Restore the embed-style behavior so OCIChatConfig.get_complete_url always
appends the OCI GenAI chat path. Routing through get_oci_base_url ensures the
optional explicit api_base has its trailing slash stripped before the suffix is
joined, matching the embed config and the test_respects_explicit_api_base
expectation.
- Use SerializeAsAny on CohereChatRequest.chatHistory so subclass-specific
fields like CohereToolMessage.toolResults are not dropped during Pydantic
v2 serialization.
- Make OCIEmbedConfig.get_complete_url append the /20231130/actions/embedText
action path consistently with chat, so setting litellm.api_base to the
region inference base URL no longer posts to the bare hostname.
- Map OCI finishReason (COMPLETE / MAX_TOKENS / TOOL_CALLS) to OpenAI
finish_reason values in handle_generic_response, mirroring the streaming
handler and the Cohere non-streaming handler.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
handle_cohere_response now sets message.content to None when the Cohere
response text is empty, matching the OpenAI convention for tool-call-only
responses.
handle_cohere_stream_chunk now extracts toolCalls — both directly from
the chunk and from the terminal chunk's chatHistory CHATBOT message —
and emits them in the delta. Previously, CohereStreamChunk lacked a
toolCalls field, so any tool calls in the stream were silently dropped.
- Cohere param map: keep tool_choice/n as False (not omitted) so unsupported
params are dropped or rejected rather than silently passed through.
- get_complete_url: when an explicit api_base/litellm.api_base is provided,
use it as-is instead of unconditionally appending /20231130/actions/chat
(mirrors the embed config behavior).
- Cohere stream: require both chatHistory and finishReason to be present to
identify a terminal consolidation chunk, avoiding silent text suppression
if chatHistory ever appears on a non-terminal chunk.
- Generic usage: use 'is not None' for reasoningTokens so a legitimate value
of 0 is preserved instead of being treated as absent.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
- Drive OCI maxCompletionTokens via supports_reasoning from the model
catalog instead of a hardcoded openai.gpt-5 prefix. Add OCI GPT-5 family
entries (gpt-5, gpt-5-mini, gpt-5-nano) with supports_reasoning: true.
Gate the override to non-Cohere vendor so Cohere reasoning models keep
maxTokens (Cohere endpoint does not accept maxCompletionTokens).
- Replace proxy-specific 'Contact your proxy admin' phrasing in the four
Router blocked-deployment ServiceUnavailableError messages with neutral
SDK-appropriate text.
OpenAI retired `gpt-4o-audio-preview` (404 model_not_found in CI as of
2026-05-19), and the existing try/except in these tests only re-raised
on 'openai-internal' errors. Other exceptions were silently swallowed,
so the next line ran with an unbound `response`/`completion` and
failed with an unrelated UnboundLocalError that masked the real cause.
Extend the skip condition to also cover model_not_found / 'does not exist'
so the suite reports the upstream outage cleanly, matching the pattern
used in ce87c41 for the realtime and nvidia_nim rerank tests.
Re-raise unknown exceptions instead of falling through.
Anchor oci_region to ^[a-z][a-z0-9-]{0,30}[a-z0-9]$ inside get_oci_base_url
so user-supplied regions that would redirect the signed request to an
attacker-controlled host (e.g. 'evil.com/#') fail with HTTP 400 before
the URL or signature is built. Empty string still falls back to the
us-ashburn-1 default, so existing callers are unaffected.
* refactor(bedrock/sagemaker): switch to lazy loading for response stream shapes
- Replace eager loading of BEDROCK_RESPONSE_STREAM_SHAPE and SAGEMAKER_RESPONSE_STREAM_SHAPE with lazy loading via get_bedrock_response_stream_shape() and get_sagemaker_response_stream_shape() respectively.
- This change optimizes performance by avoiding unnecessary imports and logging warnings unless the response stream shapes are actually needed.
- Update relevant classes and tests to utilize the new lazy loading functions, ensuring consistent behavior across the codebase.
* test(bedrock/sagemaker): add fixtures to clear response stream shape cache
- Introduced `_reset_bedrock_response_stream_shape_cache` and `_reset_sagemaker_response_stream_shape_cache` fixtures to prevent lru_cache leakage between tests in their respective modules.
- Updated tests to utilize these fixtures, ensuring that the response stream shape cache is cleared before and after each test run.
- Added `pytest.importorskip("botocore")` to ensure that tests are skipped if the botocore library is not available.
* fix(proxy): decode bytes and pass-through SSE for Google-native streamGenerateContent (#27444)
* fix(proxy): address Greptile review on Google-native SSE bytes path
Remove unreachable try/except around SSE pass-through yield and add a
unit test covering pre-formatted SSE bytes, terminator padding, and
non-SSE byte fallback wrapping.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Tai An <antai12232931@outlook.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(ui): add Interactions API support to playground with streaming
Adds /v1beta/interactions as a selectable endpoint in the UI playground.
Uses SSE streaming (stream=true) and parses content.delta events for real-time output.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(interactions): remove forced gemini provider so all providers work via interactions API
Proxy endpoint was hardcoding custom_llm_provider="gemini" before routing,
preventing non-Gemini models from using the litellm_responses bridge.
Also reverts the UI Gemini-only model filter.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(interactions): fix streaming for non-gemini providers via bridge
Two bugs in LiteLLMResponsesInteractionsStreamingIterator:
1. content.delta was emitted without "type":"text" in delta dict, so the
UI type-check always failed and no tokens were displayed
2. First OutputTextDeltaEvent was silently dropped (used to emit content.start
with empty text); fixed by handling ResponsePartAddedEvent for content.start
so text deltas go directly to content.delta
Co-authored-by: Cursor <cursoragent@cursor.com>
* undo unrelated changes
* fix(ui): extract model from top-level field in interactions bridge events
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* test(interactions): remove tautological gemini-provider assertion
The test_no_forced_gemini_provider_in_request_data check only asserted
against dict literals it had just constructed, so it always passed and
did not exercise the create_interaction endpoint. The endpoint
deliberately defaults custom_llm_provider to gemini, so the assertion
was also factually incorrect. Drop the misleading test.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(interactions): use ContentPartAddedEvent and guard interaction.start ordering
- ResponsePartAddedEvent corresponds to reasoning summary parts, not text
content parts. Use ContentPartAddedEvent which is the event emitted before
text output deltas (type response.content_part.added).
- Mirror the OutputTextDeltaEvent ordering guard: if interaction.start has
not been sent yet, emit it first before content.start to honor the
documented event ordering contract.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* test(interactions): cover ContentPartAddedEvent ordering and no-op paths
* fix(tests): treat corrupt VCR cassette payloads as cache miss + use gpt-realtime in OpenAI realtime guardrails test
VCR redis persister was raising UnicodeDecodeError on cached payloads that
fail to UTF-8 decode (e.g. legacy entries written by another version of
the persister), failing tests at fixture setup instead of degrading to a
cache miss. Wrap decode+deserialize in a try/except so corrupt cache
entries are treated as CassetteNotFoundError, surfacing the failure via
the existing _record_cache_failure / VCRCassetteCacheWarning path.
OpenAI shut down gpt-4o-realtime-preview-2024-12-17 (and the entire
gpt-4o-realtime-preview family) on 2026-05-07. The live realtime
guardrails integration test now fails with model_not_found instead of
receiving session.created. Point OPENAI_REALTIME_URL at the current GA
model gpt-realtime, and relax the assertion in
test_text_message_blocked_by_guardrail_no_ai_response to also accept the
model's refusal-to-repeat the block message (gpt-realtime declines
verbatim-repeat instructions, which is still a safe outcome since the
original user message was blocked before reaching OpenAI). The
BLOCKED_PHRASE leak check is preserved as a hard invariant.
