OCR is the paid, opt-in tier (DOCUMENT_OCR_ENABLED, default off). The per-tier
escalation gate already declines to hop to OCR when it's disabled (the pre-OCR
tier is terminal — no surprise cost), but that left operators blind to how much
OCR demand exists.
evaluate_escalation now returns a structured EscalationDecision:
- "hop" — a higher tier can run; the caller raises EscalateError (queue-hop).
- "suppressed" — the ideal next tier (e.g. ocr) exists but is DISABLED; the caller
indexes the current tier's output as terminal and records the
would-be hop on the new astrolabe_document_escalation_suppressed_total
{from_tier,to_tier,reason} counter instead of hopping.
- None — index as-is (good text, or no such tier at all).
So with OCR off, escalation_suppressed_total{to_tier="ocr"} is the latent OCR
demand an operator weighs before enabling OCR; enabling it converts these into
real document_escalation_total{to_tier="ocr"} hops. next_available_tier gains an
ignore_enabled flag to compute the *ideal* (enabled-gate-ignored) target.
Tests: registry suppressed vs hop vs terminal (incl. structured-hop-not-suppressed
when OCR off but structured available); _parse_pdf_tier records suppressed +
indexes without raising.
Deck #324 (parent #323).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- metrics: update_ingest_queue_depth now pre-zeroes every managed ingest queue
before applying live counts, so a queue that drains to empty (and drops out of
procrastinate's list_queues_async) reads 0 instead of sticking at its last
non-zero value (ghost backlog in Grafana/alerts). Adds a regression test.
- procrastinate: comment that _is_transient_infra_error treats all qdrant errors
as transient deliberately (bounded same-tier retry; over-broad is acceptable).
- escalation: note next_tier is the building block; production routing uses
ProcessorRegistry.next_available_tier.
- tests: add evaluate_escalation fast+ocr-only low-confidence -> ocr case.
Deck #323.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Register the periodic stalled-job reclaim on a dedicated ingest-maintenance
queue that every worker drains (any --tier), so reclaim still fires when the
fast fleet is scaled to zero and only ocr workers run. procrastinate's
periodic-defer dedup keeps it single-run across drainers.
- escalation: mark `unsupported`/`forced` reason labels as reserved (not raised).
- processor: note that options/progress_callback are intentionally not threaded
through _parse_pdf_tier yet (symmetric with the inline path).
- tests: assert TieredEscalationStrategy backoff progression (4/8/16/…/300s);
cover get_ingest_pending per-queue aggregation + the legacy job_counts
fallback; add an external-path zero-page no-escalation case; use the canonical
INGEST_QUEUE_FAST instead of the back-compat alias.
Deck #323.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Split external (procrastinate) document processing into per-tier queues so a
document is attempted at most once per tier and requeued to the next tier's
queue on a low-quality parse, using procrastinate's native retry.
- escalation.py: TIER_LADDER (fast->structured->ocr) + EscalateError signal
- registry: process_tier (one tier) + evaluate_escalation post-parse gate
(reuses classify_from_text) + next_available_tier; shared _classify_result
and _oversize_result with the inline pipeline
- processor: process_document(tier=...) runs one tier and raises EscalateError
before embed (junk text never indexed); inline memory path unchanged
- queue/procrastinate: ingest-fast|structured|ocr queues; TieredEscalationStrategy
(queue-hop on EscalateError, bounded same-tier transient retry); queue-aware
task; producer defers to ingest-fast; per-queue counts + all-queue reclaim
- cli: worker --tier {fast,structured,ocr}
- billing: pages_ocr usage event + pipeline_tier metadata (paid OCR billed apart)
- observability: astrolabe_ingest_queue_depth{queue,status} gauge + per-queue
counts in nc_get_vector_sync_status / management status endpoint
- config: INGEST_ESCALATION_ENABLED (default true), INGEST_TRANSIENT_MAX_ATTEMPTS
INGEST_ESCALATION_ENABLED=false and INGEST_QUEUE=memory preserve prior behaviour.
