* fix: preserve system prompt across tool calls when memories are enabled
The native tool-call loop runs generate_chat_completion with
bypass_system_prompt=True, so the provider layer does not re-apply the
model's default system prompt on tool-call iterations. It relies instead
on metadata['system_prompt'], captured in process_chat_payload, to carry
the full system prompt forward and restore it after RAG injection.
That capture read the model default system prompt from
form_data['params']['system'], but apply_params_to_form_data had already
popped 'params' from form_data, so model_system_prompt was always empty.
metadata['system_prompt'] therefore only captured whatever was already
materialized in the messages. With memories enabled, that is the injected
<memory_context> system message, so tool-call requests were restored with
memory-only system content and the model's system prompt was dropped.
Without memories there was no system message to capture at all.
Capture the model default system prompt from form_data['params'] before
apply_params_to_form_data pops it, and use that value when building
metadata['system_prompt'].
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014Z4L51mvxDJCx1EDxP2vFN
* refactor: condense system prompt capture comment to a single line
Replace the four-line explanation above the model_system_prompt capture with a one-line note. The variable name and the surrounding code already convey what happens; the comment only needs to state why the capture sits before apply_params_to_form_data.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Previously, when web search retrieved pages successfully but saving them to the vector DB failed (for example an unreachable or misconfigured embedding endpoint), process_web_search swallowed the exception at debug log level and still returned status: True with the collection name. The chat then showed "Searched N sites" followed by "No sources found" at retrieval time, hiding the actual misconfiguration from the user and making the failure look like a search bug.
process_web_search now logs the failure at exception level and raises an HTTPException with an actionable message pointing at the embedding configuration in Admin Settings > Documents. chat_web_search_handler surfaces the detail of any HTTPException raised during the search in the emitted error status, so the real cause (embedding misconfiguration, search engine errors, no results) is shown in the chat UI instead of the generic "An error occurred while searching the web". Non-HTTP exceptions keep the generic message, so raw internal error strings are not exposed.
Ref #26750, #25038
The legacy features block in process_chat_payload honoured client-supplied features.image_generation and features.web_search flags and dispatched to the image generation/edit provider and the web-search provider without re-checking the per-user permission that the direct /images routes and the native function-calling path enforce. A user denied features.image_generation or features.web_search could still trigger billable server-side image generation or web search via POST /api/chat/completions with params.function_calling set to legacy. Gate both branches on admin-or-has_permission before invoking chat_image_generation_handler / chat_web_search_handler, matching the existing code_interpreter gate, so a forged flag from an unpermitted user is ignored. Normal completions and permitted users are unaffected.
The chat completion entry point fetched the model row and then check_model_access immediately fetched the exact same row again. Inside the check, the direct grant lookup and every hop of the base-model chain each refetched the caller's group memberships, because neither call passed user_group_ids even though both AccessGrants.has_access and has_base_model_access already accept it.
check_model_access now takes an optional prefetched model_info (used only when its id matches the requested model, so stale callers cannot bypass the lookup) and resolves the caller's group ids once, sharing them across the direct check and the whole base-model chain. The group fetch is skipped entirely for the owner-with-no-base-chain case, which previously needed no groups either.
DB round trips for one completion-entry access check (non-owner model with one base-model hop):
| queries | before | after |
| --- | --- | --- |
| model row SELECTs | 3 | 2 |
| group membership SELECTs | 2 | 1 |
For deeper base-model chains the before column grows by one group SELECT per hop; the after column stays at one.
Functionally verified with stubbed model, group and grant accessors: owner fast path issues no group or grant queries; a non-owner with a base chain resolves groups once and passes the same set to every hop; a prefetched matching model_info skips the duplicate row fetch while a mismatched one is refetched; denial and unknown-model cases still raise; the arena path is unchanged.
convert_payload_openai_to_ollama deep-copied the entire request payload on every completion routed to an Ollama model, and again on every tool-call iteration. The cost of that copy scales with the number of messages and nested content parts in the history, so long chats pay the most, purely as CPU work before the request even leaves the server.
The function only ever mutates two things: it deletes keys on the top-level dict and on the nested options dict. convert_messages_openai_to_ollama already builds fresh message dicts. Shallow-copying exactly those two levels therefore preserves behavior while removing the whole-tree copy.
