Port 11433 serves nothing; Qwen3-Reranker-4B is on 11455. Qwen3.6 spends
its budget reasoning before it answers, and its 131072 window leaves ample
input space at 32768.
The skill assumed the Logfire MCP is loaded. It is not loaded in every
session, which left no way to inspect a run at all. Document the HTTP query
API as the fallback, including the mandatory min_timestamp, the API keys
replacing read tokens, and the project-scoping trap: a key for the wrong
project authenticates and returns zero rows rather than erroring.
Also record three things that produced wrong readings in practice:
assertions/scores/metrics are keys inside the attributes column rather than
columns, one exception is emitted once per span level so failures must be
counted at case level, and assertion_pass_rate drops unjudged cases from its
denominator so judged and floor rates have to be quoted together.
Add a section for monitoring a run that is still in flight, since an eval
prints nothing until it finishes: case-span progress, the serial-execution
check that makes an ETA valid, and the per-case diagnostic attributes.
Vendor the query helper next to the skill so it does not point at a path
outside the repo, and derive its region from the key prefix.
`Agent.from_spec` raised `TypeError` on `RAGCapability` and `AnalysisCapability`,
whose constructors take a state class, packaged instruction text and a tool-name
set, and silently omitted both from the generated spec schema. The two
zero-configuration capabilities constructed but with `id=None`, so pydantic-ai's
duplicate-id rejection no longer held and a spec could register two citation
policies, defeating the single-decision-maker invariant.
Override `from_spec` on all four, delegating to `create_capability()` so ids and
instructions come from one place. The spec surface is `db_path`, `config`,
`defer_loading`, `request_limit` and `vision`; a live `HaikuRAG` client stays out
of it, and a `config` mapping is validated through `AppConfig`.
The documented `HaikuRAG("knowledge.lancedb")` and `rag(db_path="my.lancedb")`
forms both raised `AttributeError: 'str' object has no attribute 'exists'`.
`Store.__init__` assigned its argument to a `Path`-annotated attribute without
coercing, and `resolve_db_path` returned a non-None argument unchanged. Every
runnable example wraps the path in `Path(...)`, which is why it survived.
Coerce in `Store.__init__` and `resolve_db_path`; widen the annotations on
`Store`, `HaikuRAG` and both `create_capability` factories to accept `str`.
urlparse().path keeps the leading slash in front of a Windows drive, so
file:///C:/docs/a.pdf read as \C:\docs\a.pdf and the ingester reported
"File does not exist" for every file it discovered. url2pathname is the
stdlib conversion that strips it, per platform.
Four sites each decided both "is this local" and "what path is this":
FSSource._uri_to_path and supports, resolve_adhoc_fetcher,
create_document_from_source and check_source_accessible, and convert.
is_local_uri and uri_to_path in haiku.rag.uri own those two decisions now,
which closes two more cases of the same root cause. A bare C:\docs\a.pdf
parses with scheme "c", so add-src raised "No source adapter for URI scheme
'c'" and convert silently treated the path as raw text. And convert and
check_source_accessible never percent-decoded at all, so a file named
a[b] c.md read as missing on Linux and macOS too.
A file URI's host is reattached after conversion rather than passed to
url2pathname, which as of 3.14 rejects a non-local authority off Windows.
file:////server/share is the empty-authority spelling of a UNC path, its
host being the first path segment, so that host is normalised into the
authority before conversion. Output is identical on 3.12, 3.13 and 3.14.
The ad-hoc FS fetcher roots at the path's own anchor rather than "/", which
on Windows is only the current drive.
test_uri.py runs on ubuntu, macos and windows across 3.13 and 3.14 without
the project installed: --noconftest because the repo conftest imports
dependencies that job does not need, and -o addopts= to drop the
repository's -n auto. The Windows legs are what cover the drive conversion.
Fixes#574.
Sixty-three comments said what the next statement already said: # Connect to
LanceDB above connect_lancedb, # Path object above isinstance(source, Path),
# Get page numbers from provenance above the prov loop, # Clear and populate
results above list_view.clear(). They cost a read and carry nothing.
The line is whether a comment restates one statement or labels a phase. Phase
labels stay: the migrations keep # Create staging table with new schema and
# Copy from staging to final table in batches, each heading ten lines of a
long procedure. So do comments carrying a fact the code cannot: the
merge_insert update-only note on document_meta, why the poller builds sources
eagerly, why create_document_from_source returns a list for directories, that
indexes need training data, the field-group markers in the config models, and
the file:// URL-encoding note in create_document_from_source.
capabilities/ is untouched. Its docstrings sit next to prompt surface, and
changing them needs an eval to back it.