Deck #323.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-1 review nits. The constant now only gates the diagnostic `image_heavy`
flag (not routing), so the old name was misleading. Rename + reword its comment
to state the diagnostic-only intent. Also add a classify_pdf symmetry test
(`test_classify_pdf_image_heavy_clean_text_stays_fast`) pinning that a full-page
raster image with a clean text layer routes fast on the classify_pdf path too.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The tier-0 classifier escalated any page with raster-image coverage >=0.80 to
the OCR tier regardless of its text layer. On OHR-Bench this drove ~45% of all
OCR escalations: clean born-digital pages dominated by a figure, and scanned
pages that already carry a usable OCR text layer -- re-OCR adds nothing for
either, but each one was routed to the paid tier-3 OCR.
Route on the text signals only (near-empty or junk-quality layer). Image
coverage is still computed and still raises the `image_heavy` diagnostic flag,
but no longer routes. True scans with no/garbage text continue to escalate via
the empty-text and quality signals, so genuine OCR needs are unaffected.
Trade-off: image-only content on an otherwise-clean page (handwriting, stamps,
text inside figures) is no longer force-routed to OCR. This was previously
intentional; the escalation cost outweighed the benefit for RAG indexing.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-3 review on PR #892 found a real bug: the gateway backend's httpx.Timeout
raises httpx.ReadTimeout (a httpx.TimeoutException, NOT a builtin TimeoutError),
so the `except TimeoutError` added in r2 only covered the Mistral
(anyio.fail_after) path — gateway timeouts still fell through to
reason="error". Catch both (TimeoutError, httpx.TimeoutException) so either
backend's timeout lands in the dedicated parse_failed_reason="timeout" bucket.
Add an end-to-end test driving a gateway httpx.ReadTimeout through the
processor.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-2 review on PR #892:
- OcrProcessor.process now catches TimeoutError separately and returns
parse_failed_reason="timeout" with a populated message ("OCR timed out after
Ns"), instead of conflating timeouts with API errors under "error" and logging
an empty suffix. Lets dashboards tell a too-low timeout from a failing
provider. Test added.
- Add validator-rejection tests for DOCUMENT_OCR_TIMEOUT_SECONDS=0 (gte=1) and
DOCUMENT_MAX_PDF_SIZE_MB=-1 (gte=0), matching the existing validator-test
pattern.
- Comment the _Settings test fixture's max_pdf_size_mb=0.0 default.
SonarCloud: quality gate was failing on new_security_hotspots_reviewed (S5332
"use https") from an http:// URL in the new gateway-timeout test — switched to
https:// (mirrors commit 98c9d58e).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-1 review on PR #892:
- Wire DOCUMENT_OCR_TIMEOUT_SECONDS into _MistralOcrBackend too (was
gateway-only): wrap process_async in anyio.fail_after so the SDK-managed
client honours the setting; on expiry it fails fast as a clean parse error.
Test added.
- Tighten the misleading "honoured without a restart" comment — per-call
get_settings() is for test monkeypatching; a live change still needs a
restart since the backend is cached for the pod lifetime.
- Comment the size guard's two intentional gaps: an explicit processor_name
override bypasses it, and the early return skips the parse-duration histogram.
SonarCloud (new-code smells in the added tests):
- S1244 float-equality asserts → pytest.approx (test_config.py, test_ocr_processor.py).
- S1186/S7503: rewrite the gateway-timeout test with mocker AsyncMock/MagicMock
instead of a hand-rolled fake client (no empty method, no async-without-await).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two ingest-robustness fixes from card 309 (OHR-Bench smoke-test triage).
The OCR backend timeout was a hardcoded 180s module constant, so a tenant
whose gateway has its own shorter ceiling couldn't tune it. Promote it to
DOCUMENT_OCR_TIMEOUT_SECONDS (default 180), resolved per call via get_settings
so an override applies without a restart.
Large, awkward PDFs (e.g. a 42 MB scanned DUDE) were handed straight to the
fast/OCR tiers, where they burned the full OCR timeout for zero recovered
text. Add a pre-parse size guard in the tiered PDF pipeline: a PDF over
DOCUMENT_MAX_PDF_SIZE_MB (default 50, 0 disables) fails fast with
parse_failed_reason="oversize" before any tier runs, so the existing
permanent-failure path marks the placeholder failed and records
astrolabe_document_parse_failed_total{reason="oversize"} instead of retrying.
Both knobs go through Settings + dynaconf validators (env-var keys verified by
regression tests) and are documented under Background Indexing Configuration.
