four OKF evidence receipts under docs/data (migration v48/v49
receipts, tier-1 baseline, B4 live evidence; ~7 KB) move unchanged into
receipts/retired-okf-evidence/ -- they are the measurements the retirement
rests on, so they live with the other receipts instead of beside the
product's data files. Nothing under docs/ describes OKF in the present
tense; the finish-line grep over the branch hits only receipts, the
RETIRED-marked ADR sections, the learner-topic string, openspec (retired
in Stage 8) and the CHANGELOG entry.

…of (byte-identical to main)