Benchmark (per conversion call):
| payload | before | after | speedup |
| --- | --- | --- | --- |
| 200-message text chat (~180 KB) | 0.22 ms | 0.057 ms | 4x |
| 20-message chat + 1 MB base64 image | 0.41 ms | 0.38 ms | 1.1x |
The image row barely moves because deepcopy shares immutable strings; the win comes from container-heavy histories, which are exactly the payloads that grow over a conversation's lifetime.
The output is byte-identical to the previous implementation (verified against it, including dict key order, root parameter hoisting, max_tokens remapping, stop handling and response_format precedence), and the caller's payload is left unmodified exactly as before.
stream_wrapper without a content handler iterates aiohttp's response.content, which reads line by line: every line costs a buffer scan, a slice, a bytes concat, a generator resume and its own ASGI response message. A typical SSE event is two lines (the data line and the blank separator), so every upstream token event became two yields and two transport writes even on routes where the body is never inspected.
stream_wrapper now takes passthrough=True, which iterates response.content.iter_any(): the exact same bytes, one yield per network read, no line scanning. It is applied only to routes no internal consumer parses line-by-line: the ollama pull/push/create/generate proxies and its v1 completions, chat completions, messages and responses endpoints, plus the openai embeddings, responses and catch-all proxies. The two internally consumed chat routes keep line iteration, which the streaming middleware and the Ollama-to-OpenAI converter require; the ollama send_request signature documents that constraint.
Benchmark (local aiohttp SSE server, 500 events, consumed through stream_wrapper):
| metric | before (readline) | after (iter_any) |
| --- | --- | --- |
| stream consumption time | 1.46 ms | 0.62 ms |
| generator yields + response writes per stream | 1000 | 1 |
The single yield is a loopback artifact (the whole body arrives in one buffered read); over a real network it becomes one yield per TCP read instead of two per SSE event.
Functionally verified: line mode and passthrough mode produce byte-identical output for the same stream, and passthrough always yields fewer, larger chunks.
_process_picture_url validated the picture URL with validate_url() but then fetched it with a plain aiohttp session that resolves the hostname again at connect time, leaving a DNS-rebinding TOCTOU window (the same gap already closed for the RAG loader, the content probe, the image fetches and webhook delivery). Routing the fetch through get_ssrf_safe_session() pins the connect-time resolution via _SSRFSafeResolver and rejects non-global addresses, so a rebinding host can no longer redirect the fetch to loopback, RFC1918 or cloud-metadata endpoints. It also stops the forwarded OAuth access_token from leaking to a rebound internal target.
Custom per-connection headers can now forward the user's groups to
upstream backends via two new template placeholders:
- {{USER_GROUPS}}: comma-separated group names
- {{USER_GROUP_IDS}}: comma-separated group ids
The group lookup is async, so get_custom_headers becomes an async
wrapper around the sync template substitution (parse_custom_headers)
and fetches groups lazily — only when a header value actually
references a groups placeholder. The external document loader path
runs in a worker thread without an event loop, so Loader.aload
prefetches the groups before offloading and passes them through to
ExternalDocumentLoader.
Claude-Session: https://claude.ai/code/session_01EbBEfTyu8fFJmC13rnQthT
Co-authored-by: Claude <noreply@anthropic.com>
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
`_normalize_token_expiry()` derived the session expiry from the access token alone, and that value is what `oauth_session.expires_at` stores and what both `get_oauth_token()` implementations check to decide whether to refresh five minutes ahead. Providers that issue a shorter-lived id_token than access token (Microsoft Entra ID: roughly 60 minutes against 75) therefore left a window where the session still looked valid while the id_token had already expired, so pipes and tools reading `__oauth_token__["id_token"]` forwarded a dead JWT and downstream services rejected it with 401.
The stored expiry is now capped at the id_token's `exp` claim whenever that JWT expires first, which moves the refresh ahead of the earliest expiring token in the set. This is applied in the single function every session write already passes through, so it covers both the SSO manager and the MCP client manager on their callback and refresh paths alike. Sessions without an id_token, with an opaque one, or with no `exp` claim are unaffected.
Fixes#27066
When a filter's outlet() modified the structured assistant output in place, the change was shown immediately but lost after reload. outlet_filter_handler built its outlet payload with a shallow reference to the message's output list from messages_map, so the filter mutated the stored baseline itself and the subsequent output comparison compared the object against itself, never detecting a change and never persisting it. The same aliasing corrupted originalContent for messages whose text lives only in output. Deepcopy the output when building the outlet payload so messages_map stays a pristine pre-filter baseline and the existing change detection persists outlet-modified output through the existing upsert path. Fixes#27017.
