Skip to content

feat: expose Files and vector-store HTTP APIs - #485

Merged
franciscojavierarceo merged 4 commits into
mainfrom
codex/file-search-http
Nov 7, 2026
Merged

franciscojavierarceo merged 4 commits into
mainfrom
codex/file-search-http

Conversation

@franciscojavierarceo

@franciscojavierarceo franciscojavierarceo commented Oct 27, 2026 •

Copy link
Copy Markdown
Collaborator

Summary

Expose the Files and vector-store upload, lifecycle, attachment, and search routes over the pluggable core service. Add server configuration for local file bytes, embeddings, and an optional trusted sqlite-vec extension path. Wire the routes into authentication and OpenAPI, with deployment documentation. Reconcile abandoned blob cleanup intents at startup and periodically while the gateway runs. Local routes enforce the configured API key and request-body ceiling; deletion tolerates a cleanup marker already removed by reconciliation, and startup logs provider setup diagnostics. This layer does not register the Responses file_search built-in tool.

Review order: #485 → #486 → #34. #483 and #484 are merged. PostgreSQL vector indexing remains in #278.

Test Plan

  • cargo test -p agentic-server --test file_search_http_test: 6 passed, including missing, incorrect, and valid API-key cases and configured multipart/JSON body limits.
  • cargo test -p agentic-server-core --test file_search_service: 32 passed, 1 ignored, including the deletion cleanup-marker race regression.
  • Full workspace cargo test --offline passed on the restacked feat: execute Responses file_search built-in tool #34 head containing these fixes.
  • cargo test -p agentic-server --lib openapi: 19 passed.
  • cargo test -p agentic-server --bin agentic-server config_file::tests: 37 passed.
  • cargo build --offline -p agentic-server --bin agentic-server and cargo clippy --offline -p agentic-server -p agentic-server-core --all-targets -- -D warnings: passed.
  • openai==3.8.0 client E2E: upload, list/retrieve/content, vector-store attachment, filtered search, detach, and deletion passed against the rebuilt local gateway. The Rust CI job runs this script.
  • Formatting and repository pre-commit hooks passed on signed-off commits. CI also runs PostgreSQL file-search persistence, sqlite-vec, and bounded PDF ingestion checks.
  • OpenAI reference cassette parity for Files and vector-store routes remains unverified: this environment has no OpenAI API credential. The focused local gateway HTTP suite and OpenAI SDK client E2E cover the route lifecycle; no reference cassette was hand-authored.

franciscojavierarceo added a commit that referenced this pull request Nov 3, 2026
## Summary

Add typed file, vector-store, and search contracts; pluggable
`FileSearchRepository` and `FileBlobStore` interfaces; portable SQL
metadata and bounded exact retrieval; and local blob storage. Store
listing batches current attachment counts and usage. Durable,
token-fenced cleanup intents cover uploads and deletions; expired leases
cannot let a publisher expose missing content. Recovery retains
abandoned-upload tombstones for later sweeps when a delayed write
finishes after an initial cleanup pass. Local staging is addressable by
file ID, and cancellation drains publication before cleanup. This is the
independently compilable foundation of the file-search stack; HTTP
routes and periodic cleanup are in #485. CI uses the macOS 15 Apple
Silicon runner because GitHub is retiring macOS 14 and its scheduled
brownout canceled wheel validation.

Review order: #483 → #484 → #485 → #486 → #34. PostgreSQL vector
indexing remains in follow-up #278.

## Test Plan

- `cargo test --offline -p agentic-server-core --test
file_search_service`: 31 passed, 1 PostgreSQL test ignored locally.
Includes two-service upload/recovery interleavings, restart recovery
after metadata rejection plus failed blob removal, delayed-staging
cancellation, and a late-write/failed-rollback regression.
- `cargo test --offline -p agentic-server-core --lib
storage::local_files::tests`: 5 passed, including absent-directory and
deterministic staging cleanup.
- `cargo test --offline -p agentic-server-core --lib
storage::schema::tests`: 6 passed, 4 PostgreSQL tests ignored locally;
PostgreSQL CI exercises the final schema.
- `cargo clippy --offline --all-targets -- -D warnings`, `cargo fmt --
--check`, and repository pre-commit hooks: passed.
- The official OpenAI Python SDK HTTP integration test is in #485 and
passed locally against the rebuilt final stack.

