alex s ca20626f84 fix(models): replay malformed tool-call arguments as valid JSON (#1327) ... * fix(models): replay malformed tool-call arguments as valid JSON A model that emits a tool call with truncated or otherwise invalid JSON arguments fails that one call, but the raw string is recorded in the session. Strict OpenAI-compatible servers (vLLM, SGLang) validate every assistant tool call in the request, so each later turn is rejected with "Assistant tool call function.arguments must be valid JSON" and the agent never recovers. The turn guard now rewrites such arguments on the way out to a JSON object carrying the original text, alongside the existing duplicate call-id repair. * fix(agents): tell the model to re-issue tool calls whose arguments are not valid JSON A streamed turn that ends mid-tool-call leaves the client with a JSON prefix as the arguments. Instead of the SDK's generic parse-error result, the tool wrapper now short-circuits with a clear 'not executed, re-issue with complete arguments' message so the model recovers in one turn. * fix(models): treat NaN/Infinity tool-call arguments as malformed * test(cost): pin model resolution in the provider-prefixed cost test * fix(models): treat over-nested tool-call arguments as malformed		2026-10-14 18:17:20 -04:00
..
__init__.py	Add configurable token / cost usage limits (#576)	2026-06-22 11:17:08 -04:00
conftest.py	fix(ci): make the pre-commit mypy hook and the test suite pass on a fresh checkout	2026-09-02 15:15:51 +03:00
test_agent_factory_shell.py	feat(llm): keep images away from text-only models (#1465)	2026-10-07 23:11:58 +03:00
test_agent_factory_tool_arguments.py	fix(models): replay malformed tool-call arguments as valid JSON (#1327)	2026-10-14 18:17:20 -04:00
test_agent_graph_coordination.py	fix(agents): stop parents waiting on finished non-interactive children	2026-09-02 22:11:12 +03:00
test_agent_tool_registration.py	feat(agents): let callers choose the top-level agent's finish tool (#1496)	2026-10-08 19:11:50 -04:00
test_api_spec.py	feat: support API specs and Postman collections as targets (#866)	2026-08-03 21:07:44 -07:00
test_api_spec_targets.py	feat: support API specs and Postman collections as targets (#866)	2026-08-03 21:07:44 -07:00
test_auth_cli.py	Sign in with a ChatGPT subscription for inference (#854)	2026-07-24 15:41:19 -07:00
test_budget_pause_policy.py	fix(budget): parked agents count as active; park never overwrites a stop	2026-09-30 03:13:40 +03:00
test_caido_bootstrap.py	perf: bootstrap Caido concurrently with the scan start (#1143)	2026-08-21 12:09:59 -07:00
test_caido_handle.py	perf: bootstrap Caido concurrently with the scan start (#1143)	2026-08-21 12:09:59 -07:00
test_cli_fail_on.py	fix(cli): let --fail-on through when no terminal is attached	2026-10-05 00:37:27 +03:00
test_cli_mcp_config.py	Add MCP server support (#1137)	2026-08-24 14:00:16 -04:00
test_cli_resume_picker.py	feat(cli): add -r for --resume and a title column to the resume picker	2026-10-06 07:51:00 +03:00
test_cli_target_list.py	feat(cli): strix cloud — managed platform CLI (login, scans, billing, and the rest of the API) (#1177)	2026-09-01 14:39:34 -04:00
test_cloud_cli.py	fix(cloud): print top-up instructions on 402 and guide oversize or archive --source (#1242)	2026-09-02 15:26:37 -04:00
test_cloud_cli_runtime.py	fix(ci): make the pre-commit mypy hook and the test suite pass on a fresh checkout	2026-09-02 15:15:51 +03:00
test_cloud_idempotency.py	fix(ci): make the pre-commit mypy hook and the test suite pass on a fresh checkout	2026-09-02 15:15:51 +03:00
test_cloud_payment_proxy.py	fix(ci): make the pre-commit mypy hook and the test suite pass on a fresh checkout	2026-09-02 15:15:51 +03:00