Refs: Deck board 12 card 309 (AC #3 OCR timeout + size guard).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Addresses round-1 review on #878:
- Move the eager `document_processors` imports out of the API startup graph:
`app.py` (get_registry now imported inside initialize_document_processors,
after the disabled early-return) and `vector/processor.py` (get_registry now
imported at its single use site). Importing `app` + `cli` no longer loads
`document_processors` / `_isolation` at all -- the #877 stack is fully out of
startup (pymupdf still loads via search/pdf_highlighter, a Windows-compatible
and separately-tracked concern).
- Make `tests/unit/test_pdf_parse_isolation.py` importable on Windows: guard the
top-level `import resource` with try/except and skip the three rlimit
computation tests via a `requires_resource` marker when the module is absent.
The Windows no-op / import-guard tests don't use the real module and still run.
- Fix the `# pragma: no cover` comment on the win32 branch to be accurate.
- Add `enable-cache: true` to the package-smoke setup-uv step.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
`document_processors/_isolation.py` did an unconditional module-level
`import resource`, a POSIX-only stdlib module absent on Windows. It was
pulled into the API startup path via
`server/webdav.py -> utils/document_parser -> document_processors`, so
the MCP server failed to start on Windows since 0.101.2 with
`ModuleNotFoundError: No module named 'resource'`.
- Guard the import behind `sys.platform`; bind `resource = None` on
win32. `_apply_mem_limit()` degrades to a logged no-op when the module
is unavailable (the RLIMIT_AS cap is a Linux-pod safety measure, not a
correctness requirement).
- Make the document-parser import in `server/webdav.py` lazy so server
startup never loads the ingest document stack
(document_processors -> pymupdf -> _isolation) at all -- it is only
needed when a file is actually read and parsed. This both fixes#877
and decouples the API layer from ingest-only deps.
- Add unit regressions for the no-op path and the win32 import guard.
- Add a cross-platform `package-smoke` CI job (ubuntu + windows) that
installs the package isolated and runs the CLI, exercising the
cli -> server -> webdav import chain that crashed in #877.
Fixes#877
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #863 round 4: classify_from_text's docstring now states that the
image_heavy flag (and the image-coverage trigger) are only set when
image_coverage is supplied, so the flag reads zero for tenants with
DOCUMENT_OCR_DETECT_SCANNED=false -- self-documenting the metric semantics.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #863 round 3:
- classify_from_text emits the "scanned" flag (was "no_text_layer") for the
empty-text-layer case -- same name + meaning as classify_pdf, so
astrolabe_document_classifier_flag_total isn't split across two labels for the
same concept (and matches the metric's documented vocab).
- classify_from_text logs at DEBUG when image_coverage length != the expected
min(pages, MAX_SAMPLED_PAGES), so a 1:1-alignment contract break (extractor
reorders/skips pages) surfaces instead of silently misattributing coverage.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #863 round 2:
- classify_pdf now flags a page needs_ocr on the SAME three signals as
classify_from_text (image scan OR low text-quality OR near-empty), not image
coverage alone. Previously a word-merged digital doc with no images routed
"fast" via classify_pdf but "ocr" via the pipeline -- so an operator
reproducing routing offline got a different answer. They now match.
- Add a test that when image_coverage is shorter than the page boundaries (the
MAX_SAMPLED_PAGES cap on large scans), the leading page uses the scan signal
and later pages fall back to text-quality.
Left as-is: overlong_score (>20) partially overlaps merge_score (>12) -- the
double-penalty on very-long tokens is intentional, not a bug (per review).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #863 review:
- MIN_TEXT_QUALITY 0.45 -> 0.5 so the module/diagnostic default matches the
DOCUMENT_OCR_MIN_TEXT_QUALITY setting (registry always passes the setting; this
keeps classify_pdf and the test/default path on the production threshold).
- image_coverage_per_page is bounded to MAX_SAMPLED_PAGES (the image pass is the
costly part, so a 200-page scan isn't fully rasterised on the hot path); pages
beyond the cap fall back to the text-quality signal, and page_fraction still
gates over every page.
- Extracted _page_image_coverage(page) helper, shared by classify_pdf and
image_coverage_per_page (DRY + keeps the tiling-double-count note in one place).
- Scan-detection failure logs at WARNING (not DEBUG) so a systematic failure on
an OCR-enabled tenant is visible at LOG_LEVEL=INFO.
