JSON output is fetch_result.v1; plain output is human-friendly
labeled sections (chunk: before / target / after; doc/span: full
text + stderr truncated hint).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Line-based slice over fmt_canonical_to_markdown output.
PDF / audio source_type → span_not_supported StructuredError.
Out-of-range line_end clamps to total; effective_end reflects
post-budget trim. invalid_input on zero / inverted bounds.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Walks CanonicalDocument blocks, serializes to markdown, applies
chars/4 budget when opts.max_tokens is set. doc_not_found
preserved through StructuredError.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Chunk mode + +-N context. doc / span modes return placeholder
errors (filled by subsequent tasks). fmt_canonical_to_markdown
helper introduced now since doc mode (Task 4) consumes it.
Errors are typed StructuredError so classify preserves
chunk_not_found / doc_not_found through the wire layer.
Adds SqliteStore::list_chunk_ids_for_doc so the facade can derive
+-N neighbors without leaking direct rusqlite usage into kebab-app.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Domain types for `kebab fetch` 3 modes (chunk / doc / span). All
types Serialize so wire layers hand them through serde_json
directly. FetchKind is snake_case-renamed to match the wire
discriminator literal in fetch_result.v1.
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>
ErrorV1 is the workspace wire error struct; boxing here would
force every call site to deref through a Box for no win — the
err-path is rare. Single allow at the function level.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
SearchInput gains max_tokens / snippet_chars / cursor (all optional).
Output wrapped in search_response.v1 to match CLI; existing
tools_call_search test updated to read v["hits"] instead of the bare
array.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
JSON output wrapped in search_response.v1 (breaking — agent must
adapt). Plain output unchanged + [truncated; use --cursor X]
stderr hint when budget tripped.
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>
Budget loop: snippet shorten → k pop → ≥1 hit floor. Cursor
encode/decode threads corpus_revision; mismatch surfaces as
stale_cursor anyhow error. App::search retained as thin wrapper.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Opaque base64(JSON{offset, corpus_revision}). Mismatch or
malformed input returns ErrorV1 with code = stale_cursor.
base64 promoted to workspace dep.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pointed at the actual fb-33 design spec path + clarified that
the AskOpts type widening is a byproduct of the new wire schema
forcing single-sink 3-stage transport, not a stand-alone breaking
change.
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>
Three Ollama-gated integration tests covering:
- stderr lines parse as answer_event.v1 (retrieval_done first,
final last, all carry RFC3339 ts).
- stdout final line is answer.v1 (backwards compat).
- non-stream path (--json without --stream) unchanged.
- BrokenPipe stderr → child terminates cleanly via cancel
propagation through pipeline SendError.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Background-thread driver runs ask_with_config; main thread
drains the receiver, serializes each StreamEvent to ndjson on
stderr. BrokenPipe → drop receiver → pipeline SendError →
cancel + LlmStreamAborted refusal. Final stdout line is the
existing answer.v1 (ingest_progress.v1 backwards-compat
pattern).
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>
Worker channel now carries kebab_app::StreamEvent. drain_stream
matches on Token { delta }; RetrievalDone and Final are ignored
(citations render from last_answer, Final is redundant with
worker join). app::AskState.rx type widened to match.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
RetrievalDone after retrieve+stale-stamp, Token per LM chunk
(SendError → break, FinishReason::Cancelled, RefusalReason::
LlmStreamAborted), Final on success. answers row still persists
on cancel for audit. Adds FinishReason::Cancelled, re-exports
StreamEvent from kebab_rag, migrates two pre-fb-33 sink tests
in tests/pipeline.rs to the new StreamEvent type (the
"dropped receiver does not abort" test inverts to record cancel).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3-variant discriminated enum (RetrievalDone / Token / Final).
AskOpts.stream_sink now carries StreamEvent. Other crates fail
to compile until subsequent tasks adapt their call sites.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3-variant StreamEvent enum (RetrievalDone / Token / Final) 을 통해
RagPipeline 이 retrieval / per-token / final 단계를 sink 로 발사.
CLI `kebab ask --stream` 이 ndjson event 를 stderr 로 흘리고 final
stdout line 은 기존 answer.v1 그대로 (ingest_progress.v1 패턴).
Cancel = stdout 닫힘 → SendError → LLM stream break +
RefusalReason::LlmStreamAborted 로 partial answer 기록.
MCP streaming 은 v0.5+ 별도 검토 (scope out).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
fb-32 머지로 wire schema 가 search_hit.v1 / citation.v1 의 required
필드를 두 개 (indexed_at, stale) 확장 — additive minor 로 분류했지만
strict validator 입장에서는 한 번 깨진 셈이라 minor bump.
surface 변경 (사용자 도그푸딩 영향):
- 모든 search hit / RAG citation 의 wire JSON 에 indexed_at (RFC3339) +
stale (bool) 두 필드 추가
- CLI plain 출력 — stale doc 의 doc_path 옆에 [stale] tag (TTY = 노란색)
- TUI Search/Inspect/Ask pane — stale doc 의 doc_path 좌측에 [STALE] 배지
(Theme::Warning role)
- config.toml [search] stale_threshold_days 신규 (default 30, 0 = 비활성)
- env KEBAB_SEARCH_STALE_THRESHOLD_DAYS
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- spec: add one-line cross-link to HOTFIXES entry per CLAUDE.md
Spec-contract policy
- HOTFIXES: rename heading from "fb-32" to "p9-fb-32" matching
the rest of the file's full-ID convention
- config: defensive assert before string-replace in negative TOML
test guards against default-value drift causing unhelpful unwrap
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mirror of Task 9's search-output rendering: yellow [stale] on TTY,
plain text otherwise. JSON path inherits via serde on AnswerCitation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Yellow when TTY, plain when not. JSON path inherits via serde
on the domain type; no CLI-side wire change needed there.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- kebab-app::staleness::compute_stale gains note pointing at the
kebab-rag mirror so future modifiers know to update both copies.
- kebab-rag::pipeline: doc comments adjacent to compute_stale and
embedding_ref_for were positioned such that rustdoc would
misattribute them. Reorder/separate so each comment hugs its
own function.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
pack_context widened to carry indexed_at + stale alongside marker
and Citation. LLM-citation construction site now plumbs real values
from upstream SearchHit instead of the Task 6 UNIX_EPOCH placeholder.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Test helper missed the SearchHit field expansion from fb-32 Task 1.
UNIX_EPOCH + false placeholders consistent with the cross-crate
synthetic-mock pattern (hybrid.rs, vector.rs build_hit Task 4 stub).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
compute_stale: strict > boundary, threshold=0 disables, future
timestamps treated as fresh (clock skew safety). App::search
re-stamps on cache hit so config threshold changes take effect
without flushing the cache.
Also unblocks the workspace build by plugging placeholder
indexed_at/stale into the two AnswerCitation construction
sites in kebab-rag/pipeline.rs (the score-gate refusal path
forwards from SearchHit; the LLM-citation path uses
UNIX_EPOCH/false until Task 7 wires the real values through
pack_context).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
