Follow-up to #31411 (superseded and merged as #31997). Two related fixes
so LiteLLM callers see what TinyFish actually returns, plus small
correctness cleanups.
## Response headers surfaced on _hidden_params
TinyFish sets useful response headers (x-request-id on every response,
retry-after and x-ratelimit-limit on 429s). Previously these were only
accessible via BaseLLMException.headers on error paths; on the success
path they were dropped entirely.
Fix: stash headers on both LiteLLM-conventional channels, matching the
pattern used by Gemini / Volcengine / Manus / ChatGPT / OpenAI-responses
providers.
- `_hidden_params["headers"]` -- raw dict from httpx, all keys lowercased.
- `_hidden_params["additional_headers"]` -- passed through
process_response_headers, which prefixes any x-litellm-* provider
header with `llm_provider-` so downstream LiteLLM code that trusts
bare x-litellm-* markers can't be spoofed (values still survive
under the prefixed key for observability).
## Top-level response extras (query, total_results, page, future fields)
transform_search_response was building a fresh SearchResponse from just
`results`, silently dropping every top-level field TinyFish's response
carries beyond `results` / `object`.
Fix: mutate parsed.results to its truncated slice and return the same
SearchResponse instance rather than reconstructing. Every field pydantic
populated during model_validate -- declared attributes AND extras
(query, total_results, page, parameter_warnings, and any future TinyFish
additions) -- survives regardless of which storage bucket holds it.
Robust against upstream schema evolution: if LiteLLM later promotes a
field from extras to declared, this code needs no change.
## Code cleanup
- List-valued custom params JSON-encoded on the wire (matching the
existing dict handling), so callers can pass a natural Python list
for JSON-array wire params.
- URL-encodable-params adapter accepts float in addition to
str / int / bool; server-side rejection of a wrong-typed float now
surfaces cleanly with `TinyFish Search:` attribution + docs link.
- Assorted comment / docstring / test-fixture hygiene (no logic changes).
## Tests
70 unit + integration tests pass locally. Live-tested against
production TinyFish with 6 diverse queries (basic / max_results /
country=US / language=ja / domain filter / fetch={"format":"html"}) --
all 6 pass every expected-behavior check.
* feat(tinyfish): make search provider permissive, attribute errors
Reshapes the TinyFish search provider so LiteLLM mirrors the TinyFish
Search API surface instead of maintaining a parallel cherry-pick.
Request side:
- Drop misleading request TypedDict
- Stop sending max_results on wire (TinyFish ignores it); clamp to [1,10]
client-side via self-threaded state
- Guard non-numeric max_results from bare ValueError
- Auto-JSON-encode dict params; lowercase bool serialization for ux-labs
Response side:
- Drop both Pydantic response models; parse directly into SearchResponse
so per-result extras flow through via extra="allow"
- Default missing title/url/snippet to "" instead of failing the call
- Read top-level parameter_warnings and re-fire as verbose_logger.warning
(pre-wired for upcoming TinyFish-side rollout; no-op today)
Error handling:
- Attributed _wrap_error helper at 3 call sites in transform_search_response
("TinyFish Search: <msg>. See https://docs.tinyfish.ai/search-api for
details.")
- Dispatch non-2xx responses through _wrap_error (fixes pre-existing bug
where 4xx/5xx silently returned empty SearchResponse)
- Wrap json.JSONDecodeError on 200 bodies
- Wrap pydantic.ValidationError for envelope-shape mismatches
Bug fix worth flagging: 4xx/5xx responses now raise an attributed
BaseLLMException instead of silently returning SearchResponse(results=[]).
Follow-up to #30634.
* fix(tinyfish): apply ruff format; guard OverflowError in max_results clamp
- Run ruff format on the touched files (CI lint job rejected the prior
commit's formatting).
- Add OverflowError to the except clause in the max_results clamp so
callers passing math.inf (or other non-finite floats) get the same
warn-and-ignore behavior as other malformed values. Greptile spotted
this in the first-pass review.
