Two new wire schemas land as additive minor: ocr_stats.v1 (corpus-wide
aggregate — total_events, success_rate, p50/p90/p99/max_ms, by_engine,
top-10 by_doc by failure count) and ocr_failures.v1 (per-doc or
corpus-wide recent failures, with --doc-id + --limit). Both ship via
new CLI subcommands `kebab inspect ocr-stats` / `inspect ocr-failures`.
App gains four facade methods: inspect_ocr_stats /
inspect_ocr_failures plus their *_with_config companions — required by
CLAUDE.md "the facade rule" so `--config <path>` is honored. The CLI
dispatch arms thread cfg explicitly into the _with_config form.
Runtime introspection emit (WIRE_SCHEMAS in schema.rs) gains two
entries; the meta JSON Schema (schema.schema.json) is untouched
because its wire.schemas is pattern-based, not enum-based.
ingest_log::percentiles extended to (p50, p90, p99, max). p99 surfaces
only via inspect ocr-stats; IngestSummary (round 1) stays 3-percentile.
SKILL.md synced with the two new schemas (AC-13).
Closure r2 G2 (facade *_with_config pair) + G3 (runtime emit, not
meta schema file) + closure r1 F4 (p99) resolved.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
이전: schema.v1.models 가 parser_version / chunker_version 단일 값만 보고 →
multi-medium corpus (md + pdf + code Rust/Python + dockerfile + k8s + manifest)
의 version cascade audit 누락 risk.
이후: additive minor — Models struct 에 active_parsers + active_chunkers Vec<String>
추가. backward compat: 기존 단일 field 보존 (markdown default), 신규 array 는
optional (#[serde(default)] + JSON schema required 미포함).
source:
- kebab_store_sqlite::fetch_distinct_parser_versions() 가
documents.parser_version DISTINCT + ORDER BY 반환.
- fetch_distinct_chunker_versions() 가 chunks.chunker_version 동일 pattern.
- collect_models 가 매 schema 호출마다 재계산 (cache 없음 — R-3 자동 해결).
wire schema additive only — 메이저 bump 불필요. v0.20.1 minor 로 충분.
integrations/claude-code/kebab/SKILL.md 동기 갱신.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`answer.schema.json` 의 `refusal_reason` description 의 PR 번호 정정:
`multi_hop_decompose_failed` 도입 시점 = PR-2 (#167, RefusalReason variant
+ ask_multi_hop decompose-failure 분기). PR-3a (#168) 는 `Answer.hops`
field + RagCfg knob 만 — refusal variant 와 무관.
검증
- `cargo test -p kebab-cli -j 1 --test wire_ask_multi_hop` 4 모두 통과.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Round 1 review found 2 doc gaps:
- docs/wire-schema/v1/reset_report.schema.json: 'orphans_only' missing
from scope enum; orphans_purged/purged_paths properties absent
- README: --orphans-only not listed in the reset prose
Schema additions are additive minor (default values keep back-compat).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- wire schema: relax effective_end.minimum 1 → 0 + expand
description to cover line-clamp + out-of-range sentinel
(panic-fix R1 emits Some(0) when line_start=1 and range is
beyond doc end — schema must accept it)
- tests: tighten first-chunk-target boundary test to assert ≤ 2
total neighbors (3-chunk doc, N=2). Strict "first chunk →
context_before empty" not assertable until chunks.ordinal
column lands (R1 #9 architectural caveat)
- store: trim contradiction in list_chunk_ids_for_doc warning
comment — drop "good enough for sequentially chunked
markdown" phrase that conflicts with "hash sort dominates"
paragraph above
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Previous round-1 fix dropped the speculative cursor branch on
the truncated path, leaving a contradiction with the docs:
- snippet-only shrunk → cursor emitted (returned == k_effective)
- k-popped → cursor null (returned < k_effective)
But docs promised the opposite.
R2 resolution: emit cursor whenever more hits may be reachable
(either retriever filled the page OR budget popped hits — the
popped ones remain fetchable from offset+returned). Drop the
artificial "widen vs paginate" copy; truncated and next_cursor
are now independent signals — caller may do either or both.
Updates: app.rs::search_with_opts logic + SearchResponse doc +
schema description + SKILL.md two bullets + max_tokens=0 test
asserts cursor IS emitted on k-pop case.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- error_wire: StructuredError wrapper preserves ErrorV1 through
anyhow → classify pipeline. Adds downcast short-circuit so
cursor::decode's typed code = "stale_cursor" reaches the wire
instead of being string-formatted to code = "generic".
- app: search_with_opts now wraps cursor::decode error in
StructuredError instead of anyhow! string format.
- test: error_wire pins both negative (bare anyhow → not
stale_cursor) AND positive (StructuredError → stale_cursor)
invariants. CLI integration test runs end-to-end and asserts
error.v1.code on stderr.
- app: next_cursor only emitted on full-page (k-pop) path; drop
speculative emit on snippet-only truncation that would point at
a different page than the agent expected.