- Add the missing DOCUMENT_OCR_MIN_PAGE_CHARS range-validator test.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The hot-path classifier escalated to OCR purely on character count, so a
scanned/handwritten PDF with a low-quality embedded text layer (>16 chars/page
but garbled) routed `fast` and indexed the junk -- e.g. Student 147.pdf's
"Little Acoms Primary"/"0110912020", which pollutes the vector and demotes the
doc in search (Deck #207).
- classifier: recalibrate `_text_quality` with a long-token-fraction term that
detects word-merging (dropped inter-word spaces) -- the dominant junk-layer
failure the old whitespace/overlong(>20) terms missed. Measured: the Student
147 scan ~0.42 (60% pages junk) vs >=0.94 for clean digital docs.
- classify_from_text now routes on quality + scan: a page is OCR-worthy if
near-empty OR low text-quality OR (when OCR + scan detection are enabled) it's
mostly a raster image. New `image_coverage_per_page` re-opens the PDF for the
scan signal, so that cost is paid only by OCR-opted-in tenants. Thresholds are
passed in from per-tenant settings (keyword-only).
- config: 4 per-tenant settings -- DOCUMENT_OCR_MIN_TEXT_QUALITY (0.5),
DOCUMENT_OCR_PAGE_FRACTION (0.5), DOCUMENT_OCR_MIN_PAGE_CHARS (16),
DOCUMENT_OCR_DETECT_SCANNED (true) -- with range validators.
- metrics: new astrolabe_document_ocr_page_fraction histogram (the value the
page-fraction threshold acts on) alongside document_text_quality, so operators
can tune the OCR escalation per tenant (quality vs cost).
Escalation gate, OCR backends, and off-by-default behavior unchanged (#858).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Follow-up to the tiered document processor (#858), landing the round-4 review
nits the reviewer approved without:
- pypdfium2_fast: free the page handle in an outer finally so a corrupt page
that makes get_textpage() raise can't orphan it.
- test: classify_from_text junk-text-layer path (non-zero chars, low quality,
high ocr_frac) flags bad_text_layer -- the hot-path coverage gap.
- test: build_ocr_backend raises ValueError when the gateway M2M client_id is
set without its token_url/secret.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #858 review round 3:
- document_tier1_engine / document_ocr_provider now validate + normalize via
Settings.__post_init__ _enum_fields (the repo's canonical opt-in-enum pattern;
case-insensitive) instead of dynaconf Validators. A typo now raises ValueError
at load and "Gateway" normalizes to "gateway".
- classify_from_text gates no_text_layer/bad_text_layer on ocr_frac >=
OCR_PAGE_FRACTION, matching classify_pdf -- a "fast"-routed doc with a few junk
pages no longer emits a misleading flag (keeps the shadow vs hot-path
classification metrics consistent).
- build_ocr_backend warns when an EXPLICIT provider is misconfigured
(gateway without EMBEDDING_GATEWAY_URL, mistral without MISTRAL_API_KEY)
instead of silently returning None.
- Pypdfium2FastProcessor.health_check probes the import; documented why
OcrProcessor.health_check is unconditionally True (lazy per-tenant backends).
- Removed the leftover per-boundary / per-chunk debug logging loops.
Tests: enum normalization + rejection for the two new settings.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #858 review round 2:
- OcrProcessor backend resolution is now guarded by an anyio.Lock (lazy-init,
double-checked) so a burst of concurrent first-OCR calls resolves the backend
once instead of each fetching its own gateway M2M token.
- The document_tier1_engine=pymupdf rollback now logs a warning when it falls
back to the fast processor (no 'structured' registered) instead of silently
using the very engine the operator opted out of.
- classify_from_text defaults ocr_frac to 0.0 (not 1.0) for a zero-page PDF, so
the recorded classification metric is "fast" (no OCR evidence) rather than a
misleading "ocr"; the no_text_layer/bad_text_layer flags are gated on having
sampled at least one page.
New tests: zero-page classify routes fast, rollback-fallback warning.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #858 review:
- 🔴 OcrProcessor now resolves its backend once and reuses it. Rebuilding per
call created a fresh GatewayTokenProvider each time -- discarding its M2M-token
cache, so every OCR'd document fetched a new token -- and a new Mistral client.
- 🔴 build_ocr_backend uses explicit ValueError (not assert, which is stripped
under `python -O`) for the gateway M2M triple.