* fix(tests): migrate realtime + nvidia_nim rerank tests off shut-down upstream models
OpenAI shut down the entire gpt-4o-realtime-preview family (including the
undated alias) on 2026-05-07. The live realtime tests still connected
with that dead alias and failed with messages_received=1 (an error event
'The model gpt-4o-realtime-preview does not exist' instead of
session.created). Point the live OpenAI realtime tests at gpt-realtime,
the current GA realtime model:
- test_openai_realtime_simple.py: get_model() -> gpt-realtime
- test_openai_realtime.py: test_openai_realtime_direct_call_no_intent and
test_openai_realtime_direct_call_with_intent -> openai/gpt-realtime
Mocked unit tests (test_realtime_query_params_construction,
test_realtime_query_params_use_normalized_model_name) are left as-is:
they never hit the network and assert string plumbing only.
NVIDIA reached end-of-life for the hosted
nvidia/llama-3.2-nv-rerankqa-1b-v2 rerank API on 2026-05-18 with no
published replacement, so the live BaseLLMRerankTest.test_basic_rerank
for nvidia_nim now returns HTTP 410 ('Gone'). NVIDIA's hosted catalog
rotates on a schedule, so swapping in another live model would only
defer the failure. Override test_basic_rerank in TestNvidiaNim to mock
the sync/async HTTP transport (same pattern as
test_nvidia_nim_rerank_ranking_endpoint in this file) and inject a fake
NVIDIA_NIM_API_KEY via monkeypatch. The request/response transformation
and cost calculation stay covered offline.
* test(callbacks): harden flaky proxy callback-leak detector
The proxy callback-leak detector (test_check_num_callbacks_on_lowest_latency)
was failing on this PR with 'abs(85 - 95) <= 4' — a bounded one-time
registration jump caused by switching to latency-based-routing
(+LowestLatencyLoggingHandler, +SlackAlerting). The count then plateaus
under load, so this is pollution from the test's own config update, not a
leak.
Replace the brittle two-sample diff threshold with a sampler that settles
past the deliberate config switch and only flags sustained monotonic
per-type growth, with a terminal-burst confirmation pass for leaks that
would otherwise escape the >=2-interval guard. Normalizes instance
addresses so identical callbacks at different memory locations collapse,
and names the leaking type on failure.
* fix(interactions): preserve first text token when both start events are missing
When OutputTextDeltaEvent arrived before any ResponseCreatedEvent or
ContentPartAddedEvent, the double-fallback path emitted interaction.start
and silently dropped the first delta's text — the second delta's
content.start carried only that chunk's delta, and the first token never
made it to any content.delta event consumed by the UI.
Queue a content.start that carries the first delta's text alongside the
interaction.start emission, and drain pending events before pulling the
next upstream chunk.
* chore(ui): remove unused InteractionOutput/InteractionResponse interfaces
Co-authored-by: Yassin Kortam <yassin@berri.ai>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(deepseek): route messages api through anthropic config
Add a DeepSeek-specific Anthropic Messages config so deepseek/... models use the native messages endpoint and preserve thinking blocks. Strip Anthropic custom tool type markers that DeepSeek rejects while keeping hosted tool types intact.
* fix(deepseek): normalize anthropic messages api base
Handle OpenAI-style DeepSeek api_base values ending in /v1 or /v1/messages by stripping those suffixes before adding the /anthropic messages path.
* chore(deepseek): format messages transformation
* chore(deepseek): add test package markers
* fix(deepseek): tighten anthropic url path check and fall back to DEEPSEEK_API_BASE
Author: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
* fix(tests): normalize smart quotes in realtime guardrail refusal check
gpt-realtime nondeterministically returns refusals with Unicode curly
apostrophes (e.g. 'I’m sorry, but I can’t assist with that.'), but the
safe_markers tuple in test_text_message_blocked_by_guardrail_no_ai_response
only contains straight ASCII apostrophes. The substring match then fails
even though the response is a clear refusal, flipping CI red.
Normalize the AI text to ASCII quotes before the marker check so both
straight and curly variants count as safe outcomes.
* fix(deepseek): drop redundant anthropic v1/messages endswith check
* fix(deepseek): strip /beta suffix in anthropic messages URL normalization
Co-authored-by: Yassin Kortam <yassin@berri.ai>
---------
Co-authored-by: Felipe Rodrigues Gare Carnielli <felipe.gare@hotmail.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(bedrock): sanitize batch metadata to prevent Pydantic ValidationError
Proxy guardrail hooks (Model Armor, OpenAI Moderations) and internal
processing inject non-string values (dicts, floats) into the request
metadata. When the Bedrock batch handler passes this metadata directly
to LiteLLMBatch (which inherits OpenAI's Batch Pydantic model with
metadata: Dict[str, str]), Pydantic raises a ValidationError. This
causes the router retry loop to re-submit the same Bedrock job
multiple times before ultimately failing.
Add _get_openai_compatible_batch_metadata() that serializes non-string
values to JSON strings via safe_dumps, skips None values and internal
logging keys, ensuring the response object always validates.
* test(bedrock): add tests for batch metadata sanitization
Covers _get_openai_compatible_batch_metadata: string passthrough, dict/float
serialization, None/internal key exclusion, and LiteLLMBatch compatibility.
---------
Co-authored-by: Noah Nistler <60981020+noahnistler@users.noreply.github.com>
* test(callbacks): TEMP diagnostic probe for callback-leak flake
Hardened leak detector (sample N, flag sustained monotonic per-type
growth, normalize instance addresses) + a temporary always-fail probe
on test_check_num_callbacks_on_lowest_latency that dumps the per-type
series and raw reprs via the JUnit failure message, to settle real-leak
vs bounded-pollution on CCI. Diagnostic block is clearly marked and
will be reverted before the PR.
* test(callbacks): harden proxy callback-leak detector, drop diagnostic
CCI diagnostic confirmed the 85->95 jump is a bounded one-time
registration from the test's own switch to latency-based-routing
(+LowestLatencyLoggingHandler, +SlackAlerting), flat at 95 for 2.5 min
under load — not a leak. Final detector: settle past the deliberate
config/update, sample N times, flag only sustained monotonic per-type
growth, normalize instance addresses, name the leaking type on failure.
Removes the temporary always-fail probe.
* test(callbacks): address review - drop redundant settle, close terminal-burst blind spot
- test_check_num_callbacks: remove leftover sleep(30) before sleep(SETTLE_SECONDS) (60s -> 30s dead wait).
- Add _terminal_suspects + _detect_leaks_confirmed: when monotonic net growth is confined to the final interval (escapes the >=2-interval guard), take one confirmation sample. A real ongoing leak keeps climbing and is flagged; a one-time terminal registration plateaus and is ignored.
* feat(prometheus): add user_email and user_alias to user budget metrics
User budget Prometheus gauges now expose human-readable labels alongside
user_id, matching team and API key budget metrics for Grafana filtering.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(prometheus): gate user budget email/alias labels behind opt-in flag
Address greptile review: adding labels to existing metrics is a
breaking cardinality change. Gate behind
prometheus_user_budget_label_include_email_alias=True (default: False)
so existing dashboards and recording rules are unaffected.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(opentelemetry): JSON-serialize dict metadata fields for OTEL span attributes (#27451) (#27455)
Squash-merged by litellm-agent from Anai-Guo's PR.
* feat(dashscope): add embeddings and reranks(qwen3-rerank) support via OpenAI-compatible endpoint (#27508)
Squash-merged by litellm-agent from yimao's PR.
* fix(vertex_ai/gemini): raise BadRequestError when image_url or url fi… (#24550)
Squash-merged by litellm-agent from krisxia0506's PR.
* fix(vertex_ai): raise error on mid-stream 429/error chunks instead of silently swallowing (#23711)
Squash-merged by litellm-agent from krisxia0506's PR.
* fix: raise BadRequestError for file content blocks missing 'file' sub… (#24503)
Squash-merged by litellm-agent from krisxia0506's PR.
* Fix Gemini MIME detection for extensionless GCS URIs (#27278)
Squash-merged by litellm-agent from krisxia0506's PR.
* fix(vertex_ai/partner_models): drop unused vertexai SDK gate from count_tokens (closes#28084) (#28107)
Squash-merged by litellm-agent from voidborne-d's PR.
* feat(chart): add support for autoscaling behavior in HPA (#27990)
Squash-merged by litellm-agent from FabrizioCafolla's PR.
* feat(proxy): add blocked flag to models for pause/resume from the UI (#27927)
Squash-merged by litellm-agent from Cyberfilo's PR.
