Round-4 review on PR #893 (no blockers, minor items):
- Document why Mistral's _is_transient is SDK-level only (429/5xx): a bare
connection drop the SDK surfaces as httpx/ConnectionError isn't an SDKError
and isn't retried here by design — the pod-rollover target is the gateway
(OpenAI-compatible) path, which does cover connection errors.
- Include the last error (%r) in the retry helper's "not resolved after N
attempts" error log.
- Add test_mistral_embed_batch_retries_on_5xx (batch path parity with embed()).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-1 review on PR #893:
- _drop_reason now descends through nested ExceptionGroups to the first leaf
(was single-level), so a doubly-wrapped cause isn't mislabelled "other";
added a nested-group test. Commented why both the httpx and openai isinstance
branches exist (raw Nextcloud-API errors vs SDK-wrapped variants).
- Documented that generate() intentionally shares the broadened transient retry
(RAG sampling path), with the worst-case latency note.
- Added a docstring note to process_document on how the provider-level retry
(5x) layers over the outer loop (3x in-process / 1x procrastinate).
- Added test_embed_batch_retries_on_connection_error for the batch path.
- Renamed test_retry_reraises_non_rate_limit_immediately ->
test_retry_reraises_when_predicate_returns_false (it tests the predicate, not
a specific status).
SonarCloud:
- S5708 (BLOCKER) on the helper's dynamic `except exception_type`: the type is
constrained to BaseException/tuple by the signature; suppressed with a
justified NOSONAR.
- S7503 (async without await) in the embed-retry test: use AsyncMock side_effect
instead of a hand-rolled async function.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
From card 309 (OHR-Bench smoke-test triage): during a backend-pod rollover the
embedding endpoint was briefly unreachable, and openai.APIConnectionError /
ConnectError propagated unretried (the provider only retried 429). Documents
exhausted the 3 in-process retries and were dropped for that scan cycle.
Broaden the provider-level retry to the transient set -- APIConnectionError,
APITimeoutError, 429, and 5xx -- on the existing exponential backoff (2s->60s,
5 attempts), so a few seconds of retry rides through the rollover. Permanent
4xx (auth, bad request) still re-raise immediately. Generalize the shared
_retry helper (retry_on_rate_limit -> retry_on_transient, predicate renamed to
should_retry, accurate log label) with a back-compat alias; Mistral gets 429+5xx
for parity. The production gateway path inherits this via GatewayProvider, which
delegates to the decorated OpenAIProvider methods.
Add astrolabe_vector_ingest_dropped_total{reason}, incremented when a document
exhausts retries, classified (connection|timeout|rate_limit|server|qdrant|other)
by _drop_reason so the embed-drop rate is alertable per cause. Dropped docs are
NOT marked failed, so the next full scan re-picks them (re-queue via scan loop).
Refs: Deck board 12 card 309 (AC #1 no permanently-dropped docs; embed-drop
metric for AC #5).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-8 claude-review (no blockers; comment-only):
- 🟡 Documented that Ollama's /api/embed prompt_eval_count is assumed
batch-level total and is unverified against a live instance (Ollama isn't the
Cloud billing provider); if it proves last-item-only, switch to per-item
summing. The char estimate already covers versions that omit the field.
- 🟡 Noted on the astrolabe_embedding_tokens_total counter that operation="query"
is recorded pre-Qdrant, so it can legitimately exceed the billing-store
tokens_embedded aggregate when a search fails post-embed — dashboards
shouldn't alert on that healthy gap.
Deferred (reviewer: "minor nit, acceptable"): record_indexing_usage awaited in
the task group — the group awaits all child tasks regardless, the write is
best-effort + fast, and start_soon would need the tg threaded into the closure
for marginal gain.
Deck #284.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Billing product model finalized (Deck #281): bill pages externally, record
tokens internally. Rename the data-plane metric literals to match the now-
canonical contract (Deck #284) — the control plane's METRIC_EVENT_NAMES is
already renamed, so the old names would be unmapped and never sync to Stripe.
Rename (values unchanged):
- embeddings_queries → tokens_embedded (value = real token count, already
emitted by this PR; the unit upstream providers bill on).
