Ahmed AllamandAhmed Allam b9c2592b53 fix(llm): retry statusless mid-stream provider errors (quota/billing) ...

The SDK's http_status retry policy only retries errors carrying a known
HTTP status code, but quota/billing (and other provider-side) failures
often surface inside a streamed response as a bare error with no status
code, so they were failing on the first attempt. Add a statusless retry
policy to DEFAULT_MODEL_RETRY so they are retried (before any content is
streamed; user aborts are never retried), restoring the pre-SDK engine's
resilience. If the provider is genuinely exhausted, the error still
propagates and fails the scan after retries.

2026-07-17 16:47:14 -07:00

..

__init__.py

Add configurable token / cost usage limits (#576)

2026-06-22 11:17:08 -04:00

test_agent_factory_shell.py

Default sandbox exec commands to Bash (#764)

2026-07-14 03:44:05 -07:00

test_agent_tool_registration.py

Allow scan agent tool registration (#733)

2026-07-11 23:58:51 -04:00

test_cli_target_list.py

Add target list CLI option (#711)

2026-07-06 23:33:08 -04:00

test_config_loader.py

feat(settings): add force_required_tool_choice to LlmSettings (#730)

2026-07-10 18:36:33 -04:00

test_cost_tracking.py

fix(report): restore cost tracking for OpenRouter and other LiteLLM-routed models (#801)

2026-07-17 13:38:23 -07:00

test_docker_client_delete.py

fix(runtime): swallow torn-down docker socket in sandbox delete() (#721)

2026-07-10 00:13:35 -04:00

test_execution.py

Add configurable token / cost usage limits (#576)

2026-06-22 11:17:08 -04:00

test_hooks.py

Add configurable token / cost usage limits (#576)

2026-06-22 11:17:08 -04:00

test_inputs.py

Support routed OpenAI required tool choice (#732)

2026-07-10 18:43:07 -04:00

test_local_dir_staging.py

fix(runtime): stage symlink-safe copies for LocalDir uploads (#766)

2026-07-14 17:40:23 -04:00

test_local_sources.py

Add target list CLI option (#711)

2026-07-06 23:33:08 -04:00

test_model_retry.py

fix(llm): retry statusless mid-stream provider errors (quota/billing)

2026-07-17 16:47:14 -07:00

test_models.py

Warn when configured LLM is not frontier-recommended (#586)

2026-07-13 17:41:44 -07:00

test_notes.py

fix: avoid note ID collisions (#630)

2026-07-02 22:54:44 -04:00

test_optional_deps.py

fix(providers): declare bedrock + vertex extras and add provider import-error hints (#588)

2026-07-07 10:24:49 -04:00

test_provider_hints.py

fix(providers): match google submodule imports and walk full exception chain

2026-07-10 07:21:47 -07:00

test_proxy_client.py

revert(proxy): drop overfit Caido reconnect/HTTPQL band-aids, keep serialization lock (#799)

2026-07-17 13:18:40 -07:00

test_proxy_renderer.py

fix(tui): show 'more content available' for view_request over 15 lines (#687)

2026-07-06 03:50:02 -07:00

test_report_writer.py

fix(reporting): require advisory_cvss for dependency findings + add SCA TUI renderer (#753)

2026-07-12 17:31:49 -07:00

test_reporting_fields.py

fix(reporting): require advisory_cvss for dependency findings + add SCA TUI renderer (#753)

2026-07-12 17:31:49 -07:00

test_runner_rate_limit.py

fix(core): bound per-agent image memory (proactive budget + inherited-context scrub) (#779)

2026-07-15 18:13:42 -07:00

test_runner_root_prompt.py

Add root scan prompt options (#750)

2026-07-12 12:31:15 -04:00

test_sarif_stride.py

feat(report): tag SARIF rules with STRIDE legs derived from CWE (#708)

2026-07-06 21:19:53 -04:00

test_sarif.py

feat(report): SARIF 2.1.0 emitter for CI / code-scanning integration (#626)

2026-07-03 10:43:31 -04:00

test_session_entries.py

fix(runtime): stage symlink-safe copies for LocalDir uploads (#766)

2026-07-14 17:40:23 -04:00

test_skill_dir_extension.py

Add skill directory registration (#746)

2026-07-12 12:05:58 -04:00

test_state_repo_context.py

fix(report): omit SARIF provenance for multiple repos (#726)

2026-07-10 09:41:18 -04:00