* fix: pass socket timeouts to Redis cluster clients (#27920)
Squash-merged by litellm-agent from tomdee's PR.
* Fix/cache token (#28009)
Squash-merged by litellm-agent from escon1004's PR.
* fix(deepseek): forward reasoning_content in multi-turn thinking mode conversations (#28080)
Squash-merged by litellm-agent from Divyansh8321's PR.
* fix(guardrails): return HTTP 400 instead of 500 for blocked requests (#27617)
* fix: reset org and tag budgets (#27326)
* reset org budgets
* reset tag budgets
---------
Co-authored-by: Michael Riad Zaky <michaelr@Mac.localdomain>
* fix(ui): omit allowed_routes from key edit save when unchanged (#27553)
* fix(ui): omit allowed_routes from key edit save when unchanged
When a team admin opens Edit Settings on a key with key_type=AI APIs and
saves without changing anything, the UI re-sends the existing allowed_routes
value, which the backend's _check_allowed_routes_caller_permission gate
rejects for non-proxy-admins (LIT-2681).
Strip allowed_routes from the patch in handleSubmit when it deep-equals the
original keyData.allowed_routes. The backend treats absence as "leave alone,"
so no-op saves now succeed for non-admins. Admins explicitly editing the
field still send the new value.
* fix(ui): order-insensitive allowed_routes diff + cover null-original case
Address Greptile review:
- Switch the "is allowed_routes unchanged" check to a Set-based comparison so
a server-side reorder of the array doesn't register as a user edit and
re-trigger LIT-2681.
- Add two regression tests: (1) keyData.allowed_routes is null and the form
is untouched — patch should strip the field; (2) server returned routes in
a different order than the user originally entered — patch should still
recognize the value as unchanged.
* chore(ui): strip ticket refs and tighten comments in key edit fix
- Remove internal-tracker references from in-code comments
- Tighten the WHY comment in handleSubmit to two lines
- Drop redundant test-block comments — test names already describe the case
* fix(ui): annotate Set<string> generic in allowed_routes diff to fix tsc
* fix(guardrails): return HTTP 400 instead of 500 for guardrail-blocked requests
GuardrailRaisedException and BlockedPiiEntityError both lacked a
status_code attribute. When these exceptions reached the proxy
exception handler (getattr(e, 'status_code', 500)), the fallback
defaulted to HTTP 500 — making intentional guardrail blocks
indistinguishable from server errors and causing unnecessary client
retries.
Changes:
- Add status_code=400 (keyword-only) to GuardrailRaisedException
- Add status_code=400 (keyword-only) to BlockedPiiEntityError
- Update _is_guardrail_intervention() to recognize both exceptions
so downstream loggers record 'guardrail_intervened' instead of
'guardrail_failed_to_respond'
- Add 6 unit tests for default/custom status codes and getattr pattern
- Strengthen existing blocked-action test with status_code assertion
Fixes#24348
---------
Co-authored-by: Michael-RZ-Berri <michael@berri.ai>
Co-authored-by: Michael Riad Zaky <michaelr@Mac.localdomain>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
Co-authored-by: Krrish Dholakia <krrish+github@berri.ai>
* fix(router/proxy): address Greptile P1+P2 review comments on PR #28161
- router: raise ServiceUnavailableError (503) instead of RouterRateLimitErrorBasic (429)
when a specifically-addressed deployment is administratively blocked; 429 misleads
retry-enabled clients into spinning forever against a paused model
- proxy_server: compute get_fully_blocked_model_names() once before both branches in
model_list() instead of duplicating the call in each branch
- deepseek: upgrade silent debug log to warning when injecting placeholder
reasoning_content so callers are clearly notified of degraded multi-turn quality
- tests: update two blocked-deployment assertions to expect ServiceUnavailableError
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix: address bug detection findings (cache token order, mutable defaults)
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix: address bugs in async pass-through, anthropic cache token detection, rerank tests
- async_get_available_deployment_for_pass_through: enforce blocked check on specific deployments
- cost_calculator: detect anthropic-style usage by attribute presence (not truthiness) to avoid mixing OpenAI cached_tokens into anthropic normalization when read=0
- dashscope rerank tests: pass request to httpx.Response constructions for consistency
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix code qa
* fix(vertex_ai/gemini): strip MIME parameters from GCS contentType
GCS object metadata's contentType field can include parameters such as
'text/html; charset=utf-8'. Strip them in _apply_gemini_mime_type_aliases
so downstream get_file_extension_from_mime_type sees a bare MIME type.
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(vertex_ai/gemini): clarify mime-type error message string concatenation
Co-authored-by: Yassin Kortam <yassin@berri.ai>
---------
Co-authored-by: Tai An <antai12232931@outlook.com>
Co-authored-by: Vincent <yimao1231@gmail.com>
Co-authored-by: Kris Xia <xiajiayi0506@gmail.com>
Co-authored-by: d 🔹 <liusway405@gmail.com>
Co-authored-by: Fabrizio Cafolla <developer@fabriziocafolla.com>
Co-authored-by: Filippo Menghi <113345637+Cyberfilo@users.noreply.github.com>
Co-authored-by: Tom Denham <tom@tomdee.co.uk>
Co-authored-by: escon1004 <70471150+escon1004@users.noreply.github.com>
Co-authored-by: Divyansh Singhal <97736786+Divyansh8321@users.noreply.github.com>
Co-authored-by: robin-fiddler <robin@fiddler.ai>
Co-authored-by: Michael-RZ-Berri <michael@berri.ai>
Co-authored-by: Michael Riad Zaky <michaelr@Mac.localdomain>
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
Co-authored-by: Krrish Dholakia <krrish+github@berri.ai>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(caching): replay openai/responses bridge cache hits as chat streams
When chat completions route through openai/responses, cached ModelResponse
payloads under aresponses keys were deserialized as ResponsesAPIResponse
(500) or re-translated as responses events (empty streaming deltas). Deserialize
chat-shaped cache entries as acompletion and bypass the responses stream iterator
for cached CustomStreamWrapper replay.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(caching): map responses bridge call_type for sync vs async stream replay
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix: handle ModelResponse cache return in responses bridge and drop dead acompletion check
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(caching): detect chat cache hits via object field before choices fallback
Prefer chat.completion object type over the broad choices-key heuristic so
Responses API cached payloads are not misclassified if their schema changes.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(caching): cover responses bridge cache-hit paths in CI-tracked test suite
The new bridge cache replay logic in caching_handler.py and the
preformatted-stream guard in litellm_responses_transformation/handler.py
were exercised only by tests under tests/local_testing/, which the
responses-caching-types and misc shards do not run. Codecov flagged the
patch as 29.72% covered.
Add equivalent unit tests under tests/test_litellm/ so the responses,
caching, types, and misc shards execute them and ship their coverage
data to Codecov:
- _is_chat_completion_cached_dict happy/sad paths
- aresponses streaming bridge cache hit -> CustomStreamWrapper
- responses non-streaming bridge cache hit -> ModelResponse
- legacy ResponsesAPIResponse stream + non-stream replay
- _is_preformatted_cached_chat_stream true/false
- completion/acompletion early return on cached ModelResponse
- completion/acompletion skip rewrap on preformatted cached stream
* fix: add negative guard on object field in _is_chat_completion_cached_dict
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(vcr): treat corrupt cassette payloads as cache miss
* test: bump EOL'd NVIDIA rerank and OpenAI realtime models in CI
The NVIDIA hosted rerank endpoint for nvidia/llama-3_2-nv-rerankqa-1b-v2
reached end-of-life on 2026-05-18 and now returns HTTP 410 Gone, breaking
TestNvidiaNim::test_basic_rerank. Switch to nvidia/nv-rerankqa-mistral-4b-v3,
which is still hosted on the NVIDIA API catalog and is already listed in
model_prices_and_context_window.json.
OpenAI also retired the gpt-4o-realtime-preview-2024-12-17 model used by
test_realtime_guardrails_openai (now returns model_not_found). Switch the
realtime test URL to the GA gpt-realtime alias.