- pages_chunks → pages_embedded (value kept as len(chunk_texts) interim;
TODO(#282): real normalized "pages indexed" count — real pages for paginated
types, chars/tokens-per-page constant otherwise — is deferred to the
instrumentation card, this only lands the name/contract).
- All literals, log strings, docstrings, comments, the migration comment, and
tests renamed; grep confirms zero old strings remain.
Observability (new): export embedding token cost to Prometheus as
astrolabe_embedding_tokens_total{provider,operation} (operation = index|query)
so the billed cost unit is visible in Grafana, not just the per-tenant billing
DB. Dedicated counter (doesn't inflate the existing chunk/request metrics) and
always-on (independent of USAGE_METERING_ENABLED, so OSS/self-host gets it).
Wired on both the indexing batch embed and the search query embed (query inside
the per-request cache-miss branch, so reused embeddings aren't double-counted).
Note: the rename orphans any pre-existing embeddings_queries/pages_chunks rows
in tenant app DBs (CP no longer maps them) — acceptable; pipeline is inert with
throwaway dev/sandbox data.
Deck #284 (folded into PR #875).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-5 claude-review (merge-ready; all nits):
- 🟡 Added test_empty_doc_types_normalizes_to_null pinning doc_types=[] → None
in record_search_usage metadata (matches the None case).
- 🟡 record_search_usage docstring now notes nc_semantic_search_answer always
meters with doc_types=None (it exposes no doc_types parameter).
- 🟢 BM25HybridSearchAlgorithm.__init__ now sets query_embedding /
query_token_count alongside _embedded_query, so all three cache fields are
instance attributes from construction (was relying on the class-level
SearchAlgorithm defaults).
- 🟢 Ollama embed_batch_with_usage caches _dimension inline (mirrors
OpenAI/Mistral), so the dimension is set via any embed path.
- 🟢 record_indexing_usage documents the independent-record / partial-failure
semantics under SUM aggregation.
Deck #67.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-2 claude-review findings:
- 🟡 Base-class recursion invariant: documented on embed_with_usage /
embed_batch_with_usage that a provider overriding embed()/embed_batch() to
delegate to the *_with_usage variant MUST also override that variant, or the
two recurse. (No recursion today; the shipped providers pair the overrides.)
- 🟡 Processor metering had no unit test: extracted the two-event recording
into a module-level record_indexing_usage() helper and added
tests/unit/test_processor_metering.py (value mapping, flag/zero-chunk no-ops,
best-effort failure swallowed).
- 🟡 SonarQube hotspots (python:S5332) were 3 http:// URLs in the new test
fixtures (mock hosts, never contacted) blocking the quality gate
(new_security_hotspots_reviewed). Switched them to https:// so no hotspot is
raised.
- 🟢 Zero-chunk guard: record_indexing_usage() no-ops when chunk_count == 0, so
an empty document no longer writes zero-value billing rows.
Deferred (stated on the PR): Mistral x.index-or-0 sort key (pre-existing,
equivalent), CHANGELOG note for the Ollama /api/embed switch (CHANGELOG is
commitizen-generated from commit bodies, which document it), class-var
query_token_count (safe under the per-request instance pattern).
Deck #67.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Round-1 claude-review findings:
- 🔴 Multi-doc_type search billed N embedding calls as 1. nc_semantic_search
loops search() once per doc_type on one BM25HybridSearchAlgorithm instance,
and each call re-embedded the query, so only the last query_token_count was
recorded. Cache the dense embedding per query on the (per-request) instance
so the query is embedded — and metered — exactly once regardless of how many
doc_types are searched. This also removes the redundant per-type embed work
and avoids billing a user N× for one logical query.
- 🟡 Ollama embed() now delegates to embed_with_usage() so single and batch
embeds use the same /api/embed endpoint (was the legacy /api/embeddings),
keeping _detect_dimension and other embed() callers consistent.
- 🟢 round() instead of truncating int() when coercing provider-reported token
counts (forward-compatible if a provider ever returns a float).