The OAuth / OIDC section in Admin Settings > Authentication had no
enable/disable switch, unlike the LDAP section above it. Add one that
persists via the existing Save flow and actually gates OAuth sign-in,
mirroring how the LDAP toggle works.
- config: new ENABLE_OAUTH persistent config ('oauth.enable'), defaulting
to True so existing deployments with a provider configured keep working.
- oauth: expose ENABLE_OAUTH via the OAuth runtime config and reject the
login and callback handlers with 404 when it is disabled.
- /api/config: report no OAuth providers when disabled so the login page
hides the OAuth buttons (and cannot auto-redirect), without clearing the
admin's provider configuration.
- auths: expose ENABLE_OAUTH through the admin OAuth config get/update
endpoints (OAuthConfigForm + OAUTH_CONFIG_KEYS).
- Authentication.svelte: bind the OAuth / OIDC header Switch to the
persisted oauthConfig.ENABLE_OAUTH and collapse the section when off,
matching the LDAP header (size, weight, alignment).
OpenAPI specs with circular schema references, such as Mealie's where Recipe and RecipeCategory reference each other through properties and array items, crashed convert_openapi_to_tool_payload with a RecursionError, so the tool server produced no specs and the integration never appeared in the model or tool selection. resolve_schema already had a visited-set guard against circular references, but the recursive calls for properties and items dropped the set, so cycles running through those edges were never detected. This threads the visited set through those calls and passes a per-path copy when following a $ref, so only true ancestor cycles are pruned to an empty schema while sibling references to the same schema still resolve fully. Fixes#27239.
The events:chat socket handler called the ownership-checked update for last_read_at, discarded the boolean it returns, and then cancelled the chat's pending timers regardless of the answer. cancel_timers_for_chat selected on the internal marker, the type, the parent chat id and the status, and never on the owner, so it matched rows belonging to any user. An authenticated user who knew another user's chat id could mark that chat read over their own socket session and silently cancel the owner's pending timers, and the owner got no notification: the scheduled action simply never fired.
The missing owner predicate also cut the other way in ordinary use. Because the query matched every timer sharing a parent chat id, one user reading a chat cancelled the timers of anyone else holding one on the same chat, so this was collateral damage as much as an attack.
cancel_timers_for_chat now requires a user_id and filters on it, which is the durable fix, and the socket handler returns early unless the ownership-checked update reports that the caller owns the chat. The parameter is required rather than defaulted so a later caller cannot reintroduce the unscoped query by omission. Both existing call sites already know the acting user. Timer rows are created with the same owner as the parent chat and the execution path already refuses to run one whose owner does not match, so scoping the cancellation the same way cannot strand a timer that would otherwise have fired.
One behaviour change worth noting: an administrator posting into another user's chat no longer cancels that user's chat.user_message timers, because the acting user is the administrator. The timer fires instead of being cancelled, which is the safe direction.
The Socket.IO handshake and the terminal WebSocket route each reimplement JWT authentication instead of going through the HTTP dependency chain. Both verified that the token decoded, that it had not been revoked, and that the user row existed, but neither applied the role check that `get_verified_user` enforces on every HTTP route, so any role outside `user` and `admin` was accepted.
That splits authorization across two planes. Deactivating an account by setting its role to `pending` takes effect immediately over HTTP, which returns 401, while the same JWT still opens a WebSocket. Changing a role disconnects the account's live sockets but does not revoke its token, so the client simply reconnects and gets a fresh session. Until the token expires, four weeks by default, a deactivated account keeps its channel rooms and can still read and write any note it holds an access grant on through the collaborative document handlers.
Resolve the user once, in `get_verified_user_by_token`, and route both WebSocket entry points through it. The role set moves into `VERIFIED_USER_ROLES` so the HTTP and WebSocket gates cannot drift apart, which is the underlying cause rather than either call site on its own. This also replaces five copies of the decode, revocation check and user lookup sequence.
`user-join` now resolves the user instead of reusing the identity cached in `SESSION_POOL`, which costs one extra query per handshake. Gating on the cached role would make the authorization decision depend on every future role-mutation path remembering to tear down the session pool, and that is precisely the invariant that failed here.