- PIPELINE_TIER in the Qdrant payload now reflects the tier that actually
produced the doc: the registry stamps result.metadata["pipeline_tier"] and the
processor reads it (was hardcoded "fast", wrong for OCR/structured).
- Escalation now requires classification.page_count > 0, so a zero-page
(empty/corrupt) PDF isn't pointlessly sent to OCR; documented that a fast
FAILURE (encrypted/unopenable) is a hard failure and is not OCR-escalated.
- Documented the OCR page_boundaries separator-attribution choice.
- Downgraded the per-document page-boundary / page-assignment INFO logs to debug.
New tests: zero-page no-escalation, pipeline_tier stamping.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
OCR is an enhancement, not a gate. Previously, escalating a scanned doc to the
OCR tier returned the OCR result unconditionally -- so with DOCUMENT_OCR_ENABLED
=true but no backend configured (no gateway URL / no MISTRAL_API_KEY) the OCR
processor returned success=False and the whole document was marked failed and
skipped: strictly worse than leaving OCR off (where it would at least index the
tier-1 text).
Now the registry keeps the tier-1 fast result when the OCR escalation doesn't
succeed (no backend, API down, empty output), logging a warning. A
misconfiguration degrades gracefully instead of dropping scanned docs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the OCR escalation target the tiered registry already routes to. Scanned /
no-text-layer PDFs (the tier-0 "ocr" verdict) escalate here when
document_ocr_enabled (default off).
Two interchangeable backends, selected by document_ocr_provider
(auto | gateway | mistral | none):
- gateway: POST to the Astrolabe Cloud model gateway's /v1/ocr -- the same
M2M-authenticated gateway as embeddings, so NO provider keys live in the pod
(the platform default; reuses EMBEDDING_GATEWAY_URL + the M2M creds).
- mistral: call the Mistral OCR API directly from the pod (MISTRAL_API_KEY), for
self-hosters / deployments without the gateway.
"auto" prefers the gateway, then direct Mistral.
Both return per-page markdown joined into text + exact page_boundaries (the
pdf_highlighter contract; bbox re-derived from the PDF bytes as for other tiers).
Validated end-to-end via direct Mistral on the scanned Student 147.pdf:
success, 15 pages, 22k chars, offsets exact, ~4s.
Settings: document_ocr_provider (enum-validated), document_ocr_model
("mistral/mistral-ocr-latest" -- gateway routes on the prefix, the direct mistral
backend strips it). OcrProcessor registered at lowest priority so it is never the
non-tiered default.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replaces single-engine pymupdf4llm extraction with a tiered pipeline (Deck #205,
follows the tier-0 classifier #855). pypdfium2 becomes the default and only
hot-path PDF extractor; pymupdf4llm is deprecated to a rollback toggle.
Why: pymupdf4llm's O(n^2) find_tables drove the OOM (#852) and the form-PDF
parse timeouts (#856), carries AGPL/commercial licensing liability, and -- per
the benchmarks -- recovers near-zero usable tables on the real corpus. pypdfium2
(Apache/BSD) extracts the same text far faster (Student 1a.pdf: 120s timeout ->
0.2s) with no table-detection bomb.
- document_processors/pypdfium2_fast.py: tier-1 "fast" processor emitting text +
exact page_boundaries (the pdf_highlighter contract). pymupdf processor is now
tier "structured" (the rollback engine), registered but not default.
- registry: tiered routing in ProcessorRegistry. tier-1 fast extracts, then
classification is DERIVED from that text (classifier.classify_from_text -- no
PDF re-open), records the classification metrics, and escalates scanned /
no-text-layer docs to the "ocr" tier when document_ocr_enabled (default off;
no provider yet, so fast is terminal). Wires record_document_escalation + the
real "escalated" span attribute (was hardcoded False).
- Removes the separate _shadow_classify pass from vector/processor.py -- it
re-opened every PDF and re-extracted text (~0.5-1.3s/doc of pure duplicated
CPU that lowered throughput); classification now rides the tier-1 extraction.
- Settings: document_tier1_engine ("pypdfium2" default | "pymupdf" rollback,
enum-validated), document_ocr_enabled (default false).
Tests: pypdfium2 extractor, registry tiering (fast routing, rollback, classify
recording, OCR escalation on/off), classify_from_text. Full unit suite green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #855 round 2:
- 🔴 _shadow_classify swallowed all exceptions at DEBUG, so a systematic
failure (pymupdf bug, memory pressure) is invisible at LOG_LEVEL=INFO and
trips SonarQube S2221/S5754. Log at WARNING instead (still best-effort --
indexing is unaffected).