---------

Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
@franciscojavierarceo
franciscojavierarceo force-pushed the codex/file-search-sqlite-vec branch 2 times, most recently from 714eb40 to a7ca49d Compare November 3, 2026 05:26
@franciscojavierarceo
franciscojavierarceo requested a balanced review from Copilot November 3, 2026 22:03

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🟡 Changes recommended

The local routes can expose uploaded data without API-key authentication and ignore configured request-size limits, while a reconciliation race causes erroneous deletion failures and initialization errors lose actionable diagnostics.

4 open issues
What changed in this PR

This PR exposes Files and vector-store HTTP APIs over the pluggable core storage service. It adds the HTTP and deployment layer of the file-search stack; Responses file_search execution remains outside this PR.

Changes:

  • Adds upload, download, lifecycle, attachment, and search routes with OpenAPI definitions.
  • Configures local storage, embeddings, and optional sqlite-vec, with startup and periodic cleanup reconciliation.
  • Adds HTTP and OpenAI client coverage, CI checks, and deployment documentation.
File Description
scripts/​tests/​openai-file-search-client-test.py Exercises file and vector-store APIs through the OpenAI client.
docs/​deploying/​kubernetes.md Documents persistent shared file storage.
docs/​deploying/​container.md Adds storage configuration and deployment requirements.
docs/​api/​index.md Links the file-search API guide.
docs/​api/​file-search.md Documents configuration, ingestion, retrieval, and lifecycle APIs.
crates/​agentic-server/​tests/​file_search_http_test.rs Tests HTTP lifecycle, search, validation, and binary uploads.
crates/​agentic-server/​src/​server.rs Runs periodic blob cleanup with shutdown handling.
crates/​agentic-server/​src/​openapi.rs Registers routes, upload schema, and schema tests.
crates/​agentic-server/​src/​main.rs Resolves file-search configuration and environment overrides.
crates/​agentic-server/​src/​handler/​http/​mod.rs Registers the file-search handler module.
crates/​agentic-server/​src/​handler/​http/​file_search.rs Implements Files and vector-store HTTP handlers.
crates/​agentic-server/​src/​config_file/​file_search.rs Defines storage and search configuration sections.
crates/​agentic-server/​src/​config_file.rs Integrates configuration validation and tests.
crates/​agentic-server/​src/​app.rs Merges the new routes into the gateway router.
crates/​agentic-server/​Cargo.toml Enables multipart uploads and forwards the PDF feature.
crates/​agentic-server-core/​tests/​file_search_service.rs Updates configuration fixtures for sqlite-vec.
crates/​agentic-server-core/​src/​types/​file_search/​config.rs Adds the sqlite-vec extension path setting.
crates/​agentic-server-core/​src/​tool/​file_search/​service/​setup.rs Selects configured SQL or sqlite-vec providers.
crates/​agentic-server-core/​src/​executor/​request.rs Installs the shared service and reconciles cleanup at startup.
crates/​agentic-server-core/​src/​config.rs Adds file-search runtime configuration.
Cargo.lock Records the multipart parser dependency.
.github/​workflows/​rust.yml Adds client, PostgreSQL persistence, and PDF ingestion checks.

Review effort: Balanced

Comment thread crates/agentic-server/src/app.rs Resolved
Comment thread crates/agentic-server/src/server.rs Resolved
@franciscojavierarceo
franciscojavierarceo marked this pull request as ready for review November 4, 2026 00:39
@franciscojavierarceo
franciscojavierarceo force-pushed the codex/file-search-http branch 2 times, most recently from 8def410 to 3cc360b Compare November 4, 2026 11:58
Comment thread crates/agentic-server/src/openapi.rs Resolved
Comment thread docs/api/file-search.md Resolved
Comment thread crates/agentic-server/src/openapi.rs Resolved
@franciscojavierarceo
franciscojavierarceo force-pushed the codex/file-search-sqlite-vec branch from 30ea473 to ea3f961 Compare November 5, 2026 03:12
@franciscojavierarceo
franciscojavierarceo force-pushed the codex/file-search-http branch 2 times, most recently from 7af4b65 to 9fc840a Compare November 5, 2026 05:05
@franciscojavierarceo
franciscojavierarceo force-pushed the codex/file-search-sqlite-vec branch from 51af71f to cb4f5a9 Compare November 6, 2026 02:08
@franciscojavierarceo
franciscojavierarceo force-pushed the codex/file-search-http branch 2 times, most recently from b644c3f to 8e09904 Compare November 6, 2026 02:26
franciscojavierarceo added a commit that referenced this pull request Nov 6, 2026
## Summary