Tests: per-instance query-embedding cache (embedded once across 3 doc_types;
re-embeds on a different query).
Deferred (stated on the PR): mistral/openai single-embed dual path (changes
tested error/request semantics on the cloud-critical path — separate refactor),
bedrock boto3 sync-in-async (pre-existing; no new invoke_model calls per doc).
Deck #67.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
embeddings_queries now records the embedding request's token count (the unit
upstream providers bill on) instead of an operation count, and fires on the
indexing path too. Previously only semantic search recorded it (value=1), so a
re-indexing run produced no embeddings_queries events at all — only pages_chunks.
- Provider layer: additive embed_with_usage / embed_batch_with_usage surface the
per-request token count (Mistral/OpenAI usage.total_tokens, Bedrock Titan
inputTextTokenCount, Ollama prompt_eval_count); a char-based estimate is the
fallback (Simple, and any provider/response without a token field). Gateway and
EmbeddingService forward through. The count travels as a return value / a
per-request SearchAlgorithm attribute — never on the singleton — so concurrent
indexing + search can't mis-attribute bills.
- Indexing (vector/processor.py): records embeddings_queries (value=batch tokens)
alongside the existing pages_chunks event.
- Search (server/semantic.py): value is now the query embedding's token count,
relayed from BM25HybridSearchAlgorithm via query_token_count.
The astrolabe_embeddings_queries Stripe meter (sum aggregation) now sums tokens
with no CP/Terraform change. The meter "queries"->tokens naming/unit
clarification (homelab-terraform #254) + CP rollup/portal copy is a follow-up.
Deck #67.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the seven §10.2 hook-point modules + five env vars so Astrolabe Cloud can
offload document processing to the external document-processor / embedding
gateway. Purely additive: with every setting unset the server behaves exactly
as today, so self-hosters are unaffected (Deck #92).
Hook points (all default to current monolith behavior):
- config: EMBEDDING_PROVIDER, INGEST_MODE, STATUS_BACKEND,
COLLECTION_METADATA_SOURCE, FACT_EVENT_EMITTER (+ supporting settings),
validated in Settings.__post_init__ (fail-fast STATUS_BACKEND=local with
INGEST_MODE=external); shared canonical.py.
- vector/payload_keys.py + acl_hash.py: cross-impl NAMESPACE/point_id (§2.2)
and BLAKE2b-128 ACL hash (§11), pinned by fixtures shared with the
document-processor repo.
- embedding/gateway_client.py: OpenAI-compatible GatewayProvider authenticating
via M2M OIDC client-credentials (separate realm); manual-only registry entry.
- vector/collection_metadata.py: sentinel-point / API metadata source with env
fallback.
- vector/queue/: hexagonal ingest producer ports + memory/NATS adapters
(Postgres seam); INGEST_MODE=external publishes mcp.ingest.requested.{tenant}
instead of the in-memory stream and skips the in-process processor pool. The
lifespan becomes a composition root across both deployment branches.
- vector/queue/status.py: STATUS_BACKEND=bus subscriber feeding a StatusStore
the vector-sync status endpoint reads.
- admin/payload_backfill.py: POST /api/v1/admin/payload-backfill (admin scope);
processor writes the new payload keys; query-side ACL pre-filter gated behind
ACL_PREFILTER_ENABLED (default off).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- test_registry.py: stub `mistralai.client.Mistral` in
`test_registry_mistral_wins_over_ollama`, mirroring the sibling
picker test, so the test doesn't depend on the SDK accepting
arbitrary keys.
- openai.py: convert remaining f-string `logger.info(...)` calls to
lazy `%s` formatting, aligning with the pattern in mistral.py and
the repo's logging convention.
- test_mistral.py: add four tests covering the defensive RuntimeError
guards in `embed()` and `_embed_batch_request()` — empty
response.data, single null embedding, batch null embedding, and
count-mismatch.
- docs/configuration.md: add `AWS_ACCESS_KEY_ID` and
`AWS_SECRET_ACCESS_KEY` rows to the env-var reference table; they
were already mentioned in prose but missing from the table.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- _retry.py: replace `assert last_error is not None` with explicit
`if last_error is None: raise RuntimeError(...)` so the original
rate-limit error is preserved under `python -O`.
