Devika Verma ff9b955494 fix(observability): a streamed model step ends as its reply arrives; a turn's end waits for shadow checks (OPE-244) ...

Two races found by running the schema test repeatedly:

- The streamed view ended its model step only after the engine had read
  the final piece. The engine could add the reply and end the turn first,
  and the turn's end then closed the step as interrupted, without its
  usage or finish reason. The step now ends when the final piece
  arrives, before the engine sees it.
- A shadow check runs in the background and can outlast the turn's last
  event. The turn's end is now recorded with the time of its ending
  event but sent once running shadow checks finish (at most 30 s), so
  their steps are not closed as interrupted while they run.

Also: a server test's fake provider answers the session title apart, so
the title call can no longer take the turn's only reply.

2026-11-02 10:50:08 +05:30

..

corpora

test(observability): the shared schema copy is recording format 1.1 (OPE-244)

2026-11-02 10:41:15 +05:30

conftest.py

Merge pull request #250 from Dhevenddra/fix/workspace-trust-windows-acl

2026-10-17 15:46:40 +05:30

proposal_fixtures.py

Add structured outcome and staffing proposals

2026-09-20 11:42:30 -07:00

test_accounts.py

Connectors on machines: grant handoff, GitHub and Slack on a box, subscriptions

2026-09-06 10:19:23 -07:00

test_action_sequence_eval.py

test(security): evaluate complete action sequences

2026-10-25 15:14:12 -07:00

test_anthropic_caching.py

Enable prompt caching on the Anthropic provider

2026-07-27 22:47:30 -07:00

test_anthropic_provider.py

Coworkers: models per coworker, reviewer and lead personas, team store

2026-09-17 12:19:11 -07:00

test_approval_guidance.py

Fail closed when the approval owner is unavailable

2026-09-20 19:40:18 -07:00

test_approval_integrity.py

Tests follow the web search settings API

2026-10-25 19:21:12 -07:00

test_artifact_walk.py

fix: stop artifact walk entering OS app-data dirs; context bar off by default

2026-07-30 13:10:30 -07:00

test_ask_user_upgrades.py

OPE-153: the Slack mirror gets the same way out the card has

2026-10-10 11:24:01 +05:30

test_attachment_workspace.py

Cover composer PDF materialization end to end

2026-09-25 19:22:03 +05:30

test_attachments.py

Make the time a tool instead of a line in every turn (OPE-192, final fix)

2026-09-17 18:25:47 +05:30

test_attendance_auto.py

feat(reviewer): facts computed by code reach the Auto-Approve reviewer (OPE-235)

2026-10-29 11:23:49 +05:30

test_audit_export.py

Remote machines: identity, reverse channel, acceptor, sealed key wallet

2026-09-05 08:00:16 -07:00

test_audit_redaction.py

security(audit): redact nested arguments and result previews

2026-09-11 00:47:55 +08:00

test_auto_approve_settings.py

Carry reviewer cache tokens into the metering badge

2026-08-22 09:51:16 +05:30

test_auto_approve.py

feat(reviewer): facts computed by code reach the Auto-Approve reviewer (OPE-235)

2026-10-29 11:23:49 +05:30

test_automation_create.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_automation.py

feat(observability): the engine records turns and tool steps (OPE-244)

2026-11-01 13:10:13 +05:30

test_autotitle.py

fix(server): auto-title in the session's language, not the prompt's

2026-09-08 09:10:31 +08:00

test_base_dir.py

Remote machines: identity, reverse channel, acceptor, sealed key wallet

2026-09-05 08:00:16 -07:00

test_bedrock_provider.py

models: add Claude 5 family to Bedrock matrix (Fable 5, Opus 5, Sonnet 5)

2026-10-25 14:10:11 -07:00

test_board_image_lifecycle.py

Harden board-owned image attachments and local retention

2026-09-19 23:33:33 -07:00

test_browser_root_scoping.py

OPE-122: enforce granted roots in browser upload and screenshot

2026-08-19 19:00:50 +05:30

test_browser_tabs.py

fix: track active browser tabs

2026-10-25 15:14:18 -07:00

test_browser_url_guard.py

security: vet every browser navigation, not just the model-supplied URL

2026-08-26 06:51:35 -07:00

test_builtin_personas.py

Toolset dedup: one windowed reader, sleep_until only, browser trim/rename

2026-08-20 23:06:36 -07:00

test_cache_breakpoint_placement.py

Make the time a tool instead of a line in every turn (OPE-192, final fix)