Add a `FileSearchRepository` backed by sqlite-vec for semantic cosine
retrieval on a file-backed SQLite database. It keeps portable SQL
metadata and published-chunk visibility, normalizes embeddings before
indexing, and records a provider identity so stores cannot silently
switch indexes. Keyword and hybrid search continue through the bounded
exact ranker. SQLite metadata and vector rows now publish in one
transaction, so concurrent replicas cannot remove a winning attachment.
Orphan cleanup rechecks rows under a writer lock and immediately
reclaims stale rows and per-store tables; search skips empty stores and
unpublished rows, and uses bounded exact ranking when sqlite-vec's
4,096-candidate limit is exceeded. The loadable extension path is
deployment-controlled; #485 wires its configuration.

BEIR-sized corpus testing exposed the old 64 MiB serialized-corpus limit
and top-k edge cases with duplicate chunks and near ties. This branch
keeps the default exact-search limit at 64 MiB and gives sqlite-vec a
256 MiB limit, validates vector-index coverage, and adaptively fetches
candidates to preserve the requested document count.

Review order: #483 → #484 → #485 → #486 → #34. PostgreSQL vector
indexing remains in #278.

## Test Plan

- Review follow-up: the portable vector map is migration-owned;
extension-specific index SQL lives in
`storage/file_search/sqlite_vec_index.rs`, publication has one
implementation, and writes use `BEGIN IMMEDIATE` without a process-wide
mutex. Focused storage and schema tests passed; the original 3
sqlite-vec integration tests passed, including immediate orphan-row and
orphan-table recovery.
- `SQLITE_VEC_EXTENSION_PATH=/tmp/vec0.so cargo test -p
agentic-server-core --test sqlite_vec_repository -- --ignored`: 4 passed
in CI with sqlite-vec 0.1.9, covering publication, extreme finite
embeddings, restart, filtered and duplicate-chunk search, deletion,
concurrent attachment conflicts, unpublished rows, empty stores, and
searches beyond the 4,096-candidate limit.
- `cargo test -p agentic-server-core --lib`: 1,370 passed, 6 ignored.
`cargo clippy -p agentic-server-core --all-targets -- -D warnings`,
`cargo fmt -- --check`, and pre-commit hooks passed.
- Maral's capacity regression: a new sqlite-vec integration test
publishes a serialized store above 64 MiB, then exercises keyword,
hybrid, and filtered semantic searches against it. The Rust CI run
passed this test and the full ignored sqlite-vec integration suite.
- CI downloads the pinned Linux sqlite-vec release asset, verifies its
SHA-256, and runs the ignored integration tests.

### BEIR retrieval evidence (2026-11-03, benchmark commit `fd6b574`)

Compared the provider's semantic search with [OGX's published
vector-mode
results](https://ogx-ai.github.io/docs/building_applications/rag_benchmarks).
Used the official BEIR **test** corpora, queries, and relevance
judgments, title + body text, `cl100k_base` 512-token chunks with
128-token overlap, `nomic-ai/nomic-embed-text-v1.5` embeddings, and
top-10 document scoring with `pytrec_eval`. The 512/128 setting comes
from [OGX's documented benchmark
config](https://ogx-ai.github.io/docs/building_applications/rag_benchmarks),
but this was a local preparation, not [OGX's full API ingestion
path](https://github.com/ogx-ai/ogx/tree/12a51077cdd4f89b16df5eb6de12a88b0bfcf7df/benchmarking/rag).
A local harness loaded the prepared chunks into the actual
`SqliteVecRepository` and called its `search` method for every judged
query. sqlite-vec 0.1.9 ran on CPU.