- openai.py: drop the `_retry_factory` alias chain; rename the bound
decorator to `_retry_429` to match the pattern in mistral.py.
- mistral.py: comment the imports so future reviewers understand why
`from mistralai.client import …` is the canonical path on 2.x (no
top-level `__init__.py`; no `mistralai.models` subpackage either).
- docs/configuration.md: add `OPENAI_GENERATION_MODEL` and
`OLLAMA_GENERATION_MODEL` rows to the env-var reference table.
- test_mistral.py: add direct unit test for the `_is_rate_limit`
predicate (429 → True, 500 → False, missing-attr → False).
- test_registry.py: stub `mistralai.client.Mistral` in the registry
picker test, mirroring the Ollama sibling, so the test doesn't
depend on the SDK accepting arbitrary keys.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Addresses the Claude Code review on PR #772 plus the SonarCloud S1192 finding:
- Extract `retry_on_rate_limit` into `nextcloud_mcp_server/providers/_retry.py`
as a parametric decorator. OpenAI and Mistral now share the same backoff
loop; future providers can reuse it without copy-paste.
- New `tests/unit/providers/test_retry.py` covers the decorator: 429 retry +
success, non-429 immediate re-raise, MAX_RETRIES exhaustion, default
predicate, and unrelated exception passthrough.
- Tighten Mistral SDK import to `from mistralai.client.errors import SDKError`
(the canonical sub-path; the reviewer's `from mistralai.models import
SDKError` does not exist in mistralai 2.4.5).
- Replace `MistralProvider.close()`'s direct `__aexit__` call with a no-op +
comment — the Speakeasy-generated client has no public close hook and the
underlying httpx client is closed by GC.
- Extract the duplicated "Embedding not supported" message to a module-level
constant (SonarCloud S1192).
- Align `Settings.get_embedding_model_name()` Bedrock check with the registry
by also considering `bedrock_generation_model`.
- Add the `mock_mistral_client` fixture to
`test_mistral_no_embeddings_disabled` for parity with the rest of the file.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a hosted Mistral embedding option (mistral-embed, 1024-dim) alongside
the existing Bedrock / OpenAI / Ollama / Simple providers. Implementation
mirrors OpenAIProvider: lazy dimension detection with a known-models lookup,
chunked batch requests, defensive index sort, and a 429-aware retry decorator.
In the same change, ProviderRegistry switches from os.getenv to the
dynaconf-backed Settings dataclass so all five providers share a single
configuration path. config.py gains the previously-uncovered Bedrock keys,
the new Mistral keys, the missing OPENAI_GENERATION_MODEL /
OLLAMA_GENERATION_MODEL, and SIMPLE_EMBEDDING_DIMENSION.
Auto-detection priority: Bedrock → OpenAI → Mistral → Ollama → Simple.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Fixed 8 type checker errors across the codebase:
- vector/scanner.py: Handle None scroll results with null-safe iteration
- search/{bm25_hybrid,semantic}.py: Add None checks for result.payload
- auth/{unified_verifier,webhook_routes}.py: Assert non-None auth credentials
- client/webdav.py: Add None checks before int() conversions
- providers/openai.py: Assert embedding_model is not None
- search/algorithms.py: Explicitly type doc_types set and cast values
- observability/logging_config.py: Match parent class signature (log_data)
Also fixed test_create_tag_creates_system_tag to match WebDAV implementation
(was testing OCS API endpoint, now tests correct WebDAV endpoint with
Content-Location header).
Type checker: 0 errors (down from 8), 20 warnings (ignored)
Tests: All 192 unit tests passing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add exponential backoff retry handling for OpenAI API rate limits
(429 errors). This is needed for GitHub Models API which has stricter
rate limits than standard OpenAI API.