The cassette-recording docs were wrong three ways. They named
tests/test_qa.py::test_qa_anthropic, which no longer exists; they targeted
whole modules, so a rewrite would re-record cassettes for services the
recorder is not running; and they used COHERE_API_KEY where the SDK reads
CO_API_KEY. docs/development.md now names exact tests with -n0, and the keyed
example is test_cohere_reranker, which owns the one cassette recording
api.cohere.com.
overview.md repeated the landing page: the same install-and-ask block and
five of six identical links. It was positioning prose, where the docs had no
page describing how the system works.
Rewrite it as Architecture, following the data through: source adapter,
converter, chunker, embedder, transaction; then storage and its versioning;
then retrieval, with the 10x rerank fetch and section-bounded expansion; then
the two capabilities; then laptop versus ingester. Retitled in the nav and on
the landing page, filename kept so existing links resolve.
Extras were listed in three places and none was complete.
docs/installation.md now carries a table of all fifteen slim extras, what each
provides, and which the full package already includes.
haiku_rag_slim/README.md names them and links there. The claim that other
providers need their own pydantic-ai extra was wrong: haiku.rag-slim defines
anthropic, google, groq, mistral, bedrock and vertexai itself.
configuration/storage.md opens with the four operational constraints, which
were either buried in an S3 section or undocumented: one writer per URI,
reader lag by read_consistency_interval_seconds, migrate after a
schema-changing upgrade, and the fixed embedding dimension with what
ConfigMismatchError means and which rebuild mode resolves it.
The one-writer rule is stated as a haiku.rag constraint, which is what it is:
the multi-table lock, version snapshot and rollback are process-local, so a
second writer can commit inside another's transaction and be reverted by its
rollback. storage.md and ingester.md both claimed it was a LanceDB property
that corrupts manifests. The S3 deployment section now links to the
constraint instead of restating it.
Get started reads index, Quickstart, Installation, Architecture. The landing
page's list was missing Installation.
At 327 lines it interleaved reading the tables, deriving the lookups every
check needs, and the bodies of ten checks. Six checks were already
functions; the rest were inline, so none of them could be read or tested
without the others around them.
Each one is now a function taking exactly what it needs:
_check_document_meta_parity, _check_orphaned_chunks, _check_orphaned_items,
_check_documents_without_items, _check_dangling_item_refs,
_check_vector_dimension, _check_unembedded_chunks, _check_picture_data,
_check_settings_row and _check_pending_migrations. run_db_checks reads the
tables, then appends results.
_document_centroids takes the vector reduction. Passing the matrix as a
parameter keeps it a local of run_db_checks, so the del before clustering
still drops the last reference — measured at 6.2 MB allocated to reduce a
102 MB matrix, no second copy. There is no snapshot object: one holding
vectors would keep the largest allocation alive past the del.
The reduction also rebound doc_ids from the document-id set to the centroid
id list halfway through the function. The centroid ids have their own name
now.
No test changes: the 80 doctor tests cover these through run_db_checks and
pass unchanged.
benchmark.py was 1220 lines holding six unrelated jobs: populating a
database, running retrieval, running QA, resolving datasets, moving
databases to and from HuggingFace, and wiring the Typer CLI.
qa.py takes both QA runners with their live summary, refusal metrics and
target resolution. population.py takes populate_db and the batched ingest.
retrieval.py takes run_retrieval_benchmark. artifacts.py takes HF_REPO_ID and
the download/upload bodies. experiment.py takes DEFAULT_JUDGE_MODEL and
build_experiment_metadata, which retrieval and QA both record.
benchmark.py keeps the CLI at 258 lines: the Typer app, config and case-id
loading, dataset resolution, evaluate_dataset, and three commands whose
bodies are now a loop over specs. The module-level side effects stay with it
— load_dotenv before configure_telemetry, so credentials and LOGFIRE_TOKEN
are in the environment before telemetry and model setup read them — so no
importable module carries one.
Test patch targets follow the code. get_model, run_capability_question,
run_capability_conversation, set_eval_attribute and HaikuRAG are patched
inside moved code, so they move with it; run_qa_benchmark,
run_retrieval_benchmark and find_config_file stay patchable on
evaluations.benchmark because evaluate_dataset and _load_config still look
them up there.
