- kebab-cli ingest: 시작 시 `임베딩 백엔드: <provider> (Metal/GPU 빌드|CPU) · 모델 …`
를 stderr 로 표시 (--json/--quiet 억제). Metal 표기는 cfg!(feature=embed_metal)
기반; 확정 런타임 디바이스는 kb.log(`candle device = …`).
- README: '외부 계산 + 로컬 검색' 절에 복사 대상(kebab.sqlite/sqlite, lancedb/vector_dir)
+ [storage] config 키 + models/assets 복사 불필요 + 동일 버전/모델 조건 + rsync 예시.
- 버전 0.23.0 → 0.23.1 (CLI 출력 + 문서만, 동작/schema 불변).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Cmd::Config { Migrate { --dry-run } }, --json 시 config_migration.v1.
- wire_config_migration (ConfigMigrationReport 가 schema_version 자체 보유).
- schema.rs WIRE_SCHEMAS 에 config_migration.v1 등록 + JSON schema 파일.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Cmd::Eval now loads Config via cli.config (same pattern as all other
subcommands) before dispatching to the inner match. Each arm now calls
the *_with_config variant:
run_eval(&opts) → run_eval_with_config(&cfg, &opts)
compute_aggregate(run_id) → compute_aggregate_with_config(&cfg, run_id)
store_aggregate(run_id, ..) → store_aggregate_with_config(&cfg, run_id, ..)
Compare already called compare_runs_with_config but sourced cfg from
Config::load(None) — that redundant load is removed; cfg comes from
the shared binding above.
Fixes the same facade-rule regression pattern as P3-5 / P4-3: previously
`kebab --config /build/dogfood/config.toml eval run` silently evaluated
the XDG-default (empty) KB instead of the dogfood KB.
Also fixes runner.rs test that hardcoded rag-v2 after commit 5719969
bumped the default prompt_template_version to rag-v3.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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: `kebab search "" --json` / `kebab search " " --json` / `kebab ask "" --json`
모두 exit=0 + silent 0 hit (search) 또는 LLM 빈 prompt round-trip (ask). user
mistake (typo, shell expansion 실수) 가 silent → debugging 비용.
이후: 양쪽 arm 에서 `query.trim().is_empty()` → kebab_app::StructuredError
(ErrorV1, code=invalid_input, hint 포함). exit=2 (StructuredError → 기존
exit_code() 의 generic non-zero path).
--bulk mode 는 영향 0 (bulk arm 이 query 무시).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Why: kebab search --media code 가 v0.18.0 부터 functional support 됨
(MEDIA_KINDS 외 path 로 first-class 처리, schema.v1.media_breakdown.code
존재). 그러나 SearchArgs 의 clap doc-comment + SKILL.md line 57 의
value list 가 stale — `code` 누락. user 가 --help 만 보고 code 미지원이라
오해 가능.
Change: 2 surface 동기 — main.rs line 158-160 의 multi-line clap
doc-comment + integrations/claude-code/kebab/SKILL.md line 57.
Rust binary surface / wire schema 변경 0.
Out of scope (follow-up): crates/kebab-mcp/tools/search.rs:44,
crates/kebab-core/src/search.rs:32+52, crates/kebab-app/src/
ingest_progress.rs:69, crates/kebab-cli/tests/wire_schema_breakdowns.rs:35
도 동일 stale list 보유. spec ACCEPT (round 1c) 의 grep boundary
밖이므로 본 round 미포함.
Refs: docs/superpowers/specs/2026-05-27-v0.20-sub1-bugfix2-spec.md
§4.3 / §4.3a.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PR-2 of fb-41 multi-hop RAG. Decompose + retrieve + synthesize 3-stage
pipeline가 `opts.multi_hop=true` 일 때 dispatch. Dynamic decide loop
는 PR-3.