- Add retry_on_rate_limit decorator with exponential backoff
- Max 5 retries with delays: 2s → 4s → 8s → 16s → 32s
- Apply to embed(), _embed_batch_request(), and generate() methods
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Increase sampling timeout from 30s to 300s in semantic.py to accommodate
slower local LLMs like Ollama
- Refactor RAG integration tests to support multiple providers (ollama,
openai, anthropic, bedrock)
- Remove unnecessary embedding_provider fixture since MCP server handles
embeddings internally
- Add --provider flag via tests/integration/conftest.py
- Add provider_fixtures.py with factory functions for generation providers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Adds OpenAI provider to the unified provider architecture (ADR-015),
supporting:
- OpenAI API (api.openai.com)
- GitHub Models API (models.github.ai/inference)
- OpenAI-compatible endpoints (Fireworks, Together, etc.)
Features:
- Embedding support with text-embedding-3-small/large models
- Text generation via chat completions API
- Automatic retry with exponential backoff for rate limits
- Provider auto-detection in registry (priority after Bedrock)
Environment variables:
- OPENAI_API_KEY: API key (required)
- OPENAI_BASE_URL: Base URL override (optional)
- OPENAI_EMBEDDING_MODEL: Embedding model (default: text-embedding-3-small)
- OPENAI_GENERATION_MODEL: Generation model (default: gpt-4o-mini)
Also adds:
- Integration tests for RAG pipeline with MCP sampling
- MCP client sampling support for integration tests
- Ground truth Q&A pairs for Nextcloud User Manual
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Switch from sequential loop to /api/embed batch endpoint
- Use 'input' array parameter instead of individual 'prompt' requests
- Process in chunks of 32 to avoid quality degradation (issue #6262)
- Reduces HTTP overhead: 128 texts = 4 requests instead of 128
- Maintains backward compatibility with embed() for single embeddings
Ref: ollama/ollama#6262
Refactored LLM provider infrastructure to support sustainable additions of new providers with both embedding and text generation capabilities.
## Major Changes
### Unified Provider Architecture (ADR-015)
- Created `nextcloud_mcp_server/providers/` with unified Provider ABC
- Providers now support optional capabilities (embeddings and/or generation)
- Auto-detection registry with priority: Bedrock → Ollama → Simple
- Backward compatible - existing code continues to work
### New Providers
- **BedrockProvider**: Full Amazon Bedrock integration
- Embeddings: Titan Embed, Cohere Embed models
- Generation: Claude, Llama, Titan Text, Mistral models
- Model-specific request/response handling
- AWS credential chain integration
- **OllamaProvider**: Migrated with both capabilities support
- **AnthropicProvider**: Moved from test code to production providers
- **SimpleProvider**: Migrated in-memory fallback provider
### Breaking Changes
None - full backward compatibility maintained:
- `embedding.get_embedding_service()` still works
- RAG evaluation tests updated to use unified providers
- All existing tests pass (127 unit tests)
### Testing
- Added 9 comprehensive Bedrock unit tests with mocked boto3
- All existing unit tests pass
- Type checking (ty) and linting (ruff) pass
- Verified backward compatibility
### Documentation
- `docs/ADR-015-unified-provider-architecture.md`: Comprehensive ADR
- `docs/bedrock-setup.md`: AWS setup guide with IAM permissions
- `CLAUDE.md`: Updated with provider architecture section
### Dependencies
- Added `boto3>=1.35.0` to dev dependencies (optional)
## Environment Variables
### Bedrock
- `AWS_REGION`: AWS region (e.g., "us-east-1")
- `BEDROCK_EMBEDDING_MODEL`: Model ID for embeddings
- `BEDROCK_GENERATION_MODEL`: Model ID for generation
- `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`: Optional credentials
### Ollama
- `OLLAMA_BASE_URL`: API URL
- `OLLAMA_EMBEDDING_MODEL`: Embedding model (default: "nomic-embed-text")
- `OLLAMA_GENERATION_MODEL`: Generation model
## AWS Bedrock Permissions Required
Minimal IAM policy:
```json
{
"Effect": "Allow",
"Action": ["bedrock:InvokeModel"],
"Resource": ["arn:aws:bedrock:*::foundation-model/*"]
}
```
See `docs/bedrock-setup.md` for detailed setup instructions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