Unrelated to the responses-bridge cache fix in this PR, but committing
here to unblock CI per maintainer guidance.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* test(realtime): switch retired gpt-4o-realtime-preview to gpt-realtime
OpenAI removed gpt-4o-realtime-preview and all its date snapshots on
2026-05-18 (every variant now returns model_not_found), breaking the
live-WebSocket OpenAI realtime tests in CI:
- test_openai_realtime_direct_call_no_intent
- test_openai_realtime_direct_call_with_intent
- TestOpenAIRealtime.test_realtime_connection
- TestOpenAIRealtime.test_realtime_with_query_params
Point each of those to the current GA alias gpt-realtime (verified live).
Pure unit/mock tests that just assert the string value (e.g. in
test_realtime_query_params_construction and the
test_realtime_query_params_use_normalized_model_name mock) are left
alone since they do not depend on model availability.
Also relax the AI-response assertion in
test_text_message_blocked_by_guardrail_no_ai_response: gpt-realtime
occasionally produces a polite refusal ("I'm sorry, but I can't say
that") when the cancel arrives after the model has already started
generating, which is the expected outcome (no real AI content) but does
not contain the words 'blocked' or 'guardrail'. The primary guardrail
behaviour (guardrail_violation error event + transcript_delta block
message) is still asserted unchanged.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* test(nvidia_nim): mock rerank live API instead of hitting EOL'd endpoint
NVIDIA reached end-of-life for the hosted nvidia/llama-3.2-nv-rerankqa-1b-v2
rerank API on 2026-05-18 (returns HTTP 410 Gone), and the proposed
replacement nv-rerankqa-mistral-4b-v3 returns HTTP 404 for the CI account,
breaking TestNvidiaNim::test_basic_rerank.
Override test_basic_rerank to mock the HTTP transport (same pattern as
test_nvidia_nim_rerank_ranking_endpoint above) so the request/response
transformation and cost calculation stay covered without depending on
NVIDIA's hosted catalog rotation. The model identifier reverts to the
original llama-3.2-nv-rerankqa-1b-v2 since the request never leaves
the test process.
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
* fix(tests): use gpt-realtime in realtime guardrails test
OpenAI shut down gpt-4o-realtime-preview-2024-12-17 on 2026-05-07, so
the live OpenAI realtime guardrails integration test now fails with
model_not_found (session.created never arrives, _wait_for_event times
out). Point OPENAI_REALTIME_URL at the current GA model, gpt-realtime.
Scope limited to this test: the pricing-catalog JSON keeps the retired
entries intentionally (historical cost calc + separate Azure timeline),
and the Azure realtime cost-calc test is unaffected.
* fix(tests): mock nvidia_nim rerank instead of hitting EOL'd endpoint
NVIDIA reached end-of-life for the hosted nvidia/llama-3.2-nv-rerankqa-1b-v2
rerank API on 2026-05-18 with no published replacement, so the live
BaseLLMRerankTest.test_basic_rerank for nvidia_nim now returns HTTP 410
("Gone"). NVIDIA's hosted catalog rotates on a schedule, so swapping in
another live model would only defer the failure.
Override test_basic_rerank in TestNvidiaNim to mock the sync/async HTTP
transport (same pattern as test_nvidia_nim_rerank_ranking_endpoint in this
file) and inject a fake NVIDIA_NIM_API_KEY via monkeypatch. The
request/response transformation and cost calculation stay covered offline.
Scope limited to nvidia_nim; other BaseLLMRerankTest providers untouched.
* fix(tests): migrate remaining realtime tests off shut-down gpt-4o-realtime-preview
OpenAI's 2026-05-07 shutdown removed the entire gpt-4o-realtime-preview
family, including the undated 'gpt-4o-realtime-preview' alias (not just the
dated snapshot fixed earlier). Three live tests still connected with the
dead alias and failed with messages_received=1 (an error event instead of
session.created):
- test_openai_realtime_simple.py: get_model() -> gpt-realtime (drives
TestOpenAIRealtime.test_realtime_connection / test_realtime_with_query_params)
- test_openai_realtime.py: test_openai_realtime_direct_call_no_intent and
test_openai_realtime_direct_call_with_intent -> openai/gpt-realtime
(the with_intent test shares the same dead alias even though it was not
in the failing set this run)
Mocked unit tests (test_realtime_query_params_construction,
test_realtime_query_params_use_normalized_model_name) are left as-is: they
never hit the network and assert string plumbing only.
Also fixes test_text_message_blocked_by_guardrail_no_ai_response, which now
connects (the earlier URL swap worked) but tripped a model-wording-brittle
assertion. The guardrail flow asks the model to voice the block message
verbatim; gpt-4o-realtime-preview complied (output contained 'blocked'),
gpt-realtime refuses verbatim-repeat instructions ('I'm sorry, but I can't
repeat that message.'). Since the original user message is blocked before
it reaches OpenAI, the refusal is still a safe outcome. Assertion #3 now
accepts both voicing and refusal, and adds a hard check that the blocked
phrase never leaks into AI output.
The signing helper moved from OCIChatConfig._sign_with_manual_credentials
to a module-level sign_with_manual_credentials in common_utils.py. Four
tests in TestOCIKeyNormalization still called the old method:
- 2 failed outright with AttributeError
- 2 passed by accident because they used pytest.raises(Exception),
which happily caught the AttributeError instead of exercising the
intended OCIError path
Repoint all four to the new module-level function so they exercise the
actual oci_key type-validation branch.
The old split_chunks helper split each individual HTTP read on "\n\n",
which assumed SSE event boundaries always aligned with read boundaries.
In practice the OCI streaming endpoint delivers events that may:
- straddle two reads (chunk_creator gets a truncated JSON and crashes)
- arrive separated by a single "\n" instead of "\n\n"
- share a read with multiple complete events
Replace the inline split with module-level helpers _iter_sse_events
(sync) / _aiter_sse_events (async) that maintain a buffer across reads,
split on any newline, and yield only complete "data:" lines.
Add 25 regression tests covering event-split-across-reads, tiny-chunk
reads, single-newline separators, keepalive/comment lines, trailing
partial events flushed at EOF, "\r\n" line endings, and an end-to-end
smoke test that feeds an awkwardly-chopped payload through the splitter
into OCIStreamWrapper.chunk_creator.
Reported by John Lathouwers.
OCI Cohere's terminal SSE event re-sends the full assembled response in
`text` alongside a populated `chatHistory`. Emitting that text as another
delta concatenates the entire response onto the already-streamed output
(e.g. "How can I help?How can I help?").
Use `chatHistory is not None` as the discriminator for the consolidated
terminal event — `finishReason` is a weaker signal that could in principle
appear on a non-consolidated chunk. The two coincide today; this preserves
correctness if OCI ever ships finishReason on an incremental chunk.
Adds a live-OCI integration regression test that compares streamed vs
non-streamed length and asserts the response prefix appears only once.
Verified to fail under the previous code with the exact reported
reproduction: 'Hello! How can I help you today?Hello! How can I help you today?'.
Reported by @gotsysdba on PR #25177.
CodeQL's taint analysis re-fires the `py/weak-sensitive-data-hashing`
alert at `litellm/llms/oci/common_utils.py:103` whenever upstream code
paths into the OCI signing module change (touching `transformation.py`
opens new flow paths that CodeQL re-evaluates from scratch). The
`hashlib.sha256(..., usedforsecurity=False)` declaration silences the
direct-call form of the query but not the taint-flow form.
SHA-256 here is mandated by the OCI HTTP signing specification for the
x-content-sha256 content-integrity header — not for password storage:
https://docs.oracle.com/en-us/iaas/Content/API/Concepts/signingrequests.htm
CodeQL has no per-query path filter and GitHub Code Scanning ignores
inline lgtm/codeql comments, so path-ignoring this single ~560-line
signing utility file is the narrowest available suppression. All other
files retain full coverage of py/weak-sensitive-data-hashing — including
litellm/proxy/utils.py where the rule legitimately applies.
This restores the NEUTRAL CodeQL state the PR had on prior commits
(see `2111c98af7` for the same approach on the previous branch
evolution that the cherry-pick was rebased onto a different baseline).
