Document how to send Vertex Priority PayGo headers and explain how trafficType maps to service-tier pricing in LiteLLM, including an embedded flow diagram for quick understanding.
Made-with: Cursor
When scanning backward over counted messages, preserve old behavior for
adjacent assistant turns by inserting user_continue if the immediate
previous raw message is assistant. This handles malformed
assistant(tool_calls)->assistant(no-tool-calls) inputs without splitting
valid assistant(tool_calls)->tool chains.
Made-with: Cursor
- aresponses() now pops prompt_id from kwargs after the async hook runs
and passes merged_optional_params via _async_prompt_merged_params.
responses() checks for this internal kwarg first and skips the sync
hook entirely when present — eliminating double-merge of template
messages.
- merged_optional_params from async_get_chat_completion_prompt is no
longer discarded (_); it flows through to local_vars in responses().
- Async tests now assert get_chat_completion_prompt.assert_not_called()
to directly detect any double-execution regression.
Made-with: Cursor
- Populate container_id on streaming code_interpreter_results by
re-emitting at message_delta when container info arrives
- Reconstruct Pydantic OutputCodeInterpreterCall objects from plain
dicts in _extract_tool_result_output_items so responses_output
has uniform types across streaming and non-streaming paths
- test_non_bash_tool_result_skipped: verifies text_editor results produce
zero code_interpreter_call items
- test_end_to_end_streaming_chunks_to_code_interpreter_output: exercises
full path from Anthropic SSE chunks through ModelResponseIterator,
stream_chunk_builder, and _extract_tool_result_output_items without
a live server
Skip non-bash tool result types (e.g. text_editor_code_execution_tool_result)
to avoid producing empty code_interpreter_call items in Responses API output.
Replace str(content) fallback with empty string so non-dict content
(e.g. list-shaped text_editor results) produces outputs=None instead
of raw Python object representations in logs.
- Empty stdout/stderr now produces outputs=None (matching OpenAI parity)
instead of outputs=[{logs:""}], in both streaming and non-streaming paths
- Fix test fixture to use real Anthropic type "bash_code_execution_tool_result"
instead of "code_execution_tool_result"
- Add test for empty-output → outputs=None behavior
- Add unit tests for _extract_tool_result_output_items: Pydantic objects,
plain dicts (post-model_dump), empty/missing provider_specific_fields,
and in-place substitution preserving output ordering
When both stdout and stderr are empty strings, the `if parts else
str(content)` fallback produced the raw dict representation as logs.
Drop the fallback so logs is correctly empty.
stream_chunk_builder uses "last value wins" for list-valued
provider_specific_fields keys. _build_code_interpreter_results was
emitting only new items (incremental), so earlier results were silently
dropped when multiple sequential code executions occurred.
- Emit cumulative list from _build_code_interpreter_results, matching
web_search_results pattern
- Assemble server_tool_use input from input_json_delta deltas at
content_block_stop (Anthropic streams input: {} in start block)
- Handle dict items in _extract_tool_result_output_items after
model_dump() serialization in stream_chunk_builder
- Simplify _merge_provider_specific_fields to last-value-wins for lists,
matching stream_chunk_builder semantics
PR #18945 added support for capturing Anthropic server-side tool results
(bash_code_execution_tool_result, etc.) in provider_specific_fields, but
the data never reached the Responses API output because:
1. Non-streaming: provider_specific_fields wasn't copied into _hidden_params
2. Streaming: chunk delta's provider_specific_fields wasn't accumulated
3. Tool results weren't mapped to standard output items
This fix:
- Copies provider_specific_fields to _hidden_params in transform_response()
- Accumulates provider_specific_fields from streaming chunk deltas
- Maps bash_code_execution_tool_result to code_interpreter_call output items
with code and outputs (matching OpenAI's native shape)
- Removes redundant function_call items for server-side tools
- Adds OutputCodeInterpreterCall type to the output union
Restore backward-compatible behavior: only insert assistant_continue
between directly adjacent user messages, not across tool-call chains.
The _counts_for_alternation skip logic was a silent behavioral change
for [user, assistant(tc), tool, user] sequences.
Made-with: Cursor
- Fix async path: call async_get_chat_completion_prompt in aresponses()
before executor dispatch, mirroring acompletion() in main.py. Discard
merged_optional_params in async path (sync responses() handles them
via local_vars), avoiding TypeError from duplicate kwargs in partial().
- Fix provider re-resolution: replace "/" in model heuristic with
model != original_model comparison so bare model names are handled.
- Add 3 async tests covering hook invocation, optional param
propagation, and non-message item filtering in aresponses().
Made-with: Cursor
- Restore backward compat for leading assistant(tool_calls) — always prepend user_continue
- Replace partial assertions with full list assertion in trailing tool-call test
Made-with: Cursor
Avoid inserting assistant continue messages in the middle of assistant tool_call->tool chains by inserting before the next counted user turn, and add regression coverage for this edge case.
Made-with: Cursor
These were only used in block_key/unblock_key for cache refresh,
which now uses _delete_cache_key_object instead.
Co-authored-by: yuneng-jiang <yuneng-jiang@users.noreply.github.com>
- test_block_key_nonexistent_key_returns_404: verifies block_key returns
404 (not misleading 401) when the key doesn't exist in the DB
- test_unblock_key_nonexistent_key_returns_404: same for unblock_key
- test_block_key_existing_key_succeeds: verifies block_key succeeds and
invalidates cache for existing keys
- Update test_unblock_key_supports_both_sk_and_hashed_tokens to reflect
the new cache invalidation pattern (_delete_cache_key_object instead
of get_key_object + _cache_key_object)
Co-authored-by: yuneng-jiang <yuneng-jiang@users.noreply.github.com>
The block_key() and unblock_key() handlers previously returned a
misleading 401 'Authentication Error' when the body 'key' didn't exist
in the database, even though authentication (via Authorization header)
succeeded correctly.
Root cause: After auth passed, the handlers called get_key_object() for
cache refresh. This function was designed for auth token lookup and
raises ProxyException(code=401) when a token isn't found. Additionally,
Prisma's update() silently returns None for non-existent records instead
of raising an error, so the code reached get_key_object() without
detecting the missing key.
Fix:
- Add an explicit existence check (find_unique) before the update
- Return 404 ProxyException with 'Key not found' if the key doesn't exist
- Replace get_key_object() + manual cache update with _delete_cache_key_object()
to invalidate the cache (next read will re-fetch from DB)
- Reuse the find_unique result for audit logs, eliminating duplicate queries
Co-authored-by: yuneng-jiang <yuneng-jiang@users.noreply.github.com>
Extract duplicate file preview JSX blocks (responses and chat image
previews) into a reusable FilePreviewCard component, reducing ~50
lines of duplicated markup in ChatUI.tsx.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Promote _fetch_managed_vector_stores_by_uuids from @staticmethod to a module-level
async helper get_managed_vector_store_rows_by_uuids, following the same standalone
helper pattern as get_team_object / get_key_object so the hot-path DB read is a
named importable function rather than an inline prisma_client.db.* call
- Pass no-log=True to both inner _call_aresponses sub-calls so they do not fire
independent billing/monitoring callbacks; cost is accumulated in the synthesized
response's _hidden_params for the outer responses() call
- Add test_H11b covering the primary queries (plural array) function-tool schema,
complementing H11 which exercises only the backward-compat singular query path
Made-with: Cursor