- cursor: differentiate malformed-base64 / malformed-payload /
revision-mismatch error messages; all keep code = stale_cursor.
- test: cursor_rejected fixture uses .expect() to fail loud on
cursor non-emission instead of silent skip.
- test: max_tokens=0 → 1-hit floor + truncated=true.
- docs: SKILL.md + schema description distinguish snippet-shrink
(widen) vs k-pop (paginate) truncated cases. HOTFIXES notes
--no-cache semantic shift (cached path + clear vs uncached path).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wrapper around search_hit.v1[] with next_cursor + truncated.
Wire breaking — agent that parses bare array must adapt.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- pipeline: refresh module docstring step 5 to reflect new cancel
semantics (RetrievalDone/Token/Final + LlmStreamAborted)
- wire schema: spell out refusal-path behavior in answer_event.v1
description (only retrieval_done emitted; no final)
- test: factual comment on relax_score_gate-using test corrected
- test: new Ollama-gated stream_score_gate_refusal_emits_only_retrieval_done
- test: new ask_emits_no_final_when_cancelled_mid_stream pinning
the no-Final invariant on cancel
- pipeline: large_enum_variant comment broadened to acknowledge
RetrievalDone.hits as the dominant per-emit cost
- HOTFIXES: log AskOpts.stream_sink internal API break per spec
contract policy
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Discriminated ndjson event for `kebab ask --stream`. Mirrors
the ingest_progress.v1 pattern (stderr stream + stdout final
answer.v1 for backwards compat).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
schema.v1: full introspection report shape with required fields for
wire / capabilities / models / stats. capabilities object enumerates
all 10 flag names (current 6 true + future 4 false) as required keys.
error.v1: 7-code enum + permissive details object. Real emitted
details shapes documented in description (per-code context varies and
some fields are interim until IoFailure / OpTimeout typed signals
land in follow-up).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
도그푸딩 후 추가된 ask multi-turn (꼬리 물기) surface 를 frozen design
+ wire schema 에 명시. p9-fb-15 (RAG core) + p9-fb-16 (TUI UI) +
p9-fb-17 (V004 chat sessions) + p9-fb-18 (CLI session/repl) 의 spec
PR — impl PR 들이 이어진다.
변경:
- §2.3 Answer wire schema: conversation_id (String?) + turn_index
(u32?) 두 optional 필드. 기존 single-shot 소비자 (외부 wrapper)
영향 없음 — 두 필드 모두 optional.
- §3.8 RAG types:
- Answer struct 에 conversation_id / turn_index field 추가.
- Turn struct 신설 (history 가 prompt 에 들어갈 때 한 turn).
- §3.8 \"Multi-turn behaviour\" 신설 절:
- kebab-rag::ask vs ask_with_history 두 entry.
- prompt 빌드 priority: system+question (필수) → retrieved chunks
(k 줄여 fit) → history (newest 우선, oldest drop).
- retrieval query expansion (직전 answer 첫 200자 concat).
- Aborted vs Completed semantics — ask 는 single-shot 이라 cancel
시 partial token + grounded=false + LlmStreamAborted refusal
(variant 추가는 p9-fb-15 impl 가 함께).
- docs/wire-schema/v1/answer.schema.json: 두 필드 추가 +
created_at 에 format: date-time (sibling ingest_progress.v1 와
일관).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- §10 long-running 절 끝 빈 줄 3 → 1 (다른 절 사이 일관)
- wire schema + §2.4a 예제 JSON: kind_result → result (top-level
kind 와의 모호성 제거; ingest_report.v1.items[].kind 와 짝)
- wire schema 의 ts 필드: format: \"date-time\" 추가 (RFC 3339
자동 검증, wrapper 가 다른 format emit 시 즉시 잡힘)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
도그푸딩 후 추가된 long-running 작업 진행 표시 + cancel 정책을 frozen
design 에 명시. p9-fb-01/02/03 (ingest progress callback / CLI display
/ TUI background) 의 spec PR — impl PR 들이 이어진다.
변경:
- docs/wire-schema/v1/ingest_progress.schema.json (신규):
line-delimited streaming event schema. discriminated by `kind`
(scan_started → scan_completed → asset_started → asset_finished* →
embed_batch_* → completed | aborted). 마지막 줄은 기존
ingest_report.v1 그대로 (외부 wrapper backward-compat).
- 2026-04-27-kebab-final-form-design.md §2.4a (신규):
IngestProgressEvent 절. 이벤트 ordering / aborted 의 idempotency /
CLI 의 stderr vs stdout 분리 / TUI · desktop 의 in-memory 소비.
- 2026-04-27-kebab-final-form-design.md §10:
long-running 작업 (ingest, future eval run, RAG streaming, embed
batch) 의 두 invariant — progress 의 단일 source / cooperative
cancel + step boundary. trait (§7.2) 시그니처는 무영향 — facade
hidden parameter 로 추가.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