A workspace model shared publicly could be used by any user even when its
base model was private. Unregistered base models (no row in the model
table) are admin-only for direct use — get_filtered_models hides them from
non-admins and check_model_access rejects them — but has_base_model_access
treated a missing row as "no ACL" and allowed the chained request through.
has_base_model_access now takes the caller's role and only allows an
unregistered base model hop for admins, so a shared preset can no longer
reach a base model the caller could not use directly. Registered base
models keep their existing grant-based enforcement.
Claude-Session: https://claude.ai/code/session_018toPfJW1hMXAhokGaL43Ep
Co-authored-by: Claude <noreply@anthropic.com>
Docker compose list-form environment syntax passes quotes through verbatim, so WEB_FETCH_FILTER_LIST="" reaches the backend as two literal quote characters rather than an empty string. Config parsing turned that into the filter entry '""', which has no "!" prefix and therefore landed in the allow list. A non-empty allow list requires every host to match one of its entries, and a quotes-only pattern can never match a hostname, so every fetch_url and web loader request was rejected with "URL blocked by filter list" and surfaced to the user as "The URL you provided is invalid".
get_allow_block_lists now strips surrounding quote characters from each entry and drops entries that are empty after normalisation. Quoted but otherwise valid entries such as "example.com" or !"example.com" now behave as their unquoted forms, and garbage entries no longer convert the default blocklist into a match-nothing allowlist that blocks everything.
Fixes#26908
get_accessible_folder_files is the server-side filter that reduces a folder's attached-knowledge list (and, once #26723 lands, a direct model's) to the entries the caller may read, before that list is handed to the builtin knowledge tools as `__model_knowledge__`. It validated `file` and `collection` entries but passed `note` entries through unchecked (they fell into the `else` keep-as-is branch), even though notes are a first-class attached-knowledge type that flows through this list.
No current caller is exploitable, because every note consumer (`query_knowledge_files`, `view_note`, and the legacy retrieval path) independently re-checks note access before returning content. But relying on each consumer to remember that check is exactly the fragility this helper exists to remove, and the same `_has_read_access_to_file` membership short-circuit that makes an unvalidated `file` entry dangerous would turn any future note path that trusts list membership into an IDOR. Validate notes here so the filter enforces its own contract instead of leaning on downstream re-checks.
A note entry is now kept only when the caller owns it or holds a read grant. Notes are private by default and carry no self-grant, so ownership is checked explicitly alongside the grant lookup. Admins still bypass all checks and genuinely unknown types are still kept as-is.
Related: #26723
When WEBSOCKET_MANAGER=redis, app.state.MODELS and the socket session/
usage pools are Redis-backed dicts, so every membership test and
getitem is a network round trip:
- generate_chat_completion checked `model_id not in models` (HEXISTS)
and then read `models[model_id]` (HGET) on every chat completion.
A single .get() now serves both, with the same not-found error.
- The direct-connection branch spread the pool with `{**MODELS, ...}`,
which iterates keys() then fetches each value — HKEYS plus one HGET
per model. dict(MODELS.items()) issues a single HGETALL instead.
- get_user_ids_from_room called SESSION_POOL.get(sid) twice per
session (once to filter, once for the value); the usage handler
checked membership then fetched the same key. Both now do one
lookup.
In non-Redis mode these are plain dicts and behavior is identical.
Claude-Session: https://claude.ai/code/session_01MHg5zs1VBjvRWQ54qHpfYD
Co-authored-by: Claude <noreply@anthropic.com>
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true
USE_CUDA_VER=cu126
free_disk:true name:cuda126 suffix:-cuda126]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Waiting to run
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Waiting to run
The streaming handler's content accumulator is a closure cell (declared nonlocal in stream_body_handler), and CPython's in-place string append optimization only applies to plain local variables (STORE_FAST), never to cell variables (STORE_DEREF). The content += value form introduced in #27231 therefore still allocates and copies the full accumulated string on every delta, exactly like the f-string it replaced; whether that copy is cheap or expensive is up to the allocator, and measurements swing accordingly (6 to 83 ms of pure copying for a 400 KB response on Python 3.12, against 0.3 ms for this patch).
Accumulate the deltas in a list instead and join once at the single read site (publish_chat_finished_event at stream end). List append is amortized O(1) with no dependence on reference counts, bytecode specialization or allocator behaviour, so accumulation is O(n) by construction. The non-str fallback keeps the previous f-string coercion semantics.
Verified end to end against a mock SSE upstream: a streamed chat with a think-tag block plus 40 content deltas produces output items, message text, reasoning text and usage identical to current dev, with no errors in the server log.