One assertion got stronger: a QA test patched benchmark.HaikuRAG to prove the
QA path does not open its own client. qa.py has no HaikuRAG reference at all
now, so the test asserts that instead.
cli.py carried 40 pragmas over whole command bodies and app.py a
class-level one over all 412 statements, while tests/test_cli.py already
drove 29 commands through CliRunner. The pragmas hid lines the suite
executed, so the 100% gate understated real coverage and gave new CLI code
no scrutiny.
Both are measured now. 38 CLI tests stub HaikuRAGApp and assert the parsed
arguments reach the right method; 60 app tests stub the client and record
the console, pinning what each command asks for and what it prints. The only
pragma left in either file is cli() under __main__. The omit list is back to
the two Textual TUIs.
Three defects the coverage surfaced:
haiku-rag settings masked only top-level secret-named fields, so nested ones
printed in full — lancedb.api_key, providers.docling_serve.api_key, WebDAV
source passwords. It uses redact_secrets, which walks the dump.
chat guarded the wrong thing: haiku.rag.chat imports without Textual, and
run_chat raises when it imports ChatApp, so the missing extra escaped as an
ImportError. The guard is on the call. inspector raises at module import
instead, so inspect keeps its guard on the import; each has a test that
fails the way the real installation fails.
search --limit/--search-type and history --limit default to None so the
config resolves the default. Now pinned.
CI passed --cov=haiku while pyproject declares source = ["haiku_rag_slim"];
pass --cov and let the config decide. build-docs.yml only ran on push to
main, so a broken docs build merged and failed at deploy: build on pull
requests, with configure-pages, upload-pages-artifact and deploy gated to
push, and a per-ref concurrency group.
engine.py held four unrelated things: what the tables are, how to open a
connection, how to read a database's state, and the Store that coordinates
writes. At 1240 lines the Store's own concerns — locks, migrations, vacuum,
tags — were hard to find among them.
Table records, Arrow schemas, index_specs, ensure_indexes, REQUIRED_TABLES
and query_to_pydantic move to store/schema.py, which imports nothing from
haiku.rag: it describes the tables and never opens or mutates one.
gather_database_info, get_database_stats, DatabaseInfo and its result models
move to store/info.py. Nothing in Store calls them — they are read paths for
the CLI, doctor, inspector and ingester API — so info depends on engine and
not the reverse.
engine.py keeps the Store, ConnectionMode, connect_lancedb, the tag helpers
and the restore-order and retention constants. No re-exports: importers
point at the new modules.
test_app_info_uses_connect_lancedb_for_remote patched
haiku.rag.store.engine.connect_lancedb; gather_database_info now binds that
name in info.py, so the patch targets where the call is looked up.
haiku.rag.ingester.sources was never ingester-only: one-shot client
ingestion resolves adapters through it (create_document_from_source), and
convert() now fetches through HTTPSource, so the core client imported into
the ingester package to reach them.
Move the package to haiku.rag.sources and update every import. No shims:
haiku.rag.ingester.sources is gone.
The haiku.rag.sources plugin entry-point group is unchanged, so third-party
source packages need no edit — the group name now matches the module path it
always implied.
Source unit tests move to tests/sources/. test_source_plugins.py stays in
tests/ingester/: it drives a PeriodicPoller against the job repo, so it is
plugin wiring through ingester machinery rather than a source test.
Five call sites repeated the same post-conversion preparation: store the
Docling representation and resolve a title when none was supplied.
_prepare_and_title now owns that sequence. update_document continues to
call _prepare_document_from_docling directly because an explicit update
must preserve an existing empty title.
create_document, both content-replacement branches of update_document,
and source ingestion embedded eagerly before passing chunks to a
persistence funnel that checked them again. The funnels now own
embedding, including the checks required by import_document and
import_documents for caller-supplied chunks.
Move the document.embed span into ensure_chunks_embedded after its early
return. Every path that performs embedding is now instrumented, while
operations whose chunks are already embedded emit no span.
convert() previously used its own HTTP client and temporary-file path.
Route URL conversion through HTTPSource, matching source ingestion, and
move _write_fetch_body to processing.py so both paths share temporary
file handling without an import cycle.
Add walk_files for filesystem enumeration and use it from both
FSSource.discover and one-shot directory ingestion. Symlink escape
filtering now has one implementation.
