Extracts _enrich_cost_breakdown_with_cache_costs() call out of the
constructor arg list and into a separate variable. Also drops the
redundant cost_breakdown param from the function signature — reads
logging_obj.cost_breakdown directly instead.
Add cache_read_input_cost and cache_write_input_cost to CostBreakdown.
Backend (litellm_logging.py):
- Add _enrich_cost_breakdown_with_cache_costs() that reads cached_tokens
and cache_creation_tokens from usage, computes their costs via
_get_token_base_cost, and injects them into the existing cost_breakdown
dict before it reaches the spend log.
Frontend (CostBreakdownViewer.tsx):
- Show 'Cache Read Cost' and 'Cache Write Cost' sub-rows under Input Cost
when the values are present and > 0.
Types (types/utils.py):
- Add cache_read_input_cost and cache_write_input_cost to CostBreakdown.
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* azure content enhancement...
* rafactored to increase confidence score
* improvements based on additional feedback
* removed unused import
* Force-split any word longer than max length allowed
* preserve whitespace in text splitting
* moving common initialization to base class
* consolidate enforcement into async_make_request as single point, remove redundant caller-side checks, extract shared init/HTTP logic into base, and fix stale log messages
* clean up
* clean up tests
The linting workflow force-installed openai==1.100.1 which conflicts
with litellm's requirement of openai>=2.8.0, causing pip dependency
resolver errors and CI cancellation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
PR #22785 used pytest.importorskip which causes exit code 5 (all
skipped) in CI. Instead, add tenacity to the CI workflow pip install
and restore direct imports.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add cache_read_input_token_cost_per_audio_token, supports_code_execution,
and supports_file_search to the JSON schema used by the model prices
validation test.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
tenacity is not in pyproject.toml dependencies, causing ImportError
during test collection. Use pytest.importorskip to gracefully skip
when tenacity is not available.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The _encrypt_response_id method now receives request_cache=None as a
keyword argument from async_post_call_success_hook. Updated the mock
assertion to expect this parameter.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
PR #22732 changed the ToolTable schema (renamed call_policy to
input_policy, added output_policy/user_agent/last_used_at columns,
updated indexes) but didn't include a migration for these changes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tests used call_policy throughout but the actual API model uses
input_policy and output_policy. Updated _make_tool_row helper,
list filter query param, and policy update request/response assertions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The asend_message function accessed request.params.message.context_id
using attribute syntax, but message can be either a dict or an object.
Handle both cases using isinstance check, matching the existing pattern
in litellm/a2a_protocol/utils.py.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The aresponses_websocket CallType was recently added but not included
in the test exclusion list. It uses WebSocket passthrough (not Azure SDK
client initialization), so it correctly doesn't call
initialize_azure_sdk_client.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The test_streaming_mcp_events_validation test was flaky because:
1. It didn't mock the nested aresponses() call inside the iterator's
_create_initial_response_iterator(), causing real API calls that fail
without credentials
2. The iterator silently swallowed exceptions and set phase="finished",
discarding pre-generated MCP discovery events
3. The _execute_tool_calls mock had wrong signature (missing tool_server_map)
Production fix: MCPEnhancedStreamingIterator no longer sets phase="finished"
on LLM call failure — it falls through to emit MCP discovery events first.
Test fix: Added mock for litellm.responses.main.aresponses returning a fake
async streaming iterator, fixed mock signatures, removed try/except that
masked failures.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