Three small additions for OCI reasoning models, requested by users
testing the PR in production fork builds:
1. **reasoning_effort param mapping (GENERIC vendors).** OCI expects
uppercase levels ("LOW"/"MEDIUM"/"HIGH"/"NONE") on `reasoningEffort`,
but OpenAI-compatible clients send lowercase. Mapped + uppercased in
`_get_optional_params`. Marked unsupported on Cohere V1/V2 since OCI
Cohere has no reasoning models (avoids Pydantic validation failure
on CohereChatRequest).
2. **"disable" → "NONE" mapping.** OpenAI uses "disable" to turn off
reasoning; OCI uses "NONE". Without this, callers get a 400.
3. **reasoning_tokens propagated to Usage.** OCI returns
`completionTokensDetails.reasoningTokens` but it wasn't being passed
to LiteLLM's Usage object. Now flows through to
`Usage.completion_tokens_details.reasoning_tokens` so callers can
track reasoning token consumption for cost/observability.
Tests: 7 new unit tests in TestOCIReasoningEffort covering upper/lower
case, "disable"→"NONE", Cohere drop/raise paths, and reasoning_tokens
extraction (with and without completionTokensDetails). 5 new live
integration tests against xai.grok-3-mini in us-chicago-1 verifying the
full request/response loop end-to-end. Existing
test_transform_response_simple_text assertion that
completion_tokens_details was None has been updated to assert
reasoning_tokens flows through.
Verified live on xai.grok-3-mini: reasoning_effort=low → OCI accepts
"LOW", returns reasoningTokens=316 in usage. reasoning_effort=disable
→ OCI accepts "NONE". Full suite: 370/370 unit + 51/51 integration.
OCI's GenericChatRequest exposes a reasoningEffort field
(NONE/MINIMAL/LOW/MEDIUM/HIGH) that's the single biggest cost knob for
reasoning-capable models on the service:
- GPT-5 family
- Gemini 2.5
- Grok reasoning variants (3-mini, 4-fast, 4.20)
- Cohere Command-A-Reasoning
Setting reasoning_effort=LOW typically cuts reasoning-token spend 5-10×
vs the default. Without exposing this, litellm users had no way to tune
cost-vs-quality on these models.
The other GenericChatRequest fields (verbosity, parallel_tool_calls,
logit_bias, n, metadata, web_search_options, prediction) are not
exposed because they are not missing primitives — they either duplicate
prompt-engineering, framework-level controls, or are too niche to
justify the maintenance surface. We only ship what users genuinely
can't accomplish another way.
Excluded from the Cohere v1 param map: CohereChatRequest has no
reasoningEffort field, and Cohere reasoning models
(cohere.command-a-reasoning) use COHEREV2 which is a separate request
type not covered by this PR.
Verified live: GPT-5.5 + reasoning_effort="HIGH" sends
{"reasoningEffort": "HIGH"} on the wire and OCI accepts the request.
CodeQL's taint analysis traces request bodies back to environment-loaded
secrets and flags `hashlib.sha256(body).digest()` as
`py/weak-sensitive-data-hashing` — even though SHA-256 is the algorithm
mandated by the OCI HTTP request signing spec for the
`x-content-sha256` header (not a password/secret hash).
The previous suppression used legacy `# lgtm[...]` syntax which the
modern CodeQL action ignores. Switch to Python's standard
`hashlib.sha256(..., usedforsecurity=False)` (Python 3.9+) which CodeQL
honours as a non-security declaration. Behaviour unchanged.
Two errors flagged by `lint` CI:
llms/oci/chat/cohere.py:73: "object" has no attribute "__iter__"
llms/oci/chat/cohere.py:119: No overload variant of "get" of "dict"
matches argument types "object", "CohereToolCall"
Both stem from `msg.get("tool_calls")` / `msg.get("tool_call_id")`
returning `object` per the AllMessageValues TypedDict union. Bind to
`Any` locally for the iteration and coerce the lookup key with `str()`,
removing the now-unused `# type: ignore` on those lines.
No behaviour change — pure type-narrowing for the type checker.
- Run black on litellm/llms/oci/common_utils.py + 3 OCI test files
that drifted out of black-compliance during the rebase.
- Add the three bounded recursive functions in oci/common_utils.py
(`_resolve`, `resolve_oci_schema_anyof`, `sanitize_oci_schema`) to
the recursive_detector IGNORE_FUNCTIONS list. All three are bounded:
`_resolve` uses a `resolving_stack` cycle guard; the other two are
bounded by JSON-schema tree depth (no cycles in well-formed input),
matching the pattern of the existing OCI/Vertex schema walkers
already on the list.
GPT-5 / GPT-5-mini / GPT-5-nano / GPT-5.5 on OCI reject "maxTokens"
with HTTP 400:
Invalid 'maxTokens': Unsupported parameter: 'maxTokens' is not
supported with this model. Use 'maxCompletionTokens' instead.
(Same convention as OpenAI's reasoning-API contract.)
Add a model-aware rename in OCIChatConfig._get_optional_params so the
request payload uses maxCompletionTokens when the model id starts with
openai.gpt-5. Regular Llama / Cohere / Gemini / GPT-4.x continue to use
maxTokens unchanged.
Also widen OCIChatRequestPayload to carry the new optional field so it
survives Pydantic serialization.
Verified live against OCI us-chicago-1:
- openai.gpt-5, gpt-5-mini, gpt-5-nano, gpt-5.5 all return 200
- Full feature sweep on gpt-5.5 (basic, system, multi-turn, streaming,
tools, usage) all green
- meta.llama-3.3-70b-instruct still uses maxTokens (no regression)
4 new unit tests cover the helper, the routing in both pre- and
post-translation states, and Pydantic serialization.
The JSON schema for model_prices_and_context_window.json uses
`supports_native_streaming` (not `supports_streaming`) and has
`additionalProperties: false`. Rename the field across all OCI
entries to pass the schema validation test.