| Dataset | Documents / chunks / queries | nDCG@10 OGX vector → ours |
Recall@10 OGX vector → ours | MAP@10 OGX vector → ours |
| --- | ---: | ---: | ---: | ---: |
| NFCorpus | 3,633 / 4,921 / 323 | 0.3106 → **0.3101** | 0.1482 → 0.1462
| 0.1153 → 0.1137 |
| SciFact | 5,183 / 6,604 / 300 | 0.6943 → **0.6968** | 0.8369 → 0.8296
| 0.6442 → 0.6496 |
| ArguAna | 8,674 / 9,278 / 1,406 | 0.3765 → **0.3928** | 0.7610 →
0.8037 | 0.2542 → 0.2624 |

All 2,029 searches succeeded. An independent exhaustive NumPy cosine
calculation on the same embeddings gave identical aggregate nDCG@10 for
SciFact and ArguAna; NFCorpus differed by 0.000084. This validates
sqlite-vec against an exact-cosine oracle on our prepared vectors. The
proximity to OGX's published vector scores is indicative, not exact
parity: OGX's current batch ingestion path applies whitespace cleaning
and appears to use 800/400-token file-processor defaults for automatic
chunking, despite the benchmark config documenting 512/128. The
published run does not include materialized chunk/embedding or per-query
result fixtures, so its exact input and rankings cannot yet be compared.

**Scope and limit:** This is a repository-level semantic retrieval test
with prepared embeddings; it does not exercise the Files/Vector Stores
HTTP APIs, automatic ingestion, hybrid reranking, Responses
`file_search`, or end-to-end answer generation. OGX's fourth BEIR
dataset, FiQA, produces 63,129 chunks and exceeds this branch's
10,000-chunk corpus bound, so full four-dataset parity remains
unvalidated.

---------

Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
@franciscojavierarceo
franciscojavierarceo changed the base branch from codex/file-search-sqlite-vec to main November 6, 2026 04:33
Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
Signed-off-by: Francisco Javier Arceo <4163062+franciscojavierarceo@users.noreply.github.com>
@franciscojavierarceo
franciscojavierarceo merged commit 647bdf2 into main Nov 7, 2026
17 checks passed
franciscojavierarceo added a commit that referenced this pull request Nov 8, 2026
## Summary

Register and execute the Responses `file_search` built-in tool through the existing typed gateway tool loop. The handler searches the configured file-search service, keeps retrieved passages private for model continuation, exposes `file_search_call.results` only when requested, and restores typed file citations in completed and streamed output. This is the top layer of a smaller stack; the Files and vector-store APIs, provider contracts, SQLite-vec adapter, and protocol types are reviewed below it.

Review order: #483 (storage contracts and portable SQL/local providers) → #484 (SQLite-vec) → #485 (Files and vector-store HTTP APIs and provider configuration) → #486 (Responses protocol and stream lifecycle) → this PR. The existing PostgreSQL/pgvector follow-up is #278; later retrieval and lifecycle work remains stacked above it.

The storage service accepts injected `FileSearchRepository` and `FileBlobStore` implementations. The lower layers configure SQLite-vec for semantic retrieval; Milvus and remote blob stores remain adapter extension points.

## Test Plan

- `cargo test -p agentic-server-core --test file_search_tool_test`: 6 passed, covering blocking and streaming calls, citations, opt-in results, mixed client tools, failures, and selector validation.
- `cargo test -p agentic-server-core --lib`: 1,385 passed, 6 ignored on the corrected, restacked file tree. Full workspace `cargo test --offline` also passed on that tree.
- Changed-crate all-target Clippy with warnings denied, formatting, and all-file pre-commit hooks passed on the corrected, restacked file tree.
- The failing Rust CI check at `33b20ba` came from an output-item test fixture missing the typed `logprobs: []` field. The corrected citation projection test passes locally; CI is running on the cleanly restacked head.
- SQLite-vec review fixes from #484 are carried through the stack: atomic publication, safe orphan cleanup, empty/unpublished row handling, and exact fallback above sqlite-vec's candidate limit.

Signed-off-by: Francisco Javier Arceo <arceofrancisco@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants