- 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>
JOIN documents.updated_at. stale defaults to false; App facade
post-processes against config threshold.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Domain field additions for p9-fb-32. Wire serialization is
automatic via serde rfc3339. Other crates fail to compile until
they populate the new fields — fixed in subsequent tasks.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
set_draw_target switching broke cursor positioning: each hidden→stderr
restore caused indicatif to draw a fresh line instead of overwriting.
Root fix: call only set_position() in TTY AssetStarted (one draw per
file). Filename visible in non-TTY plain-line output.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
set_position() and set_message() each call update_and_draw()
independently, producing two scrollback lines per file in TTY mode.
Suppress the draw target before the two updates, restore to stderr,
then call tick() to emit exactly one frame.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
dirs::config_dir() and dirs::data_dir() both return ~/Library/Application Support
on macOS, so data_dir == config parent dir. ResetScope::DataOnly removes data_dir
and silently deletes config.toml along with it.
Fix: bypass dirs crate fallback for config/data/cache dirs; use
$HOME/.config, $HOME/.local/share, $HOME/.cache directly (XDG standard).
xdg_state_dir already used this pattern. dirs::home_dir() still used for
portability.
Migration: Config::load(None) auto-copies legacy ~/Library/Application
Support/kebab/config.toml to the new ~/.config/kebab/ on first run and
prints a migration notice to stderr.
AssetStarted now advances position (idx-1) and sets message together.
AssetFinished no longer updates the bar — Completed handles final
cleanup via finish_and_clear. Result: one bar frame per file instead
of two, eliminating the scrollback duplicate-line artifact.
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>
- ingest_file_with_config: lowercase normalize ext (caller-side) +
early error on unsupported extension (`.docx` etc. now Err with
helpful message instead of silent skipped_by_extension counter).
New test ingest_file_errors_on_unsupported_extension.
- ingest_stdin_with_config: doc comment explaining intentional
double-call of ensure helpers (idempotent + ~ms negligible).
- external::inject_frontmatter: simplify precheck via single
trim_start binding + add CR-only line ending edge case.
- external::inject_frontmatter: doc note on yaml_quote escape
contract (agent-supplied titles with special chars are safe).
Round 1 review summary: #111 (comment)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- kebab-app: add #[doc(hidden)] to ingest_stdin_with_config (CLAUDE.md
convention — all *_with_config functions should have this attribute;
fb-31's first impl missed it on the second facade fn).
- SKILL.md: "Since v0.4.0" → "Since v0.3.1" (MCP shipped in fb-30
release v0.3.1; the wrong version claim was introduced in fb-30 doc
sync and carried forward into fb-31).
- tools_call_ingest_file: add idempotency test (second call with same
content → unchanged=1, new=0). Spec called for two tests; first impl
shipped only the happy path.
Version bump 0.3.1 → 0.3.2 deferred to separate `chore/bump-v0.3.2` PR
mirroring fb-27 + fb-30 precedent (commits 73f5d73 / 5495d96).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
fb-31 added ingest_file + ingest_stdin MCP tools (Task 9) but the
spawn-based smoke test in cli_mcp_smoke.rs still asserted the fb-30
count of 4. Bump to 6 to match the live tools/list response.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5th + 6th MCP tools — first mutation surface (fb-30 v1 was read-only).
Both wrap the new kebab-app facade fns + use spawn_blocking via the
existing spawn_tool helper. tools/list now returns 6 tools.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wraps body with YAML frontmatter (title + source_uri) via
crate::external::inject_frontmatter, writes to
_external/<hash12>.md, delegates to ingest_file_with_config. Markdown
only in v1.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three scenarios — copies external md + reports new=1, idempotent on
second call (unchanged=1), errors on missing path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Single-file ingest entry. Copies bytes to _external/<hash12>.<ext>
via crate::external::copy_to_external, runs the per-medium pipeline on
that single asset (reuses ingest_with_config_opts via a SourceScope
{ root: _external/, include: [<filename>], exclude:
config.workspace.exclude }).
`.kebabignore` matches log a stderr warn line and proceed (explicit
ingest is bypass intent). Internal helper `check_kebabignore_match`
uses the `ignore` crate's GitignoreBuilder.
Returns the standard IngestReport (incremental ingest from fb-23
handles re-ingest as `unchanged`).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Final review fixes:
- docs/ARCHITECTURE.md: add kebab-mcp to UI subgraph + directory tree
(CLAUDE.md "add new crate" rule required this; missed in Task 12 doc sync).
- state.rs: replace forward-reference Task 10 comment with current-state
doc (config_path now wired by Task 10 commit 4a30959).
- tools_call_schema.rs: assert capabilities.mcp_server == true (already
pinned in schema_report + cli_schema, this closes the gap in mcp's own
test).
Version bump 0.3.0 → 0.4.0 deferred to separate `chore/bump-v0.4.0` PR
mirroring fb-27 precedent (commit 73f5d73 / PR #105).