- types/llms/oci.py: add "TOOL_CALL" to CohereChatResponse.finishReason
Literal so Pydantic does not raise ValidationError on non-streaming
Cohere tool-use calls (Greptile P1)
- test_oci_cohere_tool_calls.py: add test covering TOOL_CALL finish reason
- model_prices_and_context_window.json: remove 6 duplicate oci/cohere.embed-*
keys that were silently overridden by the more complete entries already
present in the file (Greptile P1)
- common_utils.py: move OCI_API_VERSION here from chat/transformation.py
so embed/transformation.py does not need to import chat/transformation;
change Protocol stub body from ... to pass (CodeQL "statement no effect");
add comment to sha256_base64 clarifying it implements OCI HTTP signing
spec, not password hashing (CodeQL false positive)
- chat/transformation.py: import CustomStreamWrapper from
litellm_core_utils.streaming_handler instead of litellm.utils to reduce
import cycle depth (CodeQL cyclic import)
- chat/cohere.py, chat/generic.py: import Usage and
ChatCompletionMessageToolCall from litellm.types.utils instead of
litellm.utils for the same reason
- embed/transformation.py: import OCI_API_VERSION from common_utils
instead of chat/transformation (removes the embed→chat import edge)
- Remove _extract_text_content duplication — single definition in cohere.py,
imported where needed; instance method on OCIChatConfig eliminated
- Move cryptography imports to module level with _CRYPTOGRAPHY_AVAILABLE flag
and _require_cryptography() guard; no more re-import on every signing call
- Move litellm version import to module level via litellm._version; remove
inline import inside validate_oci_environment
- sign_with_manual_credentials now returns Tuple[dict, bytes] matching
sign_with_oci_signer — asymmetry eliminated, Optional[bytes] guards removed
throughout stream wrappers (signed_json_body: bytes = b"")
- Rename _openai_to_oci_cohere_param_map → openai_to_oci_cohere_param_map
for consistency with openai_to_oci_generic_param_map
- Remove double-key bug in map_openai_params where responseFormat was stored
under both OCI and OpenAI key names simultaneously
- Remove delegating shims (adapt_messages_to_cohere_standard,
adapt_tool_definitions_to_cohere_standard, _handle_generic_stream_chunk)
from OCIChatConfig/OCIStreamWrapper; tests now import directly from
cohere.py and generic.py where symbols live
- Trim __all__ to 7 genuine public symbols; remove the 13-symbol list that
existed only to support test imports
- Collapse per-model integration test classes into pytest.mark.parametrize;
CHAT_MODELS list is the single source of truth for model-specific config
- Black + Ruff clean across all OCI files
- Add resolve_oci_schema_refs: inline $ref/$defs — OCI rejects JSON Schema refs
- Add resolve_oci_schema_anyof: flatten Optional[T] anyOf (Pydantic v2 emits these)
- Add sanitize_oci_schema: strip title, normalise null types, ensure array items
- Add OCI_JSON_TO_PYTHON_TYPES: Cohere expects Python type names (str/int/float),
not JSON Schema names (string/integer/number)
- Add enrich_cohere_param_description: embed enum/format/range/pattern constraints
into description since CohereParameterDefinition has no dedicated fields
- Apply all of the above in adapt_tool_definitions_to_cohere_standard and
adapt_tool_definition_to_oci_standard
- Fix toolChoice conversion: map OpenAI string ('auto','none','required') to OCI
dict form ({"type":"AUTO"} etc.) — the API rejects plain strings
- Update unit test expectations to match correct Python type names and enriched
descriptions
- Remove OCIVendors.GEMINI — apiFormat="GEMINI" is invalid; all non-Cohere
models use apiFormat="GENERIC"
- Add toolChoice, logitBias, logProbs to OCIChatRequestPayload so params
present in the mapping are no longer silently dropped by Pydantic
- Exclude n→numGenerations from Cohere param map (not a Cohere API field)
- Fix CohereToolResult: change callId/result to call/outputs matching
the OCI SDK's CohereToolResult structure
- Fix CohereToolMessage: replace non-existent toolCallId with toolResults
list; update adapt_messages_to_cohere_standard to build proper tool-result
history entries by resolving tool call name+params from preceding assistant
messages
- Map generic-model stream finish reasons to OpenAI convention
(COMPLETE→stop, MAX_TOKENS→length, TOOL_CALLS→tool_calls), consistent
with the existing Cohere streaming path
- Add optional id field to OCIEmbedResponse so valid API responses
carrying an id are not rejected by the Pydantic model
Addresses greptile P1: tests/test_litellm/ is for mock-only unit tests
(make test-unit target). Real-network OCI tests now live in the correct
location alongside other provider integration tests.
- Bug 1: sync and async streaming paths now use signed_json_body when provided
instead of re-serializing data with json.dumps() — the OCI RSA-SHA256 signature
covers the exact request body bytes, so re-serializing produces an invalid sig
- Bug 3: Cohere stop sequences now map to 'stopSequences' (was incorrectly 'stop')
- Bug 4: removed hardcoded Cohere defaults (maxTokens=600, temperature=1, topK=0,
topP=0.75, frequencyPenalty=0) that silently overrode user intent on every call
- Added 6 unit tests covering all three fixes
- Add OCIEmbedConfig with full Cohere embed support (7 models, batch up to 96)
- Fix sync streaming: split SSE events on \n\n before JSON parsing
- Fix reasoning models (Gemini 2.5, xAI Grok): make completionTokens and message
optional in OCIResponseChoice to handle max_tokens exhausted on reasoning
- Fix compartment_id resolution in chat transform to use resolve_oci_credentials
- Fix tool call id: make OCIToolCall.id optional, generate UUID fallback for
providers (Google via OCI) that omit it
- Add OCI_KEY env var support for inline PEM keys
- Fix datetime.utcnow() deprecation in request signing
- Expand model catalog: 29 OCI models including Llama 4, Gemini 2.5, xAI Grok,
Cohere Command A, and all Cohere embed variants
- Add 37 live integration tests: sync/async completions for Meta/Google/xAI/Cohere,
sync/async embeddings, tool use across all vendors, streaming, env var auth
- Add 23 embed unit tests covering all transform and validation paths
* fix(bedrock/cohere): wrap embedding_types as list in map_openai_params
Bedrock Cohere expects embedding_types as a JSON array but
encoding_format was passed through as a raw string, causing:
Malformed input request: #/embedding_types: expected type: JSONArray, found: String
* test(bedrock/cohere): assert embedding_types is sent as JSON array
---------
Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
* fix(tests): stabilize image-edit VCR cassettes to stop live gpt-image-1 spend
The image-edit cassettes for ``gpt-image-1`` were accumulating >50
episodes and being refused by the persister
(``tests/_vcr_redis_persister.py``), so every CI run was hitting the
real OpenAI endpoint. The async parametrize was the clearest tell:
``test_openai_image_edit_litellm_sdk[True]`` cached to 1 entry, but the
``[False]`` (async) sibling grew to 51 entries and never replayed.
Two non-deterministic sources were fueling the growth, both fixed
here. After this patch, the cassettes settle at one episode per
unique call and replay for the 24-hour TTL like every other suite.
1. Pin httpx's multipart boundary at the source. The existing
``_normalize_multipart_boundary`` rewrites the boundary in the
``Content-Type`` header reliably, but on the async transport path
the body is not always a contiguous ``bytes`` object when
``before_record_request`` runs, so the body-side replacement
silently no-ops and the recorded cassette retains the random
``boundary=<hex>`` string. The next CI run gets a fresh random
boundary, the ``safe_body`` matcher misses, and
``record_mode="new_episodes"`` appends another episode. Wrapping
``httpx._multipart.MultipartStream.__init__`` so it always uses
``vcr-static-boundary`` when no boundary is supplied eliminates
the variance for both sync and async paths and leaves the normalizer
in place as a backstop. Exposed as
``pin_httpx_multipart_boundary`` so other multipart-heavy suites
(audio, ocr, batches) can adopt the same fixture later.
2. Pass raw ``bytes`` (not ``BytesIO`` streams) through the
image-edit fixtures. A ``BytesIO`` whose file pointer is at EOF
after the first multipart upload silently encodes an empty image on
the next SDK / Router retry — yet another divergent body that VCR
records as a new episode. ``bytes`` are immutable and position-less,
so retries re-encode an identical payload every time. This is also
a small production-correctness improvement: a customer passing
``BytesIO`` today would hit the same empty-body retry bug. The
BytesIO-specific smoke test
(``test_openai_image_edit_with_bytesio``) is preserved by giving
``get_test_images_as_bytesio`` its own factory instead of aliasing
the bytes one.
3. Add ``scripts/flush_image_edit_vcr_cassettes.py`` — a one-shot
Redis SCAN/DEL helper that clears the bloated pre-fix cassettes
under ``litellm:vcr:cassette:tests/image_gen_tests/test_image_edits/*``.
Without this, the next CI run still loads the existing 51-entry
cassette, the new fixed-boundary body still doesn't match any of
the stale entries, the persister still refuses to save, and the
bleed continues. Run once with the production
``CASSETTE_REDIS_URL`` after merge (dry-run by default).
* DIAGNOSTIC: log VCR body mismatches + per-episode body hashes
Temporary observability boost so we can root-cause why
``test_image_edits.py`` async parametrizes still record fresh
episodes on every CI run even though the multipart boundary is now
pinned (sync parametrizes cache cleanly as VCR HIT). The matcher
currently raises ``AssertionError("request bodies differ")`` with
zero context, so we cannot tell whether the live body genuinely
varies, the matcher is comparing a bytes object to a stream object,
or the normalizer is silently skipping the body because it is not
bytes/str.
Three logs added; the first two are worth keeping permanently, the
third is intended to be reverted after the diagnosis lands:
1. ``_safe_body_matcher`` now emits a structured stderr block on
mismatch (type of each side, length, SHA-256, first divergent
byte offset, ±100-byte window). Always-on -- mismatches are
signal, not noise, and the existing per-test verdict already
logs once per test. PERMANENT.
2. ``_normalize_multipart_boundary`` now logs to stderr when the
body type is not bytes/bytearray/str -- the silent ``else:
return`` branch was masking exactly the case we suspect is
firing on async (httpx ``MultipartStream`` handed to vcrpy
before the body is read). PERMANENT.