2026-09-17 18:25:47 +05:30

test_catalog.py

Toolset dedup: one windowed reader, sleep_until only, browser trim/rename

2026-08-20 23:06:36 -07:00

test_chat_tools.py

Connectors on machines: grant handoff, GitHub and Slack on a box, subscriptions

2026-09-06 10:19:23 -07:00

test_cli_surface.py

The openworker program for the Mac

2026-10-05 15:28:03 -07:00

test_clock_tool.py

Make the time a tool instead of a line in every turn (OPE-192, final fix)

2026-09-17 18:25:47 +05:30

test_cloud_server.py

Fix Slack connect dead-ending on "not signed in" for expired cloud sessions

2026-10-25 15:14:12 -07:00

test_cloud.py

Fix Slack connect dead-ending on "not signed in" for expired cloud sessions

2026-10-25 15:14:12 -07:00

test_code_tools.py

fix: search workspaces under ignored directory names (#576)

2026-09-26 14:54:05 +03:00

test_codex_provider.py

fix(codex-auth): let the sign-in callback bind somewhere a container can reach

2026-09-04 21:19:05 +02:00

test_command_matching.py

PR3: split compound commands and check each part independently

2026-08-11 11:43:57 -07:00

test_compaction_engine.py

Make the compaction summary reliable, and stop losing the task statement (OPE-189)

2026-09-16 15:31:06 +05:30

test_compaction_persisted_summary.py

Persist the compaction record on the compacted notice and event (OPE-170 p2)

2026-09-08 21:24:36 +05:30

test_compaction_smoke.py

compaction: harden the smoke against per-turn event loops (OPE-27)

2026-07-29 18:00:38 +05:30

test_compaction_transcript.py

Make the compaction summary reliable, and stop losing the task statement (OPE-189)

2026-09-16 15:31:06 +05:30

test_compaction.py

test(compaction): make the new checks fail for the right reasons

2026-10-25 15:18:05 -07:00

test_config.py

feat(auto-approve): an approved plan is evidence for exactly its steps (OPE-237)

2026-10-29 14:08:30 +05:30

test_configured_spawn.py

Let leads own repository setup and preserve configured targets

2026-09-20 16:59:18 -07:00

test_connections.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_connector_registry.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_connectors_allowlist.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_connectors.py

Merge pull request #467 from zhouzhuozhzh-maker/codex/fix-465-outlook-pagination

2026-10-25 14:58:08 -07:00

test_console_scripts.py

One command on the path: openworker

2026-10-05 15:00:42 -07:00

test_context_block_placement.py

Make the time a tool instead of a line in every turn (OPE-192, final fix)

2026-09-17 18:25:47 +05:30

test_conversation_atomicity.py

Make the conversation-log shrink rewrite atomic

2026-07-24 14:28:16 +09:00

test_conversation_jsonl_robustness.py

Tolerate a corrupt line when loading a conversation .jsonl

2026-07-23 14:13:07 -07:00

test_conversation_save_mid_change.py

feat(observability): recorder, recordings.db store and stable message ids (OPE-244)

2026-11-01 12:08:27 +05:30

test_conversation_store.py

Reject path-traversal session ids in the conversation store

2026-07-23 14:09:28 -07:00

test_conversations_repair.py

fix: don't inject placeholder for trailing pending tool calls

2026-08-26 21:55:48 +05:30

test_corpus_schema.py

chore(eval): one common schema for every reviewer corpus, owner-ruling re-keys and sealed fresh rows, old run reports out of the repo (OPE-225)

2026-10-29 16:54:24 +05:30

test_dangerous_mode.py

Two switches for unattended work: a dangerous mode and an auto attendance (OPE-196)

2026-10-02 15:11:21 +05:30

test_decision_matrix_golden.py

Phase 0: golden decision table for the permission engine

2026-08-11 11:18:21 -07:00

test_decision_reviewer.py

feat(auto-approve): decision reviewers take the engine's facts; an approved plan step counts as asked for (OPE-224)