- Add test_max_results_infinity_float_warns_and_skips covering the
inf case.
* fix(tinyfish): apply --line-length 88 ruff format to match CI
CI uses 'ruff format --check --line-length 88'; my prior format pass
used the default line length, leaving several lines unwrapped. No
behavior change — purely whitespace.
* fix(tinyfish): reduce transform_search_response complexity; sort imports
CI's ruff strict-rule budget rejected the prior commit with:
- C901: transform_search_response complexity 16 > 10 (cap exceeded by 1)
- I001: import sort violation (cap exceeded by 1)
Extract two module-level helpers from transform_search_response to drop
its cyclomatic complexity:
- _default_missing_result_fields: in-place title/url/snippet defaulting
- _emit_parameter_warnings: defensive parameter_warnings reader
Auto-fix the import sort via ruff --fix.
No behavior change; the 59 existing tests still pass.
* test(tinyfish): cover defensive branches in _default_missing_result_fields
Codecov flagged 97.61% patch coverage (2 lines missing). The uncovered
lines were the non-dict raw_json and non-dict per-result item early-exits
in _default_missing_result_fields. Add two unit tests on the helper
directly to bring patch coverage to 100%.
* chore(tinyfish): apply ruff format to fix lint after staging merge
---------
Co-authored-by: Chenlu Ji <jichenlulu@gmail.com>
Search providers resolved the server-configured API key (e.g.
get_secret_str("SERPER_API_KEY")) in validate_environment whenever the
caller omitted api_key, while get_complete_url independently honored a
caller-supplied api_base. A caller who passes their own api_base and no
api_key therefore made the proxy send the operator's provider key to a
host they control; POST /search_tools/test_connection forwards
request-body api_base/api_key straight into asearch, so any authenticated
user could exfiltrate the server's search credentials.
Add a shared host-aware fallback in BaseSearchConfig.resolve_server_api_key
that only applies a server-managed secret when the caller-supplied
api_base is absent or resolves to a trusted host (the provider default or
the operator's own *_API_BASE env override); otherwise it refuses and asks
for an explicit api_key. The guard only triggers when a server secret
actually exists, so keyless and self-hosted providers (searxng, you.com
free tier) keep working. Every provider that carries a server secret is
migrated to the helper; dataforseo reuses the same guard for its
login:password basic-auth credentials.
This changes behavior for callers that previously passed a per-request
api_base while relying on a server-configured key: they must now pass an
explicit api_key, or the operator must configure the base via the
provider's *_API_BASE env var (which stays trusted).
* feat(search): add TinyFish as search provider
Adds TinyFish web search (GET https://api.search.tinyfish.ai) as the
16th search provider in LiteLLM. Follows the BaseSearchConfig pattern
used by other GET-based providers like Brave.
Includes unit tests in tests/test_litellm/ for full patch coverage.
* fix(search/tinyfish): use concrete types to pass any-discipline and ruff UP006/UP045
Replace typing.Dict/List/Optional/Union with modern syntax (dict, list,
X | None) and use concrete type parameters (dict[str, str] for headers,
dict[str, object] for params) to eliminate LIT009 Any-discipline
violations. Move _append_domain_filters to module level to avoid leaking
Any through self.
* fix(search/tinyfish): eliminate Any-typed values for any-discipline gate
Use Pydantic BaseModel and TypeAdapter at httpx/base-class boundaries
to validate untyped inputs (json(), params.get(), bare set). Three
genuine external boundaries annotated with any-ok.
* style: fix black formatting for long line
* fix(search/tinyfish): move any-ok comment to violation line for any-discipline gate
The any-discipline checker matches `# any-ok` comments by line number.
The comment was on the closing-paren line (127) but the violation was
on the call-expression line (126), so the suppression did not apply.
* fix(search/tinyfish): align with approved PR #30158
Drop explicit AND from domain filter query to match the approved
implementation. Set pricing to zero. Rename test to match behavior.