- classifier: use `with pymupdf.open(...) as doc` instead of manual try/finally.
- tests: release the Pixmap's native memory (del pix) in the image fixtures.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #855 review (all non-blocking):
- classifier: _sample_indices now always includes the first AND last page (the
old evenly-spaced sample missed the tail, e.g. last sampled index 95 on a
100-page doc -- a scanned tail could be missed).
- classifier + metrics: document that flags are diagnostic and fire
independently of routing (image_heavy on ANY page vs the ocr route needing a
page FRACTION), so flag{image_heavy} is expected to exceed classified{ocr}.
- classifier: clarify the text-quality whitespace comment (caps at 12%) and note
the image double-count approximation (min() caps coverage).
- tests: add the scanned (no text layer) and bad_text_layer (junk text over an
image) flag paths, and a test pinning first/last-page sampling.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
First step of the tiered document-processor effort (Deck #203): a cheap, local
pre-pass that recommends which extraction tier a PDF should start in, emitting
metrics WITHOUT changing routing yet -- so we gather per-tenant doc-mix data
before turning escalation on.
document_processors/classifier.py: classify_pdf(content) -> DocClassification.
Page-sampled (bounded on large docs), <~1s. Cheap signals only -- text-layer
chars, a text-quality score (catches the "Student 147" failure where a text
layer exists but is mashed/space-less junk), and image coverage. A page that is
mostly a raster image routes to OCR: its content (handwriting, stamps) isn't in
any text layer. Deliberately no get_drawings/graphics-density signal -- it's
slow on the exact pages it'd flag, the hotfix's graphics_limit already makes the
parse safe, and the (future) tier-1 quality gate catches lost tables.
Validated on the sample corpus: born-digital 2-col arxiv and a digital student
record -> fast (tier 1); a scanned+handwritten form -> ocr (tier 3).
Wiring (vector/processor.py): _shadow_classify runs the classifier on PDFs in a
worker thread, best-effort (never blocks/fails indexing), gated by the new
DOCUMENT_CLASSIFY_ENABLED setting. Metrics: astrolabe_document_classified_total
{recommended_tier}, astrolabe_document_classifier_flag_total{flag},
astrolabe_document_text_quality histogram.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #852 round 3 (all 🟡, no blockers):
- config: DOCUMENT_PARSE_TIMEOUT_SECONDS is now float (default 120.0) so a
fractional value is honoured rather than silently stored in an int field;
matches anyio.move_on_after's float seconds.
- _isolation: comment that a clean rlimit MemoryError leaves the worker alive
in anyio's pool (vs the SIGKILL/BrokenWorkerProcess path that respawns) --
acceptable since RLIMIT_AS caps virtual address space, not RSS.
- processor: note the `if indexed is False` is a deliberate identity check --
a successful index (incl. dedup hit) returns None and must not be mistaken
for a parse failure.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address PR #852 review:
- pymupdf.py: the metadata `doc` was only closed on the PdfParseFailed and
success paths, so a failure in `_extract_metadata`/`mkdir`/`get_settings`
leaked it. `doc` is only needed for metadata + page_count (the heavy parse
works from `content` bytes in the worker), so open it, read metadata, and
close it immediately under try/finally; drop the two later doc.close() calls.
- processor.py: a permanent parse failure early-returned from `_index_document`,
after which `process_document` still recorded record_qdrant_operation("upsert",
"success") + record_vector_sync_processing(success) -- counting an OOM/timeout
bomb as astrolabe_documents_indexed_total{status="success"}. `_index_document`
now returns False on that path and the caller skips the success metrics (the
failure is already recorded via document_parse_failed_total + the registry's
document_parse_total{error}).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The document processor crash-looped on one pathological PDF: pymupdf4llm's
table/graphics detection over a page with ~1M vector path items ballooned past
the 2 GiB pod limit. The parse ran in a thread, so nothing could interrupt or
memory-bound it -- a single bad file OOM-killed the whole pod.
Run the parse in an isolated worker subprocess (anyio.to_process, cancellable)
with an RLIMIT_AS memory cap and a wall-clock timeout, so a pathological file
fails THAT document instead of the pod (new document_processors/_isolation.py).