2026-10-29 16:46:22 +05:30

test_devops_team.py

Shipping lineup: remove Chat, ship Code disabled, gate unshipped personas

2026-08-20 17:59:48 -07:00

test_devsecops_team.py

Shipping lineup: remove Chat, ship Code disabled, gate unshipped personas

2026-08-20 17:59:48 -07:00

test_dm_routing.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_durable_resume.py

fix(engine): stop replaying an abandoned partial turn on retry

2026-10-25 15:13:33 -07:00

test_edit_tool_guidance.py

Bound tool results, steer edits, keep compacted turns readable (OPE-186)

2026-09-15 15:09:47 +05:30

test_egress_and_overrides.py

OPE-136: MCP permission model — EXTERNAL floor, durable per-tool trust, run grants, honest approval plumbing

2026-08-31 08:06:14 +05:30

test_email_tools.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_engine_stop.py

feat(observability): recorder, recordings.db store and stable message ids (OPE-244)

2026-11-01 12:08:27 +05:30

test_engine.py

fix(engine): stop replaying an abandoned partial turn on retry

2026-10-25 15:13:33 -07:00

test_environment.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_eval_facts.py

fix(auto-approve): plan steps only ever help; URL destinations match their host (OPE-237)

2026-10-29 14:08:30 +05:30

test_eval_metrics.py

chore(eval): one common schema for every reviewer corpus, owner-ruling re-keys and sealed fresh rows, old run reports out of the repo (OPE-225)

2026-10-29 16:54:24 +05:30

test_fake_slack.py

security: harden Slack approval handling

2026-07-24 22:33:13 -07:00

test_finish_reason.py

Persist finish_reason on assistant messages (OPE-173)

2026-09-08 16:32:11 +05:30

test_folder_present.py

Mac: no Downloads permission prompt at start

2026-09-29 21:23:41 -07:00

test_gallery_contract.py

Add structured outcome and staffing proposals

2026-09-20 11:42:30 -07:00

test_gate_sync.py

Add structured outcome and staffing proposals

2026-09-20 11:42:30 -07:00

test_gateway_inbox_reply.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_gcal_accounts.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_gemini_provider.py

Coerce union-typed JSON Schema for Gemini tool declarations

2026-07-23 07:43:24 -07:00

test_github_installs.py

Merge pull request #252 from Dhevenddra/fix/relay-tests-hermetic-name-lookup

2026-10-25 14:57:59 -07:00

test_gmail_accounts.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_headless_mcp.py

OPE-228 headless: attach MCP servers to openworker run

2026-10-22 16:09:38 +05:30

test_headless_run.py

run: --no-web-tools keeps web_search and web_fetch out of the tool list (OPE-226)

2026-10-20 17:35:20 +05:30

test_headless_trajectory.py

Trajectory keeps the partial cost total, marked incomplete

2026-10-25 14:24:16 -07:00

test_hubspot_portals.py

Connectors on machines: grant handoff, GitHub and Slack on a box, subscriptions

2026-09-06 10:19:23 -07:00

test_idle_checkins.py

Make team coordination event driven and quiet

2026-09-21 06:02:41 -07:00

test_inbox_mirror_answerable.py

Mark the relay Slack adapter as drawing buttons

2026-10-25 15:18:00 -07:00

test_inbox_routing.py

Parse inbox reply intent from the leading word, not substrings

2026-07-31 14:10:37 -07:00

test_inbox.py

OPE-136: MCP permission model — EXTERNAL floor, durable per-tool trust, run grants, honest approval plumbing

2026-08-31 08:06:14 +05:30

test_inert_writes.py

test(auto-approve): files the protected-file floor covers are human-only, not reviewer-bound (OPE-233)

2026-10-29 11:23:21 +05:30

test_interactions.py

OPE-153: the Slack mirror gets the same way out the card has

2026-10-10 11:24:01 +05:30

test_layered_corpora.py

chore(eval): one common schema for every reviewer corpus, owner-ruling re-keys and sealed fresh rows, old run reports out of the repo (OPE-225)

2026-10-29 16:54:24 +05:30

test_list_files_folders.py

List folders as well as files in list_files (OPE-203)

