Partial backport to stable/1.103.x: only the text completion endpoint test moves off the retired gpt-3.5-turbo-instruct to openai/gpt-5.4-nano with reasoning off. This line predates the OpenAI SDK rewrite of the test, so reasoning_effort goes through EndpointsClient.text_completions instead of extra_body. The SAIL, spend-log and coverage registry repairs are not needed for this line's e2e suite
(cherry picked from commit e61733b170)
Partial backport to stable/1.103.x: only the Together AI structured-output e2e case moves to the hybrid reasoning backend with reasoning off, since the reasoning-only model it picked returned no content. The CI infrastructure and other test repairs are not needed for this line's e2e suite
(cherry picked from commit 6ca90b927c)
* revert(responses): revert "fix(responses): keep gpt-5.4/5.5 tool calls on chat and merge bridged tool calls into one choice" (#44295)
This reverts commit ca1994e403.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): merge bridged tool calls into the same choice as the text
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 5724117116)
* fix(proxy): stamp the client alias on a copy of each streamed chunk so pricing sees the deployment model
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(spend): streamed alias matching a capability rule bills the deployment price
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(spend): assert every streamed chunk carries the client alias
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(logging): log the client alias on the priced streamed response, the same as non-streamed
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 7b432d78d2)
The pinned base's /etc/apk/world locks glibc-2.44=2.44-r1, so the apk upgrade in the runtime stage cannot move it. The new digest ships 2.44-r6 on amd64 and arm64
(cherry picked from commit bc911abdbb)
schema.prisma still declares the LiteLLM_SpendLogs (api_key, startTime) and (litellm_call_id) indexes while their migrations are now SELECT 1, so the v1 resolver's drift script recreated both with a blocking CREATE INDEX at boot. The drift script now drops those two statements before it is applied, matching filter_request_log_index_diff on main. The key metadata recovery fixture builds its index directly and the schema sync test exempts the two indexes.
ENFORCE_PRISMA_MIGRATION_CHECK now defaults to true in both the proxy CLI and the standalone migration entrypoint, with ENFORCE_PRISMA_MIGRATION_CHECK=false or --no-enforce_prisma_migration_check as the opt-out. The two LiteLLM_SpendLogs index migrations become SELECT 1 so operators build those indexes online by hand.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): restore pre-config-wins handling of pass-through endpoints
Config-wins (#41779) made general_settings.pass_through_endpoints a config-owned key. The DB reader then got the config list back as if it were DB rows, re-registered each entry without forward_headers on every DB sync, and the stripped copy won the route lookup, so a config pass-through with forward_headers: true stopped forwarding Authorization. UI create, update and delete of pass-throughs were also rejected while the config declared any.
This puts pass-throughs back on their pre-#41779 path: the settings store no longer lets the config own the key, the config list is captured env-resolved at load_config, each DB sync merges DB entries with config entries on paths the DB does not declare, and /config/field/info reads the stored rows only. A UI pass-through write re-applies that merge immediately so the config entries stay served until the next sync.
* fix(proxy): keep config pass-throughs in every reload of the merged list
get_config now returns DB pass-throughs plus config ones on other paths,
each DB sync republishes that merged list, and /config/field/info reads
pass_through_endpoints from the DB row so a UI write never drops stored
entries when models are not stored in the DB
* fix(proxy): keep serving pass-throughs while the config file reloads
load_yaml cleared the runtime pass-through list, so auth: false routes
answered 401 while get_config awaited the database
* fix(proxy): read stored pass-throughs from the writer before a UI write
A lagging read replica could return an older list, and the UI create and
edit flows write the whole field back
* fix(proxy): apply config file pass-through auth changes on reload
The kept runtime list was merged as if it were DB entries, so an edited
config entry on the same path was dropped. Merge the stored DB row with
the fresh config instead, and give the field-info test mock a writer
* fix(proxy): keep pass-throughs served while a DB sync reads the database
get_config resets the stored DB rows before reading them again, which
cleared the served pass-through list and made auth: false routes answer
401 for the length of the read
* refactor(proxy): move the settings store reload out of the loop
basedpyright rejects a Final variable assigned inside a loop
(cherry picked from commit 2eb2bf130b)
Hand-ported prerequisite for the #43642 backport to stable/1.103.x.
Taken from dd636373229b1ab3bfb2ed5b9b17b0ebd68b3ac7 (#43288, main), scratch_database only.
The proxy never forwards client anthropic-beta headers to azure_ai, so Foundry
400s on safeguards without the beta. Add it on the provider side when the request
carries safeguards, the way the Vertex path does.
Foundry answers safeguards without the dangerous-tool-use-2026-09-03 beta
with a 400, and the azure_ai beta map dropped that beta, so Claude Code auto
mode requests through the gateway turned from 200 into 400 once safeguards
started passing through
Adds a test-quality-ok marker on the one patch.object the picked Vertex test needs, since the GCP token exchange runs before the faked HTTP boundary. Test-only, no runtime change.
Backport of #42288 to stable/1.103.x.
Cherry-picked from fc82f6e8fa (main, first parent). Its Bedrock Mantle beta map and Mantle-only test are left out, since this line has no bedrock_mantle beta map and its Mantle messages path reuses the Bedrock Invoke one.
* fix(proxy): unregister logging callbacks removed from the stored config
POST /config/callback/delete saved the config and resynced, but the resync only
ever added callbacks, so a deleted callback kept exporting and kept showing in
/get/config/callbacks as read-only on every worker.
ProxyConfig now tracks which callback list entries each DB config sync
registered and unregisters them once the stored config stops listing them.
Callbacks it did not register (YAML, code) are never touched, and a failed
config load skips the sync instead of treating the config as empty.
* refactor(proxy): keep callback sync comprehensions to one for clause
* test(e2e): tolerate provider-side flakes on five full-suite cells (#42628)
* test(e2e): tolerate provider-side flakes on five full-suite cells
Mistral OCR retries a provider-relayed 429 with backoff, the Vertex vision
probe turns reasoning off so its 32 tokens go to the answer, the Vertex
cache cell spaces eight never-seen prefixes 15s apart around Google's
nondeterministic minimum-token rejection and prices the cached tokens
instead of prompt_tokens, and the Azure content-policy cell resends the
jailbreak prompt while Azure skips its filter
* test(e2e): shorten the new helper docstrings
* test(e2e): accept a relayed provider 429 on the rust OCR cells
The gateway already retries a provider 429 three times per call and the
Mistral key is shared across pipelines, so a throttle can hold across all
four attempts of the OCR cell. After the bounded retries the cell now
accepts the gateway's faithful relay of the provider's 429 (throttling_error,
code 429) as its second expected outcome; the gateway's own 429 and any
other error still fail the cell at once.
* test(e2e): drop the harness unit tests, the live cells cover the helpers
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
(cherry picked from commit 41ca4656cd)
* fix(streaming): keep litellm Usage on text-completion usage chunks (#43047)
* fix(streaming): keep litellm Usage on text-completion usage chunks
* fix(streaming): convert provider usage to litellm Usage instead of dropping it
(cherry picked from commit be35b22dfc)
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
The batch cleanup leftover warning used a class defined in a test-directory module. The xdist controller cannot import it, so an uncaught leftover warning crashed the whole e2e run. It is now a plain UserWarning.
The integration harness backport missed the workers option and Gateway.request headers that the OTel conversation id tests use.
Backports the batch cleanup half of #43321 so an Azure cancel still in progress after 120s leaves a warning instead of a teardown error, and points the MCP Tools UI test at DeepWiki's renamed ask_wiki_question tool.