test_cloud_session.py	fix(ci): make the pre-commit mypy hook and the test suite pass on a fresh checkout	2026-09-02 15:15:51 +03:00
test_cloud_source_upload.py	fix(cloud): print top-up instructions on 402 and guide oversize or archive --source (#1242)	2026-09-02 15:26:37 -04:00
test_cloud_wallet.py	Link CLI wallet (#1222)	2026-09-01 16:00:32 -04:00
test_codex_auth.py	feat(tui): replace Textual with a Go/Bubble Tea interface (#941)	2026-08-03 19:23:07 -07:00
test_codex_streaming.py	Sign in with a ChatGPT subscription for inference (#854)	2026-07-24 15:41:19 -07:00
test_compaction.py	fix(llm): pass LLM_EXTRA_HEADERS through ModelSettings so they reach the agent loop (#937)	2026-07-29 19:38:06 -07:00
test_completions.py	feat(cli): strix cloud — managed platform CLI (login, scans, billing, and the rest of the API) (#1177)	2026-09-01 14:39:34 -04:00
test_config_loader.py	feat(web_search): add Exa as a web search provider alongside Perplexity (#1270)	2026-09-04 10:34:28 -07:00
test_console_logging.py	fix(cli): install the stderr log handler at startup and prepare the run state before the TUI launches	2026-10-04 05:44:06 +03:00
test_context_budget.py	perf: take heavy imports off the startup path and pre-warm them in the background (#1141)	2026-08-20 20:24:08 -07:00
test_cost_tracking.py	fix(models): replay malformed tool-call arguments as valid JSON (#1327)	2026-10-14 18:17:20 -04:00
test_coverage_tool.py	feat(agents): evidence discipline, and coverage as a first-class artifact (#961)	2026-08-24 03:34:09 -07:00
test_dedupe_model.py	fix(config): drop the stored LLM connection when a linked env var changes	2026-09-02 16:10:52 +03:00
test_deferred_session.py	feat(runtime): accept an awaitable extra_files in create_or_reuse so the sandbox create does not wait for it	2026-10-14 03:32:29 +03:00
test_disable_streaming.py	feat(llm): structured per-attempt provider request log with provider request ids (#1353)	2026-09-22 20:49:41 -07:00
test_docker_client_delete.py	revert(runtime): drop the PTY teardown change in StrixDockerSandboxClient.delete()	2026-10-04 18:35:07 +03:00
test_docker_connection.py	fix(docker): keep DOCKER_HOST on from_env so TLS settings apply; a missing current context is an error	2026-10-05 03:00:25 +03:00
test_e2e_budget_lifecycle.py	refactor(tools): split wait_for_message into respond_to_user + wait_for_agents	2026-08-02 02:15:51 +03:00
test_execution.py	feat(agents): let callers choose the top-level agent's finish tool (#1496)	2026-10-08 19:11:50 -04:00
test_execution_request_log.py	feat(llm): structured per-attempt provider request log with provider request ids (#1353)	2026-09-22 20:49:41 -07:00
test_execution_transient_retry.py	feat(llm): retry 4xx model errors (#1486)	2026-10-07 18:35:33 -07:00
test_fenced_code.py	refactor: move strix/viewer under strix/interface	2026-07-26 13:11:14 -07:00
test_finish_coverage_gate.py	feat(agents): evidence discipline, and coverage as a first-class artifact (#961)	2026-08-24 03:34:09 -07:00
test_go_tui_runtime.py	fix(cli): install the stderr log handler at startup and prepare the run state before the TUI launches	2026-10-04 05:44:06 +03:00
test_hooks.py	feat(agents): let callers choose the top-level agent's finish tool (#1496)	2026-10-08 19:11:50 -04:00
test_import_warmup.py	test(warmup): assert wait_for_import_warmup blocks until the thread finishes	2026-09-05 02:45:34 +03:00
test_inputs.py	fix(inputs): send reasoning_effort as configured; no route-specific handling	2026-10-02 18:17:27 +03:00
test_install_script.py	Add Linux ARM64 standalone release support (#886)	2026-07-26 16:27:02 -07:00
test_list_reports.py	report: add update_vulnerability_report so an agent can revise a filed finding (#1210)	2026-09-01 13:07:17 -07:00
test_llm_extra_headers.py	fix(llm): apply LLM_EXTRA_HEADERS on native OpenAI route even without a custom base	2026-07-30 04:13:25 +03:00
test_llm_request_log.py	feat(llm): log the upstream provider behind OpenRouter (#1459)	2026-10-07 18:35:12 -07:00
test_local_sources.py	runtime: read_only local sources become :ro bind mounts	2026-09-20 06:10:13 +03:00
test_main_launch.py	fix(cli): let --fail-on through when no terminal is attached	2026-10-05 00:37:27 +03:00
test_mcp_client.py	fix(mcp): load catalogs before agents discover connections (#1492)	2026-10-08 12:42:39 -04:00
test_mcp_resilience.py	fix(mcp): keep the session on tool-call protocol errors and report quarantine truthfully (#1228)	2026-09-01 22:43:54 -04:00
test_model_retry.py	Sign in with a ChatGPT subscription for inference (#854)	2026-07-24 15:41:19 -07:00
test_models.py	feat(llm): detect whether a model accepts image input (#1460)	2026-10-07 22:58:43 +03:00
test_notes.py	Treat literal 'null'/'none' strings as absent for optional tool args (#1164)	2026-08-25 13:21:12 -04:00
test_output_store.py	feat(context): spill oversized tool output into the sandbox workspace (#882)	2026-07-26 14:42:22 -07:00
test_packaging.py	feat(tui): replace Textual with a Go/Bubble Tea interface (#941)	2026-08-03 19:23:07 -07:00
test_preflight_header_values.py	fix(preflight): check extra headers for subscription models and the dedupe key as sent	2026-10-04 01:48:35 +03:00
test_preflight_timeout.py	test(preflight): exercise warm_up_llm with a dedicated dedupe model without touching process-wide SDK defaults	2026-10-04 23:12:23 +03:00
test_pricing.py	test(pricing): accept any identically priced provider for bare grok-4.5	2026-10-04 20:38:45 +03:00
test_provider_dependencies.py	fix(deps): declare boto3 directly and exercise Vertex AI and Bedrock auth from the frozen binary in CI	2026-10-04 22:05:21 +03:00
test_proxy_client.py	fix(proxy): log all Caido SDK errors as warnings	2026-10-12 22:18:42 +03:00
test_pty_warning_filter.py	fix(logging): suppress Agents SDK PTY warning that interferes with TUI (#1392)	2026-10-07 11:32:42 -07:00
test_report_coverage.py	feat(agents): evidence discipline, and coverage as a first-class artifact (#961)	2026-08-24 03:34:09 -07:00
test_report_pdf.py	fix(viewer): harden PDF report rendering (#1192)	2026-08-31 20:22:33 -04:00
test_report_writer.py	csv injection hardening (#1203)	2026-08-30 23:36:16 -04:00
test_reporting_fields.py	fix(reporting): drop the static-analysis disclaimer from dependency evidence (#1520)	2026-10-14 10:59:11 -04:00
test_reporting_tool.py	fix: calibrate vulnerability severity to demonstrated impact	2026-08-03 23:40:32 +03:00
test_resume_picker.py	test(resume-picker): put the pty in cbreak so the key-reader test can't hang on macOS (#1527)	2026-10-14 15:55:22 -04:00
test_run_summaries.py	feat(cli): add -r for --resume and a title column to the resume picker	2026-10-06 07:51:00 +03:00
test_runner_interrupt.py	fix(runner): resume after a user interrupt instead of failing (#1023)	2026-08-08 16:44:12 -07:00
test_runner_mcp.py	fix(mcp): load catalogs before agents discover connections (#1492)	2026-10-08 12:42:39 -04:00
test_runner_rate_limit.py	fix(core): recover from hallucinated tool names instead of ending the scan	2026-08-04 06:14:54 +03:00
test_runner_root_prompt.py	fix(mcp): load catalogs before agents discover connections (#1492)	2026-10-08 12:42:39 -04:00
test_runner_teardown.py	Stop false "ended without calling finish_scan" error on PR reviews (#1449)	2026-10-05 19:58:20 -04:00
test_sarif.py	feat(agents): evidence discipline, and coverage as a first-class artifact (#961)	2026-08-24 03:34:09 -07:00
test_sarif_stride.py	fix(ci): make the pre-commit mypy hook and the test suite pass on a fresh checkout	2026-09-02 15:15:51 +03:00
test_secret_files.py	Create credential files with owner-only permissions (#945)	2026-08-03 19:36:59 -07:00
test_session_entries.py	runtime: read_only local sources become :ro bind mounts	2026-09-20 06:10:13 +03:00
test_session_fd.py	fix(ci): make the pre-commit mypy hook and the test suite pass on a fresh checkout	2026-09-02 15:15:51 +03:00
test_skill_dir_extension.py	feat(llm): keep images away from text-only models (#1465)	2026-10-07 23:11:58 +03:00
test_state_coverage_artifact.py	feat(agents): evidence discipline, and coverage as a first-class artifact (#961)	2026-08-24 03:34:09 -07:00
test_state_repo_context.py	fix(report): omit SARIF provenance for multiple repos (#726)	2026-07-10 09:41:18 -04:00
test_stream_idle_timeout.py	feat(llm): bound the first stream event and the whole stream (#1487)	2026-10-07 18:35:45 -07:00
test_telemetry_errors.py	feat(telemetry): classify error beacons by phase and exception class	2026-09-05 04:08:09 +03:00
test_telemetry_resume.py	handle resume tokens gracefully (#1097)	2026-08-17 16:55:27 -04:00
test_threat_model_tool.py	Mirror the run's threat models into its state dir so resume keeps them	2026-08-27 01:36:47 +03:00
test_todo.py	fix(todo): stop a todo plan failing on priority or duplicates (#1021)	2026-08-08 15:18:48 -07:00
test_tool_call_arguments.py	fix(models): replay malformed tool-call arguments as valid JSON (#1327)	2026-10-14 18:17:20 -04:00
test_tool_call_ids.py	Fill in blank tool-call ids so strict providers accept the history (#1355)	2026-09-23 18:34:22 -07:00
test_tool_call_ids_providers.py	ci: run ruff, mypy, bandit, pytest, Go TUI and viewer checks on every pull request	2026-10-04 21:07:06 +03:00
test_tool_call_limits.py	fix(llm): cap the tool calls one assistant response may queue (#977)	2026-08-06 00:06:59 +03:00
test_tool_param_descriptions.py	refactor(agents): replace respond_to_user with a text-free wait_for_user	2026-10-05 04:09:17 +03:00
test_tui_backend_controller.py	chore(models): remove the model quality warning and its allowlists	2026-09-30 10:04:28 +03:00
test_tui_backend_server.py	Fix user message retry lifecycle and TUI sync	2026-08-28 23:46:49 +03:00
test_tui_protocol_conformance.py	feat(tui): replace Textual with a Go/Bubble Tea interface (#941)	2026-08-03 19:23:07 -07:00
test_tui_resume_history.py	Fix user message retry lifecycle and TUI sync	2026-08-28 23:46:49 +03:00
test_unknown_tool_recovery.py	fix(core): recover from hallucinated tool names instead of ending the scan	2026-08-04 06:14:54 +03:00
test_unraisable_hook.py	refactor(telemetry): keep only the unraisable hook, no docstrings	2026-10-04 18:35:07 +03:00
test_update_check.py	fix(update): re-exec runs the new binary after self-update (endless update-prompt loop) (#1168)	2026-08-25 15:13:35 -07:00
test_usage_subscription.py	Sign in with a ChatGPT subscription for inference (#854)	2026-07-24 15:41:19 -07:00
test_utf8_streams.py	style: drop docstrings from the UTF-8 stream helpers	2026-10-04 01:19:48 +03:00
test_viewer.py	fix(viewer): show stopped run status	2026-09-04 01:10:10 +03:00
test_viewer_auth.py	refactor: move strix/viewer under strix/interface	2026-07-26 13:11:14 -07:00
test_viewer_runs_gating.py	refactor: move strix/viewer under strix/interface	2026-07-26 13:11:14 -07:00
test_wait_dedupe.py	fix(agents): stop parents waiting on finished non-interactive children	2026-09-02 22:11:12 +03:00
test_wait_for_user.py	refactor(agents): replace respond_to_user with a text-free wait_for_user	2026-10-05 04:09:17 +03:00
test_web_search.py	fix(web_search): send only the agent's query to Exa search	2026-09-13 19:40:50 +03:00
test_workspace_files.py	feat: place caller-provided files into the sandbox workspace (extra_files, --workspace-file) (#1085)	2026-08-14 16:43:08 -04:00