2026-10-02 15:11:21 +05:30

test_llamacpp_setup.py

llama.cpp setup: licence per model, verified downloads, 429 waits

2026-10-26 11:24:36 -07:00

test_local_machine_windows.py

Windows machine facts: no console window, readable processor name

2026-10-06 13:00:28 -07:00

test_local_server.py

Add Jan, Docker Model Runner and mlx-lm as local server providers

2026-10-26 11:10:29 -07:00

test_machine_poll.py

Connectors on machines: grant handoff, GitHub and Slack on a box, subscriptions

2026-09-06 10:19:23 -07:00

test_mangled_tool_calls.py

Diagnose truncated tool calls instead of executing their mangled args

2026-08-15 06:55:10 -07:00

test_matrix_current_models.py

Add LM Studio as a local server provider

2026-10-25 20:55:44 -07:00

test_max_output_tokens.py

Make the per-reply output-token limit configurable (OPE-177)

2026-09-08 17:08:29 +05:30

test_mcp_connectors.py

fix(tests): import ExceptionGroup from backport for Python 3.10 compatibility

2026-08-26 02:30:48 +00:00

test_mcp_floor.py

Fix CI: teach provider fakes messages.stream, un-Windows the write-fence probe

2026-08-31 08:48:28 +05:30

test_mcp_oauth.py

Fix one-click OAuth connect for servers that register a confidential client

2026-09-27 18:15:04 -04:00

test_mcp_tool_selection.py

OPE-136: MCP permission model — EXTERNAL floor, durable per-tool trust, run grants, honest approval plumbing

2026-08-31 08:06:14 +05:30

test_mcp_trust.py

OPE-136: MCP permission model — EXTERNAL floor, durable per-tool trust, run grants, honest approval plumbing

2026-08-31 08:06:14 +05:30

test_mcp.py

fix(mcp): prevent tool-call arguments from overriding MCP routing

2026-08-28 23:15:30 -07:00

test_memory_api.py

Memory V1: remembered facts, your instructions, one screen

2026-07-28 20:32:14 +05:30

test_memory.py

feat(memory): add SQLite FTS5 search index and memory_search tool (#616)

2026-09-06 01:56:18 +02:00

test_mention_router.py

Connectors on machines: grant handoff, GitHub and Slack on a box, subscriptions

2026-09-06 10:19:23 -07:00

test_mention_store_robustness.py

fix(mentions): survive non-object JSON and write mention_threads.json atomically (#709)

2026-09-30 12:02:35 +05:30

test_message_ids.py

feat(observability): recorder, recordings.db store and stable message ids (OPE-244)

2026-11-01 12:08:27 +05:30

test_message_source.py

Make the time a tool instead of a line in every turn (OPE-192, final fix)

2026-09-17 18:25:47 +05:30

test_message_timestamps.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_model_config.py

Reasoning effort and thinking controls beside the model

2026-10-06 11:49:22 -07:00

test_model_controls.py

Reasoning effort and thinking controls beside the model

2026-10-06 11:49:22 -07:00

test_model_errors.py

fix: add friendly error guidance for Qwen API key authentication failures

2026-10-17 16:32:19 +05:30

test_multiroot.py

Make the time a tool instead of a line in every turn (OPE-192, final fix)

2026-09-17 18:25:47 +05:30

test_network_access.py

OpenShell: the agent and the card are told which sites the sandbox blocked

2026-10-03 16:15:53 -07:00

test_observability_engine.py

fix(observability): a streamed model step ends as its reply arrives; a turn's end waits for shadow checks (OPE-244)

2026-11-02 10:50:08 +05:30

test_observability_golden.py

feat(observability): read endpoints, screen numbers and live step messages (OPE-244)

2026-11-02 09:17:42 +05:30

test_observability_model_steps.py

fix(observability): a streamed model step ends as its reply arrives; a turn's end waits for shadow checks (OPE-244)

2026-11-02 10:50:08 +05:30

test_observability_read_api.py

feat(gui): Steps panel with the timeline, step details and session usage (OPE-244)

2026-11-02 09:51:10 +05:30

test_observability_reviewer_helper.py

feat(observability): decision-model reviewer checks get a model step with usage (OPE-244)

2026-11-02 09:13:37 +05:30

test_observability_schema.py

fix(observability): recordings fit the shared schema; test the engine's own recordings against it (OPE-244)

2026-11-02 10:39:05 +05:30

test_observability_stamps_context.py

fix(observability): recordings fit the shared schema; test the engine's own recordings against it (OPE-244)