3. ``_RedisPersister.save_cassette`` now logs every episode's body
SHA-256, length, and 120-byte preview at save time. This lets
two consecutive CI runs be diffed: if the same test records a
different hash run-to-run, the live body genuinely varies; if
both runs record the same hash but the matcher still misses, the
bug is in the matcher itself. TEMPORARY -- revert once the
async variance is identified and fixed.
Once a single ``image_gen_testing`` CI run produces these logs,
revert this commit (or just the persister hash block) with a force
push so the cassette save path is not noisy in steady-state.
* DIAGNOSTIC: route VCR diagnostics through per-PID files (bypass xdist capture)
Re-push of the diagnostic logging from the previous commit, this
time wired so the output actually survives to the CI log. xdist
captures stdout/stderr from every passing test in the worker
process; the body-matcher and normalizer-skip diagnostics fire from
inside vcrpy machinery during the test, so for any test that
ultimately passes (which is all of them once the cassettes are
recorded), the diagnostic lines are silently swallowed.
Fix: write each diagnostic line to a per-PID file under
``test-results/vcr-diagnostics/<pid>.log`` instead of writing to
stderr. The controller's ``pytest_terminal_summary`` aggregates
those files and writes them through ``terminalreporter.write_line``,
which is not subject to per-test capture. As a bonus,
``test-results/`` is already collected by the ``store_test_results``
step in CircleCI, so the raw per-worker logs survive as build
artifacts even after the test session ends.
Three call sites updated:
1. ``_emit_body_mismatch_diagnostic`` (matcher) -- writes the
structured type/length/sha/window block via ``vcr_diag_write_line``.
2. ``_normalize_multipart_boundary`` -- logs the silent-skip path
(body not bytes/bytearray/str) the same way.
3. ``_maybe_log_episode_body_hashes`` (persister) -- replaces the
``_log.warning`` calls (which the root-logger config also
swallows in CI) with ``vcr_diag_write_line``.
Image-gen conftest is the only suite wired to dump the aggregated
log at session end. Other suites can opt in by adding
``emit_vcr_diagnostic_log(terminalreporter)`` to their own
``pytest_terminal_summary``. The diagnostic dir is cleared at the
start of each session (controller-only) so a local rerun does not
mix output from prior runs.
Same revert plan as the previous diagnostic commit: keep the
matcher + normalizer skip diagnostics permanently (they only fire
on signal events), revert the persister body-hash dump once the
async variance is identified.
* fix(tests): coalesce iterable request bodies before matching/recording
Root cause of the residual async image-edit cassette leak. The
diagnostic run for ``ba3915d9`` printed:
[vcr-safe-body-matcher] request body mismatch
body[a]: type='list_iterator' length=unknown sha256=N/A
body[b]: type='list_iterator' length=unknown sha256=N/A
httpx's async transport hands vcrpy a ``request.body`` that is a
``list_iterator`` over multipart chunks rather than a contiguous
``bytes`` blob. Two consequences:
1. ``_safe_body_matcher`` compares the two iterator objects with
``==``, which is identity comparison for arbitrary iterators -
semantically identical multipart bodies never compare equal, and
``record_mode="new_episodes"`` appends a new episode on every CI
run until the cassette crosses ``MAX_EPISODES_PER_CASSETTE`` and
the persister refuses to save (this is exactly what the OVERFLOW
warning has been catching).
2. ``_normalize_multipart_boundary`` short-circuits its
``else: return`` branch because the body is neither bytes nor
str, so any residual random boundary characters in the body bytes
are never rewritten.
Sync requests do not hit this code path: httpx's sync transport
hands vcrpy a single ``bytes`` body, so ``==`` works and the
boundary normalizer runs as intended. That is why
``test_openai_image_edit_litellm_sdk[True]`` records to ``entries=1``
and replays cleanly while ``[False]`` (async) kept growing by one
episode per run.
Fix: add ``_materialize_iterable_body`` which coalesces an iterable
``request.body`` into ``bytes`` in-place. Call it from two places:
* The top of ``_before_record_request``, so the boundary normalizer
and the cassette serializer both see bytes from then on.
* The top of ``_safe_body_matcher``, as defense in depth in case a
future vcrpy code path invokes the matcher without first going
through ``_before_record_request``.
The vcrpy ``Request`` is a wrapper used for matching and recording;
the underlying httpx transport sends its own request body
separately, so replacing the iterator on the vcrpy wrapper does
not starve the live HTTP send.
After this lands the async parametrizes should flip from
``[VCR MISS:RECORDED] entries=N+1`` to ``[VCR HIT] entries=N`` on
the next CI run, matching the sync side and dropping the residual
~$3/day to $0.
* fix(tests): handle bytes_iterator + never leave an exhausted body
Follow-up to 8e08272b. The previous attempt at coalescing iterable
request bodies bailed out (``return`` without writing
``request.body``) whenever it could not classify the chunk type.
That was the wrong failure mode for one critical case: vcrpy
sometimes presents the body as ``iter(some_bytes)``, whose Python
type is ``bytes_iterator`` and which yields ``int`` byte values
(0-255), not byte chunks. The old code saw an ``int`` chunk, hit
the ``else: return`` branch, and left ``request.body`` pointing at
the now-exhausted iterator.
The post-fix diagnostic run made this loud:
[vcr-safe-body-matcher] request body mismatch
body[a]: type='bytes_iterator' length=unknown sha256=N/A
body[b]: type='bytes_iterator' length=unknown sha256=N/A
Every async image-edit test then ballooned from entries=2 to
entries=10 in that single CI run -- the exhausted iterator meant
the live multipart upload went out as an empty body, OpenAI
returned 400, the SDK + flaky retries fired, each retry got a
fresh iterator that my hook exhausted again, and ``new_episodes``
recorded each failed attempt as a new cassette episode.
This patch:
* Recognizes ``bytes_iterator`` (chunks are ``int``) and
reconstructs the buffer via ``bytes(chunks)``.
* Keeps the existing ``list_iterator``-over-bytes-chunks handling
via ``b"".join(...)``.
* **Always writes a bytes value back to ``request.body`` after
consuming the iterator.** If the chunk shape is unrecognized,
``request.body`` is set to ``b""`` rather than left as an
exhausted iterator. That is wrong in the sense of "we lost the
body" but right in the sense of "the failure mode is now visible
(live API call sends empty body and fails fast) instead of
invisible (corrupt cassette grows silently)". Combined with the
matcher diagnostic, any future regression in this code path will
surface in the CI log immediately.
Local verification covers ``bytes_iterator``, ``list_iterator``
over bytes chunks, generator over bytes chunks, empty iterator,
already-bytes (idempotent), identical-content iterator equality
in the matcher (now matches), and differing-content iterator
inequality (still raises).
* fix(tests): clear vcrpy's sticky _was_iter flag so materialized bodies stay bytes
Actual root cause of the async image-edit cassette leak. The
previous diagnostic run produced this dead giveaway:
[vcr-episode-body-hash] ... episode[0]: body type='bytes_iterator'
is not bytes/bytearray/str -- cannot hash
[vcr-safe-body-matcher] request body mismatch
body[a]: type='bytes_iterator' length=unknown sha256=N/A
body[b]: type='bytes_iterator' length=unknown sha256=N/A
Both sides of the matcher were ``bytes_iterator`` **after** the
materializer had supposedly converted them to bytes. That made no
sense until I read vcrpy's ``Request`` class.
vcrpy's ``Request`` keeps two private flags that are set in
``__init__`` from the original body's type and **never cleared by
the setter**:
def __init__(self, method, uri, body, headers):
self._was_file = hasattr(body, "read")
self._was_iter = _is_nonsequence_iterator(body)
...
@property
def body(self):
if self._was_file: return BytesIO(self._body)
if self._was_iter: return iter(self._body)
return self._body
@body.setter
def body(self, value):
if isinstance(value, str): value = value.encode("utf-8")
self._body = value # <-- does NOT touch _was_iter / _was_file
So when httpx's async transport hands vcrpy an iterator body,
``_was_iter`` becomes ``True`` and stays there forever. Even after
``_materialize_iterable_body`` writes plain bytes via
``request.body = out``, the next read of ``.body`` re-wraps the
stored bytes in ``iter()`` -- producing a fresh ``bytes_iterator``
that compares unequal to any other ``bytes_iterator`` via object
identity. The matcher missed every time, the cassette grew by one
episode per run, and the persister saw the same iterator type when
trying to hash the body for the diagnostic log.