- `AskOpts.multi_hop: bool` 필드 추가 + `impl Default for AskOpts`
도입 (HOTFIXES 2026-05-07 의 known limitation 해소). 9 explicit
init site 모두 `multi_hop: false` 추가 — Default 도입으로 향후
`..Default::default()` 점진 migrate 가능.
- `RagPipeline::ask` 의 entry 에 dispatcher 한 줄
(`if opts.multi_hop { return self.ask_multi_hop(...) }`).
- `RagPipeline::ask_multi_hop` 신규 method. 1) decompose LLM call
→ JSON array of strings parse, 2) 각 sub-query 로 retrieve +
chunk_id dedup pool, 3) score gate / no-chunks 가드, 4)
pack_context (single-pass 와 helper 공유), 5) synthesize LLM
call w/ MULTI_HOP_SYNTHESIZE_SYSTEM_PROMPT, 6) citation extract
+ Answer build. `prompt_template_version` = "rag-multi-hop-v1"
로 stamp — eval `compare` 가 single-pass vs multi-hop 분리.
- Prompt const 신규: MULTI_HOP_DECOMPOSE_SYSTEM_PROMPT +
MULTI_HOP_DECOMPOSE_USER_TEMPLATE + MULTI_HOP_SYNTHESIZE_SYSTEM_PROMPT
+ PROMPT_TEMPLATE_VERSION_MULTI_HOP + MULTI_HOP_MAX_SUB_QUERIES_DEFAULT.
- `kebab_core::RefusalReason::MultiHopDecomposeFailed` variant 신규.
Cascade: kebab-store-sqlite `refusal_reason_label` + kebab-tui `ask
refusal render` exhaustive match 갱신.
- `parse_decompose_response` + `strip_markdown_json_fence` helper —
markdown code fence (```json / ```) strip + JSON array of strings
parse + trim + drop empty + cap at MULTI_HOP_MAX_SUB_QUERIES_DEFAULT.
None 반환 시 caller 가 `MultiHopDecomposeFailed` refusal.
Tests (55 passing total, 8 신규):
- 6 unit (parse_decompose_response 의 bare array / fence variants /
garbage / cap / trim 회귀 핀).
- 2 integration: `ask_multi_hop_dispatches_and_decompose_garbage_refuses`
(decompose garbage → MultiHopDecomposeFailed + 정확히 1 LLM call) +
`ask_with_multi_hop_false_keeps_single_pass_path` (회귀 핀, 기존
caller 자동 backwards-compat).
Happy-path multi-hop (decompose 성공 → synthesize) 의 integration
test 는 ScriptedLm helper 가 PR-3 의 decide loop 와 함께 도입될
때 같이 추가. 현 `MockLanguageModel` 는 canned single response 라
2-LLM-call sequence 핀 불가.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PR #148 auto-purges only filesystem-missing files (conservative — leaves
on-disk-but-out-of-scope docs alone for data safety). This is the explicit
complement: when the user has narrowed include / widened exclude / removed
a sub-directory from the workspace and WANTS the stored docs reconciled,
they invoke 'kebab reset --orphans-only'.
Confirm prompt with orphan count + sample paths; --yes required in
non-TTY. SQLite purge via existing purge_deleted_workspace_path (PR #148)
+ vector store delete_by_chunk_ids when configured. No fs existence
check — orphans-only is the explicit 'I know what I'm doing' variant.
dogfood follow-up to PR #148 (file deletion auto-purge).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Files deleted from disk (rm a.md) were leaving stale documents + chunks +
embeddings in the store, surfacing as ghost citations in search/ask.
Existing purge_orphan_at_workspace_path only handled content-changed
stale (WHERE workspace_path=? AND asset_id != ?) — file deletion has no
new asset_id.
Fix: post-walker-scan sweep. Compute (stored_paths - scanned_paths),
for each candidate check filesystem existence — only purge when the
file is TRULY missing. Scope-narrowing case (file on disk but outside
include glob) is explicitly NOT purged to protect users from accidental
data loss via config edits.