RAGState and AnalysisState each declared the same five fields, so the generic
base could not name them: StateT was bound to BaseModel, and every access
went through cast(Any, state), a getattr by string, or a loop clearing fields
by name so it could skip the one only AnalysisState has.
EvidenceState declares them once. RAGState adds nothing, AnalysisState adds
executions and overrides begin_invocation to clear them. StateT binds to
EvidenceState, which removes all ten casts and both state-shape getattrs; the
three getattr(ctx.deps, "state") probes stay, since those check a
host-supplied object rather than our own state.
discover_evidence reached into capability.state for two fields. It now asks
through evidence_record() and citation_index(), alongside the
evidence_tool_names() and cite_available accessors it already used. The eval
runner's _RagLikeState protocol and the chat app's getattr reads described
this shape from outside and are gone.
Compatibility is semantic JSON-object equivalence, not bytes: field names and
nesting are unchanged, so a dict stored by 0.75.0 loads and re-dumps equal,
but deriving from a shared base reorders AnalysisState's keys. Nothing
serializes, hashes or string-compares this state — every carry point
re-validates by key.
The 0.75.0 section was closed after the branch behind #558 was cut, and
every entry since anchored itself to a marker line inside it, so fifteen
entries for unreleased work were filed under a released version: the three
correctness fixes from #558, write_transaction from #559, the Config removal
from #560, the strict-config group from #561, and this PR's four
documentation fixes.
0.75.0 keeps only what it shipped.
search.limit was documented as 10 in three places while the default is 5.
The documented way to disable reranking, provider: "", is a valid
ModelConfig, so it raised "Unknown reranking provider" — disabling means
omitting reranking.model or setting it to null. The inline provider list
named four of the six rerankers. prompts.picture_description: null fails
validation, since the field is a non-optional str.
storage.data_dir: "" coerced to Path("") — the working directory — while two
doc pages promise the platform default and soliplex's example config relies
on it. Empty or whitespace now resolves to the platform directory; an
explicit "." is still honoured, so a config that wants the working directory
says so.
Three tests keep this from drifting again: every fenced yaml block in the
docs validates against AppConfig, every value in the complete example either
equals its default or is listed as a deliberate deviation, and empty
data_dir resolves to the platform default.
init-config's test reimplemented the command body instead of invoking it,
which is why the command carried a coverage pragma. It now goes through
CliRunner, with the refuse-to-overwrite guard covered too.
Every section inherited plain BaseModel, so unknown keys were dropped
silently: providers.docling_serve.timeout was documented for months while
being ignored, and a typo in any setting took the default. Sections now
derive from ConfigModel, which forbids extras, so a stale or misspelled key
fails with its path. This already found search.context_radius in a live app
config and providers.vllm in soliplex's example.
converter, chunker and chunker_type are Literals. Sizes, limits,
dimensions, token budgets, attempt counts and breaker thresholds must be
positive; retention, delays, intervals and cooldowns non-negative;
similarity_threshold within 0-1; port within 0-65535. port 0 keeps its
OS-assigned meaning and worker_count allows 0 for an API-and-reaper-only
process.
get_reranker caught ImportError and returned None, so a configured reranker
whose extra was missing silently disappeared. It now propagates.
raise_missing_extra names the install command and re-raises when the failure
came from inside an installed package, so a broken transitive import is not
reported as a missing one. zeroentropy imported bare and now guards like the
others.
The haiku.rag package declares the jina extra. jina-local already worked
there through cross-encoder's transitive transformers and torch; the
resolved package set is unchanged, but the support is now promised rather
than inherited.
Provider fields stay unconstrained: get_model ends in a pass-through to
pydantic-ai for any provider it supports, so a Literal there would reject
valid configurations.
haiku.rag.config exported two configuration instances: the lazy _config
behind get_config/set_config, and Config, loaded at import time. Nothing
linked them, and eleven signatures captured Config as a default argument,
so set_config could not reach the factories, the client, the store or the
MCP server. reranking/base.py went further and snapshotted the configured
reranker name into a class attribute at import.
Config is removed. Internal defaults are config: AppConfig | None = None,
resolved through get_config() per call. RerankerBase._model is None and
CohereReranker takes its model name as an argument, like every other
reranker.
The suite patched attributes on Config while production read the instance
get_config() returns, a different object, so those patches were no-ops
waiting to happen. They now go through get_config().