Fix: after writing the materialized bytes, also force
``_was_iter`` and ``_was_file`` to ``False``. vcrpy exposes no
public API for this, so we touch the private flags directly --
acknowledged as a pragmatic test-only hack with a clear unit
boundary (the only call site is ``_materialize_iterable_body``).
Local repro reproduces the exact production setup:
``Request('POST', url, iter(b'multipart-content'), {})`` on two
sides, runs the matcher, asserts HIT. Verified the matcher hits on
identical content and still raises on differing content.
Should be the last fix needed. Existing cassettes that contain
oddly-shaped bodies (lists of int chunks, etc. from the previous
``_was_iter=True`` save path) still match because the materializer
canonicalises both sides to bytes before comparison -- no fourth
re-flush required.
* revert(tests): drop the temp per-episode body-hash diagnostic
Removed now that 1c51ad13 has confirmed the root cause (vcrpy's
sticky ``_was_iter`` flag making the body getter re-wrap stored
bytes in ``iter()`` on every access). The hash dump did its job --
the post-1c51ad13 image_gen_testing run shows all five async
image-edit tests as ``[VCR HIT]`` with stable entry counts and
zero billing errors -- and is too noisy to keep on by default
(over 100 lines per session at steady state).
Kept permanently:
* ``_safe_body_matcher`` mismatch diagnostic in
``_vcr_conftest_common.py``. Only fires on a body mismatch,
which is signal worth surfacing whenever it happens.
* ``_normalize_multipart_boundary`` "skipped" log line. Same
rationale -- only fires when the body shape is something the
normalizer cannot rewrite in place.
* The ``test-results/vcr-diagnostics/<pid>.log`` per-PID file
plumbing (``vcr_diag_write_line`` /
``emit_vcr_diagnostic_log``). Useful for any future diagnostic
that needs to bypass xdist stdout/stderr capture; cheap to keep.
* chore(tests): delete unused flush script + wire VCR diagnostic dump everywhere
* Remove ``scripts/flush_image_edit_vcr_cassettes.py``. It was a
one-shot helper for the initial cassette flush; the iterator and
``_was_iter`` fixes mean no future flush should be required, and
the script was never run anywhere (the actual flushes happened
inside the CI conftest via the temp hacks that have since been
reverted).
* The matcher mismatch + normalizer skip diagnostics already write
per-PID files for every suite that imports the shared VCR
plumbing, but ``emit_vcr_diagnostic_log`` -- the controller-side
dump that surfaces those files into the CI log at session end --
was only wired into ``image_gen_tests``. Add the one-line call to
the 12 sibling conftests that already use VCR so the diagnostics
surface in any suite's terminal output if a body matcher ever
misses. No new output in steady state -- the dump is a no-op when
no diagnostics were recorded that session.
* chore(tests): trim non-essential comments per project comment policy
Strips docstrings, inline comments, and block comments that this PR
introduced where the code itself was already self-evident. Keeps the
few lines that document non-obvious behaviour (raw-bytes-not-BytesIO
rationale on the image fixtures, the per-PID-files-bypass-xdist note
on the diagnostic directory). Touches only comments this PR added --
no pre-existing comment is removed.
Net: -161 lines of comment/docstring across 3 files, no code
behaviour change.
* chore(tests): forward **kwargs in pin_httpx_multipart_boundary wrapper
Defensive against future httpx MultipartStream.__init__ adding new
optional kwargs. Without the forward, the wrapper would silently drop
them. No behaviour change today.
* chore(tests): canonicalize VCR matchers and surface shouldn't-happen branches
Bundles the "follow-up cleanup PR" into this one so it does not get
lost. Four small changes:
1. Introduce ``_canonical_body(req) -> (bytes, pre_type)`` and route
``_safe_body_matcher`` through it. The matcher now operates on
bytes by construction; the "compare two iterator objects via
``==`` and silently get object-identity semantics" failure mode
(which cost us this entire PR to diagnose) is structurally
impossible to reintroduce. ``pre_type`` is the body type *before*
canonicalization, surfaced by the mismatch diagnostic so a future
regression involving a new body shape is still visible.
2. Add a structured diagnostic to ``_key_fingerprint_matcher``. It
was previously raising a bare ``AssertionError("API key
fingerprints differ")`` with zero context -- exactly the
anti-pattern the body matcher had before this PR.
3. Surface "shouldn't-happen" branches via ``vcr_diag_write_line``:
* ``_strip_image_b64_payloads`` -- logs when ``response``,
``response['body']``, or ``response['body']['string']`` arrives
in an unexpected shape (vcrpy contract violation).
* ``_compute_key_fingerprint`` -- logs the ``"no-key"`` fallback
with the request method/URL so a stripped-auth-header bug is
visible instead of masked.
* ``_canonical_body`` -- logs its own empty-bytes fallback when a
body has a shape ``_materialize_iterable_body`` did not handle.
4. Re-introduce per-episode body-hash logging in
``_RedisPersister.save_cassette`` (was reverted in 927c5548 as
"noisy"). Quantified cost: ~25 KB of CI log per session at peak,
~ms-scale CPU, zero output in steady state (no save = no log).
Trade-off favours keeping it: lets two consecutive CI runs be
diffed by body hash, which is how we will spot the next regression
in the same class.
All call sites still work: local repro confirms iter==iter HIT,
iter!=iter raises, plain-bytes HIT, body-hash log emits via the same
per-PID file plumbing as the matcher diagnostics.
* chore(tests): symmetrize diag-log cleanup across every VCR-using conftest
``image_gen_tests/conftest.py`` was the only suite that cleared
``test-results/vcr-diagnostics/*.log`` at session start. The other 12
VCR-using conftests inherited any stale per-PID logs from a previous
local run and would dump them in the terminal summary -- harmless in
CI (fresh container) but confusing locally when running multiple
suites in sequence.
Extracts the cleanup into a ``reset_vcr_diag_dir`` helper in
``tests/_vcr_conftest_common.py`` and calls it from every VCR-using
conftest's ``pytest_configure``. Same single source of truth, no
inline duplication.
* fix(tests): gate body materialization on __next__ and strip PR comments
aiohttp/vcrpy stores the json kwarg as a dict; _materialize_iterable_body
was iterating it via __iter__ and joining the keys, replacing the request
body with concatenated key names ("textlanguageentities"). Gate on
__next__ so containers (dict/list/tuple) are left alone — only single-use
iterators like httpx's bytes_iterator / list_iterator are materialized.
Log diagnostic line when chunk type is unrecognized.
* fix(tests): JSON-encode dict bodies in canonical_body for stable matching
aiohttp stubs store the json kwarg as a dict; the fallback that compared
all dicts as b"" caused concurrent presidio analyze calls to be served
the wrong cassette episode. JSON-encode with sort_keys for stable bytes.
* fix(tests): guard emit_vcr_diagnostic_log against multi-conftest re-emission
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(tests): globalize multipart-boundary pin + stabilize whisper fixtures
Diagnostic shows audio_testing was silently re-recording 50+ live Whisper
episodes per CI run (over MAX_EPISODES_PER_CASSETTE, so the persister
refused to save). Two changes:
* Move the session-autouse _pin_multipart_boundary fixture into the
shared _vcr_conftest_common module so every VCR-using suite picks it
up via a single import. image_gen had it inline; the other 12 suites
silently lacked it.
* Replace the module-level open("rb") audio file handles in test_whisper
with cached bytes + a per-call (filename, bytes, mimetype) tuple,
mirroring the image_edits raw-bytes pattern. Stops the file-pointer-
at-EOF bug where the second test got an empty multipart body.
* chore(tests): drop per-episode body-hash dump and redundant emit guard
---------
Co-authored-by: shin-berri <shin-laptop@berri.ai>
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