Also pass graphics_limit (default 5000) to to_markdown -- validated to cut the
known trigger page from 112 s to 23 s with bounded memory.
On a permanent parse failure the processor returns success=False (instead of
raising, which would retry 3x); vector/processor.py marks the placeholder
"failed" and skips indexing, and the scanner stops re-queuing failed placeholders
until the file changes -- so a doomed file no longer churns.
New per-tenant (per-pod env) settings: DOCUMENT_PDF_GRAPHICS_LIMIT,
DOCUMENT_PARSE_TIMEOUT_SECONDS, DOCUMENT_PARSE_MEM_LIMIT_MB. New metric
astrolabe_document_parse_failed_total{reason=timeout|oom|error} surfaces hard
failures that previously killed the process before any except ran.
First PR of the tiered document-processor effort (Deck #199); tier 0/1/3
pipeline tracked separately.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Remaining items from the PR #831 Claude review:
- processor span symmetry: add "vector_sync.total_chars" to the sparse
embedding span (already on the dense span) and drop the redundant
"embedding.batch_size" attribute from both spans — it always equalled
vector_sync.chunk_count and would mislead once batching is split.
- metrics: document the deliberate "throughput counts only on full success"
contract in record_document_parse (partial extractions flagged
success=False are counted as a parse-error but never inflate
pages/chars/bytes throughput).
- config: extract _detect_base_provider() -> (family, model) as the single
source of truth for the provider-detection priority chain, shared by
get_embedding_model_name() and get_embedding_provider_family(). Preserves
the intentional gateway asymmetry (only the family method short-circuits).
- base.py: Optional[...] -> PEP 604 `... | None`; drop now-unused import.
Behavior unchanged (get_embedding_* outputs covered by test_config.py).
Refs Deck #175, PR #831.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Failed deletes no longer bump astrolabe_documents_indexed_total: the outer
except in process_document now gates doc_type on operation != "delete", so a
delete error is counted as processed-error but not as an indexing event.
Added test_failed_delete_is_processed_but_not_indexed.
- registry parse span: pass record_exception=True explicitly (matches
instrument_tool) and add a structured logger.warning on the parse-error path
(processor/tier/byte_size/duration_ms) for a Loki-aggregatable failed-parse
signal.
- test_error_does_not_increment_throughput: snapshot-before/delta pattern
instead of absolute 0.0 (counters are global singletons).
- config: document the deliberate gateway asymmetry between
get_embedding_model_name() (no gateway branch) and
get_embedding_provider_family() (short-circuits on gateway).
- Cleanup in touched scope: narrow `except (HTTPStatusError, Exception)` to
`except Exception` (drop now-unused import); convert registry signatures from
Optional[...] to `... | None`.
Refs Deck #175, PR #831.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Make per-tier bottlenecks in the document-processing pipeline
(scan -> fetch -> parse -> chunk -> embed -> Qdrant upsert) visible via
metrics, traces, and structured logs. Today the document_processors layer
emits only a logger.info line: no metric, no span, and page counts live only
inside a log string. The single processing-duration histogram is unlabeled and
whole-document, so it cannot isolate parse vs embed vs upsert.
New astrolabe_* metric family (distinct from the mcp_* protocol metrics):
- astrolabe_document_parse_{duration_seconds,total} + pages/chars/bytes counters
recorded at the ProcessorRegistry.process() boundary (covers all current and
future processors uniformly)
- astrolabe_document_escalation_total (dormant; tiered-pipeline readiness)
- astrolabe_embedding_{duration_seconds,requests_total,chunks_total,chars_total}
- astrolabe_document_chunks_total, astrolabe_documents_indexed_total{source,status}
Tracing: new document_processor.parse child span + enriched embed/chunk span
attributes (provider/model/batch_size/chunk_count). Structured logs gain a
consistent field vocabulary (doc_id, doc_type, processor, tier, pages, chars,
byte_size, chunks, duration_ms, status) so Loki can aggregate without regex.
Tier-readiness: processor/tier are labels from day one and a tier property is
added to DocumentProcessor, so adding docling/OCR/LLM tiers later is additive
(new label values, never new metrics). Tenant comes from the kube namespace
label; mime_type/model are span attributes only (cardinality). Existing
mcp_vector_sync_*/mcp_qdrant_* are left untouched.