Co-Authored-By: Claude Opus 4.7 (1M context) <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>
Approach: extracted `pub fn build_tools_vec() -> Vec<Tool>` from the
inline `list_tools` trait impl body — `RequestContext<RoleServer>` is
non-constructible from outside rmcp (Peer::new is pub(crate)), so a
direct trait-method call was not viable without an in-memory transport
rmcp 1.6 does not expose. The helper is the single source of truth;
`list_tools` now delegates to it.
Three test cases in tests/tools_list.rs:
- 4 tools present with correct names
- search inputSchema has "required": ["query"]
- schema/doctor tools accept empty input (type=object, no required)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Task 8 commit f9a1548 added `schema_version: String` as required field on
ErrorV1 (so kebab-mcp's direct serialize-then-emit path produces correct
error.v1 wire). The wire.rs ErrorV1 literal in the
error_wrapper_tags_schema_version_and_emits_code test was missed —
breaks kebab-cli build. Add the field to the test fixture.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds integration test schema_tool_emits_error_v1_when_db_missing that
verifies NotIndexed errors are emitted as error.v1 JSON with isError=true.
Also fixes ErrorV1 struct to include required schema_version field per
error.v1 wire contract (docs/wire-schema/v1/error.schema.json).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two issues from Task 7 review:
1. CRITICAL — call_tool "ask" arm called blocking ask handle from async
context. OllamaLanguageModel::new builds reqwest::blocking::Client
which creates+drops a tokio runtime → panic inside async. Fix:
tokio::task::spawn_blocking wrap. Also applied preemptively to
"search" arm (SqliteStore + Lance open are blocking IO too).
2. IMPORTANT — ask tool's retrieval mode hardcoded to Lexical (test
workaround for provider="none"); CLI default is Hybrid. Fix: add
`mode: Option<String>` field to AskInput, default Hybrid in handle,
test passes mode=Some("lexical") explicitly to keep test functional
on provider="none".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Fourth (and final v1) tool — `ask` (input: query / optional session_id).
Multi-turn via optional session_id (kebab_app::ask_with_session_with_config),
single-shot via ask_with_config when None. Refusal (grounded:false) NOT
mapped to isError — agent branches on the wire payload's grounded flag.
AskOpts has no Default impl (must construct manually). Answer carries no
schema_version field (tagged inline via entry().or_insert_with, idempotent).
Mode defaulted to Lexical: reqwest::blocking::Client::build creates and
drops a tokio runtime, panicking inside async context — the empty-corpus
refusal test avoids this via spawn_blocking; the tool itself uses Lexical
as the default mode since MCP callers typically run without an embedding
provider configured.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Third tool — `search` (input: query / mode / k). First tool with
non-empty input — establishes the pattern: SearchInput struct with
JsonSchema derive + Tool::new uses
rmcp::handler::server::common::schema_for_type::<SearchInput>() for
inputSchema + call_tool match arm parses request.arguments via
serde_json::from_value.
search_with_config takes owned Config, so state.config (Arc<Config>)
is cloned via (*state.config).clone(). Output: search_hit.v1 array —
SearchHit (kebab-core) does not carry schema_version field, so each
element is tagged inline before serialising.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Second tool — `doctor` (no input args, returns doctor.v1 JSON via
kebab_app::doctor_with_config_path). Mirrors schema tool's manual-dispatch
pattern: Tool::new entry in list_tools, match arm in call_tool, per-tool
module in tools/doctor.rs.
doctor_with_config_path takes Option<&Path> (not &Config), so KebabAppState
is extended with config_path: Option<PathBuf>. All existing callers
(initialize.rs, tools_call_schema.rs, serve_stdio_async) pass None for now;
Plan Task 10 (Cmd::Mcp wiring) will thread the actual --config path through.
doctor_with_config falls back to XDG default when config_path is None —
same behavior as bare `kebab doctor`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First tool wired — `schema` (no input args, returns schema.v1 JSON
mirroring `kebab schema --json`). Establishes the per-tool module
pattern (crates/kebab-mcp/src/tools/<name>.rs) + error helper that maps
anyhow::Error to MCP CallToolResult.error with error.v1 content.
Dispatch pattern: manual dispatch — explicit `list_tools` + `call_tool`
overrides on `impl ServerHandler for KebabHandler` with a
`match request.name.as_ref()` arm per tool. No proc-macro magic.
Tasks 5-7 should add a new arm + new tools/<name>.rs following the same
pattern; also add a `Tool::new(...)` entry in `list_tools`.
API shapes confirmed from rmcp 1.6 source:
- Content = Annotated<RawContent>; text via `Content::text(s)`; pattern
match via `&content.raw` → `RawContent::Text(t)` → `t.text`
- CallToolResult::success(Vec<Content>) / ::error(Vec<Content>)
- ListToolsResult::with_all_items(Vec<Tool>)
- schema_for_empty_input() from rmcp::handler::server::common
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
