Files
kebab/crates/kebab-app/Cargo.toml
altair823 35c987df1c feat(app): log retention — keep_recent_runs + retention_days (Enhancement 4)
LoggingCfg gains two fields with serde defaults: keep_recent_runs
(default 100, top-N file retention) and retention_days (default 30,
time-based retention for both ndjson files and the SQLite mirror).

IngestLogWriter::open now runs cleanup_old_logs before creating a new
ingest-*.ndjson — delete iff (idx >= keep_recent) OR (modified <=
cutoff). ingest_with_config_opts also calls
SqliteStore::prune_pdf_ocr_events(retention_days) at ingest start so
the SQLite mirror tracks the same retention window.

Backward compat (AC-9): both new fields use #[serde(default = ...)],
so a pre-v0.20.x config with only [logging] ingest_log_enabled +
ingest_log_dir parses unchanged. kebab init writes the new defaults
automatically via Config::default() -> toml::to_string_pretty (AC-12).

docs/SMOKE.md config example synced.

Closure r1 F5: explicit OR-on-stale comment inside cleanup_old_logs.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 06:17:47 +00:00

94 lines
4.6 KiB
TOML

[package]
name = "kebab-app"
version = { workspace = true }
edition = { workspace = true }
rust-version = { workspace = true }
license = { workspace = true }
repository = { workspace = true }
description = "Facade — orchestrates components for kb-cli/tui/desktop"
[dependencies]
kebab-core = { path = "../kebab-core" }
kebab-config = { path = "../kebab-config" }
kebab-source-fs = { path = "../kebab-source-fs" }
kebab-parse-md = { path = "../kebab-parse-md" }
kebab-chunk = { path = "../kebab-chunk" }
kebab-store-sqlite = { path = "../kebab-store-sqlite" }
kebab-store-vector = { path = "../kebab-store-vector" }
kebab-search = { path = "../kebab-search" }
kebab-embed = { path = "../kebab-embed" }
kebab-embed-local = { path = "../kebab-embed-local" }
kebab-llm = { path = "../kebab-llm" }
kebab-llm-local = { path = "../kebab-llm-local" }
kebab-rag = { path = "../kebab-rag" }
# p9-fb-41 PR-9c-2: facade construction of OnnxNliVerifier when
# `[rag] nli_threshold > 0`. Trait-only consumption via kebab-rag's
# `with_verifier`; no kebab-nli internals leak into kebab-app code
# beyond the construction site in `open_with_config`.
kebab-nli = { path = "../kebab-nli" }
# P6-4: image extractor + OCR + caption adapters live here. App
# threads them into the per-asset dispatch (see `ingest_one_asset`
# image branch). Trait-only consumption — no `kebab-parse-image`
# internals leak into kb-app code.
kebab-parse-image = { path = "../kebab-parse-image" }
# P7-3: PDF text extractor lives here. App threads it into the
# per-asset dispatch (see `ingest_one_asset` PDF branch) and runs the
# resulting `CanonicalDocument` through `kebab-chunk::PdfPageV1Chunker`.
kebab-parse-pdf = { path = "../kebab-parse-pdf" }
lopdf = { workspace = true }
# Enhancement 1 (v0.20.x r2): JPEG dimension decode in pdf_ocr_apply.rs.
# jpeg feature added explicitly (F3 closure-r1) rather than relying on
# feature unification via kebab-parse-image.
image = { version = "0.25", default-features = false, features = ["png", "jpeg"] }
# p10-1A-2: Rust AST extractor lives here. App threads it into the
# per-asset dispatch (see `ingest_one_asset` Code branch) and runs the
# resulting `CanonicalDocument` through `kebab-chunk::CodeRustAstV1Chunker`.
kebab-parse-code = { path = "../kebab-parse-code" }
anyhow = { workspace = true }
blake3 = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
time = { workspace = true }
uuid = { workspace = true }
tracing = { workspace = true }
tracing-subscriber = { version = "0.3", features = ["env-filter", "fmt", "json"] }
tracing-appender = "0.2"
toml = "0.8"
dirs = "5"
# p9-fb-19: in-process LRU cache for `App::search`. Capacity from
# `config.search.cache_capacity` (default 256, ~1.3 MB cap).
lru = { workspace = true }
# p9-fb-19: NFKC-normalize cache-key queries so `"Foo"` / `"FOO"` /
# `" foo "` collapse to one entry. Same crate kebab-normalize +
# kebab-core already use, no version drift.
unicode-normalization = "0.1"
# p9-fb-31: GitignoreBuilder for .kebabignore matching in ingest_file_with_config.
# Same version as kebab-source-fs (0.4) to avoid duplicate dep versions.
ignore = "0.4"
# p9-fb-34: opaque pagination cursor encodes payload as base64.
base64 = { workspace = true }
# Enhancement 3 (v0.20.x r2): direct SQL queries for inspect_ocr_stats/failures.
rusqlite = { workspace = true }
[dev-dependencies]
rusqlite = { workspace = true }
filetime = "0.2"
tempfile = { workspace = true }
# Image-pipeline integration tests use wiremock to stub Ollama for OCR
# / caption HTTP calls. Async runtime to host the mock server only;
# the kb-app code under test stays sync.
wiremock = { workspace = true }
tokio = { workspace = true, features = ["rt-multi-thread"] }
image = { version = "0.25", default-features = false, features = ["png", "jpeg"] }
# P7-3 PDF integration tests build in-memory PDF fixtures via the same
# lopdf builder pattern `kebab-parse-pdf::tests::common` uses; pinned
# to the same major (0.32) so byte output is identical between the two
# fixture surfaces.
lopdf = { workspace = true }
# error_wire::tests::llm_unreachable_classifies_to_model_unreachable needs a real
# reqwest::Error (private constructor) — built from a connect-refused call.
reqwest = { version = "0.12", default-features = false, features = ["blocking", "rustls-tls"] }
[lints]
workspace = true