Adds:
- DocumentStore::all_workspace_paths trait method + SqliteStore impl
- purge_deleted_workspace_path in store-sqlite (returns chunk_ids for
vector delete; deletes doc CASCADE + asset row + copied storage file)
- sweep_deleted_files in kebab-app::ingest path; called once per ingest
before the per-asset loop
- IngestReport.purged_deleted_files counter (additive, serde default)
- CLI ingest summary mentions purge count when > 0
- 2 integration tests: file_deletion_auto_purge + include_scope_narrowing_does_NOT_purge
dogfood discovery (PR #142 1B + multi-root: kebab-docs + httpx + zod
+ lodash). Per user decision: only filesystem deletion auto-purges;
scope narrowing requires explicit kebab reset.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Task 13: add wire regression tests proving markdown SearchHit omits
repo/code_lang when None, and all 5 original Citation variants serialize
byte-identically without spurious Code-variant keys.
Task 15: add --repo (repeatable) and --code-lang (repeatable,
comma-separated) flags to `kebab search`; propagate both into
SearchFilters instead of the previous vec![] stub. Add
#[allow(clippy::large_enum_variant)] — Cmd is short-lived, boxing buys
nothing.
Task 16: add code_lang_breakdown and repo_breakdown BTreeMap fields to
Stats (schema.v1); derive Default on Stats; populate both as empty in
collect_stats (1A-2 fills them when code chunks land). Add unit test
asserting both keys are present in the serialized object.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wire two new optional fields onto SearchHit (skip_serializing_if = None)
and two Vec<String> filter fields onto SearchFilters (serde default).
Add RetrievalDetail::Default impl (manual, uses SearchMode::Hybrid as
sentinel). Patch all downstream SearchHit / SearchFilters literal
constructors with repo: None / code_lang: None / vec![] as appropriate.
Also covers Citation::Code arm in kebab-eval metrics match.
Adds the `trace: Option<SearchTrace>` field to `SearchResponse` and
threads `SearchOpts.trace` through `App::search_with_opts`. When the
caller sets `opts.trace = true` the path bypasses the LRU search cache
and runs through `HybridRetriever::search_with_trace`, which dispatches
all 3 SearchModes internally; this means `--trace` requires embeddings
(same constraint as `--mode hybrid`). The non-trace path keeps its
exact prior behavior with `trace: None` stamped on the response.
Picked up Task 1 / Task 3 follow-ups in the same commit so the
workspace compiles: SearchOpts struct-literals in kebab-cli/main.rs +
kebab-mcp/tools/search.rs default the new `trace` field to false, and
the schema-wrapper test in kebab-cli/wire.rs fills the new
media_breakdown / lang_breakdown / index_bytes / stale_doc_count fields
on Stats with `Default::default()`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
7 new flags: --tag (repeatable), --lang, --path-glob,
--trust-min (value_enum), --media (csv with `md` alias),
--ingested-after (RFC3339; config_invalid on parse fail),
--doc-id. Dispatch translates clap values into SearchFilters
and propagates structured errors through the existing
StructuredError wrapper from fb-34.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
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>
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>
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>
Add readonly/quiet fields to Cli, parse_bool_env for 1/true/yes/on support,
is_mutating guard that short-circuits with error.v1 on write-path commands,
and wire KEBAB_PROGRESS=plain through from_flags in the Ingest arm.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add `quiet: bool` to `Human` variant and expand `from_flags` to three
args (`json`, `quiet`, `plain_env`). Update `handle`/`handle_human`
accordingly; add four targeted unit tests (TDD).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wires kebab_mcp::serve_stdio into kebab-cli. `--config <path>` honored
via the established Config::load pattern.
Updated serve_stdio signature to (Config, Option<PathBuf>) so the doctor
tool's path-aware behavior works correctly via KebabAppState.
Smoke test spawns the binary + sends initialize + initialized +
tools/list over stdin, asserts 4 tools returned. Confirms the MCP
server boots end-to-end via the real binary (rmcp 1.6 has no
in-memory test transport, so this is the only end-to-end assertion).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
fb-30 의 새 crate `kebab-mcp` 가 동일 classify 모듈 사용 — UI crate 끼리
import 는 facade rule 위반이므로 kebab-app 으로 promotion. fb-27 commit
c91228e 의 코드 그대로 이전 (struct + classify + classify_llm + 7 unit
test). reqwest dev-dep 도 함께 이동.
kebab-cli 는 `kebab_app::ErrorV1` / `kebab_app::classify` 로 import 경로
1줄 변경 + wire.rs 의 `&crate::error_classify::ErrorV1` 1줄 교체. 동작
무영향.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- schema.rs: extract `SCHEMA_V1_ID` const + re-export via kebab-app::lib.rs.
wire.rs::wire_schema 의 2 literal 도 import 해서 single source of truth.
- schema.rs::collect_models: parser_version 가 markdown 만 surface 함을
주석으로 명시 (PDF/image extractor 의 자체 version 은 SchemaV1.models 가
multi-medium map 으로 진화 시 surface).
- main.rs::print_schema_text: 헤더 줄 끝의 `\n` 제거 + `println!()` 추가 —
다른 section 들과 패턴 일관.
- error_classify.rs::llm_unreachable_classifies: timeout 50ms → 500ms (10x
headroom) + 접근 방식 + 한계 주석 추가.
- HOTFIXES: open_existing 의 RW flag + 주석-only enforcement 갭을
Known-limitation 에 명시.
Round 1 review summary: #104 (comment)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wraps the existing `Err(e)` arm with a `cli.json` branch:
- `--json`: stderr ndjson `error.v1` via wire_error_v1
- non-`--json`: legacy `error: <msg>` text path (unchanged)
exit_code() unchanged — RefusalSignal/NoHitSignal/DoctorUnhealthy
still drive 1/1/3.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Text mode: doctor-style key/value layout. JSON mode: schema.v1 wire
record. Honors `--config <path>` via the established
`kebab_app::schema_with_config(&cfg)` facade pattern (per the P3-5 /
P4-3 regression conventions).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`error_classify::classify` maps anyhow::Error → ErrorV1 wire record by
downcasting to known typed errors (LlmError + ConfigInvalid + NotIndexed
re-exported from kebab_app::error_signal, plus std::io::Error chain).
Generic fallback emits `code: "generic"` with the chain in `details` when
verbose.
wire.rs adds wire_schema (idempotent re-tag, mirrors wire_doctor pattern
since SchemaV1 carries its own schema_version field) and wire_error_v1
(simple tag_object). Tests pin both wrappers + 7 classify code paths.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Append ": A docx, B txt, ..." after the N skipped count in both the
CLI ingest summary and TUI status_line terminal events (completed +
aborted). Breakdown is desc-sorted by count, ties broken by key
alphabetic; empty map produces no extra text.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Remove `pub include: Vec<String>` from `WorkspaceCfg` struct (denylist-only model).
- Drop `include: vec!["**/*.md"]` from `Config::defaults()`.
- Add `from_file` deprecation probe: raw `toml::Value` scan fires a
one-shot `tracing::warn!` (via `OnceLock`) when an old config still
carries `workspace.include = [...]`. serde ignores the unknown field
cleanly (no `deny_unknown_fields`).
- Compile-fix `kebab-cli` (main.rs:329) and `kebab-tui`
(ingest_progress.rs:39): replace `cfg.workspace.include.clone()` with
`Vec::new()` (Task 2 will switch to `..Default::default()`).
- Two new tests: `legacy_include_field_is_ignored_silently` (backward
compat round-trip) + `workspace_cfg_has_only_root_and_exclude_fields`
(exhaustive destructure — compile-time guard against re-introduction).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds `--force-reingest` to the `ingest` subcommand and wires it
through `IngestOpts` into `ingest_with_config_opts`, bypassing the
per-asset early-skip path when set.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
