Commit Graph
7 Commits
Author SHA1 Message Date
Dark-Alex-17 af9622d31c fix(rag): stop routing Qdrant requests through an ambient proxy
make_client used a bare reqwest builder, which honours whatever proxy the
environment advertises. That made it the only HTTP client in Coyote to do so:
utils::set_proxy discards ambient settings and applies only Coyote's configured
proxy, and every other client goes through it.

The symptom is that a perfectly healthy Qdrant is unreachable and the error
belongs to the interposing proxy, not the store, so it reads as a Coyote or
Qdrant fault. Locally an installed Socket Firewall answered `.rag attach`
against 127.0.0.1:6333 with an HTML 'Connection Required' page and HTTP 405.

Both #[ignore]d live tests now pass against a real Qdrant; they failed with that
same 405 before this change, which is the first time either has run green.

A remote store that genuinely needs Coyote's configured proxy is a follow-up:
that means threading the proxy config into the provider.
2026-08-11 22:15:04 -06:00
Dark-Alex-17 1322d73c7b style: further cleanup 2026-08-11 21:50:46 -06:00
Dark-Alex-17 de91ffa517 fix(rag): treat a zero min_score as no floor on Qdrant searches
parse_search_hits filtered on score > min_score, and the only caller passes
0.0. Qdrant Euclid collections score by negative distance, so every hit was
dropped and an attached Euclid collection returned nothing at all, silently.

This is the same trap the surrounding code already documents: score_threshold
is deliberately not sent because it is metric-aware and a 0.0 floor filters
everything out on Euclid. The local filter then reproduced it exactly. Only a
positive floor is now treated as a floor.
2026-08-11 21:07:20 -06:00
Dark-Alex-17 118c346345 feat(rag): support string and UUID Qdrant point IDs
Point ids were read with as_u64() inside a filter_map, so a string id was
silently dropped and a UUID-keyed collection returned zero hits with no error.
The attach wizard therefore refused such collections and told the user to
rebuild with integer ids, which defeats the purpose of attaching to a
collection someone else already built. LangChain, a common way to populate
Qdrant, uses UUIDs by default.

The integer id was never load-bearing for this driver. DocumentId is a packed
(file, chunk) pair used positionally by the local drivers, but an attached RAG
holds no local files or vectors and every positional consumer already returns
early on it, so the id only has to survive the round trip from search back to
the content fetch. Ids that cannot make that trip as a u64 are interned behind
a synthetic handle and restored when the fetch is issued, leaving collections
that already use integer ids on exactly the path they used before.
2026-08-11 14:05:38 -06:00
Dark-Alex-17 ecda258d3a style: Cleaned up some minor styling issues 2026-08-11 13:04:27 -06:00
Dark-Alex-17 3abc30d633 fix(rag): emit an sbx kit v2 mixin and declare RAG credentials to the proxy
The RAG attach sidecar was written against the sbx kit v1 spec and still emitted schemaVersion "1" with network.allowedDomains, network.serviceDomains, network.serviceAuth, credentials.sources.<n>.env and environment.proxyManaged. Every one of those keys was removed in kit v2. Coyote does not validate mixins, it copies them byte-for-byte into spec.yaml, so the invalid document surfaced only as an opaque sbx failure with no indication of which mixin caused it.

generate_rag_sbx_mixin now builds the document from the shared serializer structs instead of a format! string, which is how the envelope drifted unnoticed in the first place. render_mixin_yaml and the RAG sidecar both go through a new render_mixin_document, giving one definition of the envelope and one enforcement point for the rule that every inject domain must also appear in permissions.network.allow.

Fix an auth bug the port exposed: inject_rag_secrets bound the API key with sbx secret set, but nothing ever emitted a matching credentials entry, so the proxy held a value with no inject rule and never rewrote the auth header. An attached RAG credential silently did not work inside the sandbox. The sidecar now declares that credential; a RAG with no API key declares none while still receiving egress.

Fix the service id: the bind passed the raw file stem instead of routing it through secret_service_id, so a RAG named My_Docs produced an illegal id. The bind and the generated credentials service now share that derivation and cannot disagree.

Retire sbx_domain_forms in favour of allow_entry_for_url, now pub(crate). It emitted both a bare host and host:port because v1 serviceDomains needed a bare key; v2 has no such need, so the extra entry is simply wrong. It also defaulted a schemeless host to port 6333 while normalize_base_url resolves it to http and port 80, meaning the allow entry named a port the client never dialled.
2026-08-10 15:58:40 -06:00
Dark-Alex-17 7a732436aa feat(rag): add attach-only Qdrant provider, attach wizard and sandbox wiring
Adds QdrantProvider as a read-only driver for pre-existing remote Qdrant
collections, an interactive '.rag attach' wizard, and the sandbox credential
and domain-whitelisting wiring that lets an attached RAG work inside a sandbox.

Attach-only by design: rebuild_indexes bails for both the attached and the
unattached case rather than silently succeeding. Coyote never writes to Qdrant
in this change.

Vectors are never hydrated back from Qdrant. Cosine collections L2-normalize
stored vectors on write, so reading them back returns unit-length copies of the
originals; the YAML vector copy is authoritative and the serialization guard
stays scoped to the duckdb driver alone.

Collections keyed by string or UUID point IDs are rejected at attach time. The
read path parses point ids as u64 inside a filter_map, so such a collection
would otherwise yield zero results with no error.

The three response-shape parsers are pure functions over an already-parsed JSON
body, unit-tested against captured fixtures, with the async wrappers delegating
to them rather than duplicating the logic.

'.rag' now splits its first argument, so '.rag attach <name>' no longer tries to
load a RAG literally named 'attach <name>'.
2026-08-10 13:40:22 -06:00