Refs Deck #175 (superset of #173 Phase 2). Dashboard/recording-rules follow-up
tracked on #175 for homelab-argocd.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replace parallel per-page extraction with single to_markdown(page_chunks=True)
call. This is more efficient as pymupdf4llm can optimize internally for
full-document processing instead of making N separate calls for N pages.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Phase 1 - PDF Highlighting Optimization:
- Render each page ONCE instead of once per chunk (N chunks = 1 render, not N)
- Use PIL to draw bounding boxes on copied base images (fast) instead of
re-rendering page via pymupdf (slow)
- Add _find_chunk_bbox() to extract bbox without modifying page
Phase 2 - Parallel Page Extraction:
- Use anyio task group with run_sync() for parallel page extraction
- Each page extracted in separate thread via anyio.to_thread.run_sync()
- Event loop stays responsive during extraction
- Remove obsolete _process_sync() method
Expected improvement: 30-50% reduction in total PDF processing time.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Previously, pymupdf4llm.to_markdown() was called twice - once in
PyMuPDFProcessor during indexing and again in PDFHighlighter during
visualization. Different image path lengths caused different character
offsets, leading to highlighted pages not matching their chunks.
Also fixed issue where all chunks on the same page showed all highlights
instead of just their own highlight. Now restores original page contents
between chunks using xref stream caching.
Changes:
- Add PDFHighlighter class requiring pre-computed page_boundaries and
full_text from document processor (no fallback extraction)
- Pass pre-computed data from processor to highlighter
- Extract page-relative portion of chunk text for cross-page chunks
- Add bounding box highlighting using text anchor search
- Run highlight generation in parallel with embedding/BM25
- Cache and restore page contents to isolate highlights per chunk
Results: Highlighting success rate improved from 51% to 95% (121/128).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implements optional context expansion for semantic search results that
fetches adjacent chunks (N-1 and N+1) from Qdrant to provide before/after
context. Removes configurable chunk overlap (default 200 chars) to avoid
duplicate text appearing in both context and excerpt.
Key changes:
- Add include_context and context_chars parameters to nc_semantic_search
and nc_semantic_search_answer tools
- Implement Qdrant cache fast path for chunk retrieval (avoids re-fetching
and re-parsing documents, especially important for PDFs)
- Add _get_chunk_by_index_from_qdrant() to fetch adjacent chunks
- Remove chunk overlap from before_context (last N chars) and after_context
(first N chars) to prevent duplicate text
- Fetch context in parallel with anyio.Semaphore (max 20 concurrent)
- Pass through page_number from SearchResult to SemanticSearchResult
- Remove document-level deduplication (keep chunk-level dedup from algorithm)
Context expansion is opt-in via include_context=true parameter. When enabled:
- Populates has_context_expansion, marked_text, before_context, after_context
- Adds truncation flags when context exceeds context_chars limit
- Falls back to document fetch for legacy data with truncated excerpts
Related: nextcloud_mcp_server/search/context.py:87-382,
nextcloud_mcp_server/server/semantic.py:161-255
This commit addresses multiple issues with async operations, PDF metadata
extraction, and type safety in document processing and search.
## Async/Await Fixes
- processor.py:259 - Added await for chunker.chunk_text(content)
- processor.py:270 - Added await for bm25_service.encode_batch(chunk_texts)
- tests/unit/test_document_chunker.py - Converted all 12 test methods to async
## PDF Metadata Enhancement
- pymupdf.py:143 - Added file_size metadata extraction
- pymupdf.py:145-206 - Refactored to extract text page-by-page
- Manually loop through pages instead of using page_chunks=True
- Generate page_boundaries metadata for precise page tracking
- Works around pymupdf.layout.activate() breaking page_chunks=True
- processor.py:32-66 - Added assign_page_numbers() helper function
- Assigns page numbers to chunks based on overlap with page boundaries
- Handles chunks spanning multiple pages
- processor.py:298-300 - Call assign_page_numbers() for PDF files
## Type Safety Fixes
- bm25_hybrid.py:184 - Removed int() conversion of doc_id
- semantic.py:131 - Removed int() conversion of doc_id
- viz_routes.py:275 - Removed int() conversion of doc_id
- Added comments documenting that doc_id can be int (notes) or str (file paths)
## Testing
- All 18 tests passing (12 unit + 6 integration)
- No type errors in modified files
- Container logs show successful processing
- Vector viz searches working correctly
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