2026-11-02 10:39:05 +05:30

test_observability_store.py

feat(observability): wait steps, summary steps and each tool call's decision path (OPE-244)

2026-11-02 08:45:40 +05:30

test_observability_waits.py

feat(observability): wait steps, summary steps and each tool call's decision path (OPE-244)

2026-11-02 08:45:40 +05:30

test_ollama_context.py

Ollama: a context size for this machine, errors mid-stream, and a kept answer

2026-10-05 19:49:34 -07:00

test_openai_provider.py

tests: cover OpenAI provider gaps — key resolution, Qwen XML salvage, stream edges

2026-07-26 15:24:00 +01:00

test_openai_responses.py

Merge main into feature/permission-modes

2026-08-23 01:01:57 -07:00

test_openrouter_auth.py

OpenRouter account as its own Subscriptions provider

2026-10-06 09:47:56 -07:00

test_openrouter_routes.py

OpenRouter account as its own Subscriptions provider

2026-10-06 09:47:56 -07:00

test_openshell_inside.py

Inside OpenShell, ask about a blocked site and wait

2026-10-05 06:23:01 -07:00

test_pdf_support.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_permission_gate_corpus.py

test: compare gate row count to the corpus file

2026-10-25 15:14:47 -07:00

test_permissions_risk.py

fix(security): refuse find's fprint family under a bare allowlist entry

2026-09-25 12:51:12 +05:30

test_persona_connections.py

Toolset dedup: one windowed reader, sleep_until only, browser trim/rename

2026-08-20 23:06:36 -07:00

test_persona_loading.py

Merge branch 'main' into security/persona-git-url-validation

2026-10-05 14:10:42 +05:30

test_persona_manifest.py

Coworkers: models per coworker, reviewer and lead personas, team store

2026-09-17 12:19:11 -07:00

test_persona_models.py

Coworkers: models per coworker, reviewer and lead personas, team store

2026-09-17 12:19:11 -07:00

test_persona_registry.py

Hold the SWE Lead back from the release picker

2026-09-29 21:23:31 -07:00

test_persona_skills.py

personas: wire manifest skills + mcp into sessions (OPE-58)

2026-08-10 22:16:38 -07:00

test_plan_approval.py

fix(auto-approve): a plan step vouches for exactly its file, host and folder (OPE-237)

2026-10-29 14:08:30 +05:30

test_plan_mode.py

Step 2: Auto-Approve mode - the reviewer, the hook, and the renames

2026-08-12 12:42:17 -07:00

test_plan_steps.py

fix(auto-approve): a plan step vouches for exactly its file, host and folder (OPE-237)

2026-10-29 14:08:30 +05:30

test_project_bindings.py

Project identity: binding > git > path; named memories and boards

2026-08-23 01:24:58 -07:00

test_projects.py

Escape LIKE wildcards when re-keying board cursors

2026-08-26 03:58:21 +00:00

test_proposal_contract.py

Carry explicit approval guidance into team reviews

2026-09-20 19:31:01 -07:00

test_protected_paths.py

fix(permissions): protect more files that run later; more plain git settings (OPE-231)

2026-10-29 11:08:02 +05:30

test_provenance.py

fix(security): record attached --output= download paths for provenance

2026-10-12 00:19:10 +05:30

test_provider_router.py

test: the server's provider is the router wrapped for recording (OPE-244)

2026-11-02 09:45:08 +05:30

test_provider_verify.py

Azure OpenAI as its own provider card

2026-10-26 11:17:17 -07:00

test_providers.py

Merge remote-tracking branch 'origin/main' into feat/azure-openai-card

2026-10-26 12:01:37 -07:00

test_readonly_allowlist.py

fix(permissions): git commands run under the grant only when the project's git settings are inert (OPE-232)

2026-10-28 22:29:10 +05:30

test_readonly_git_settings.py

fix(permissions): git commands run under the grant only when the project's git settings are inert (OPE-232)

2026-10-28 22:29:10 +05:30

test_readonly_grant.py

fix(permissions): env and git config ask; the card's grant button follows the shell (OPE-232)

2026-10-28 22:29:10 +05:30

test_readonly_scoping.py

fix(permissions): the read-only checker allows only reviewed flags (OPE-232)

2026-10-28 22:29:10 +05:30

test_readonly_shell_aware.py

fix(permissions): env and git config ask; the card's grant button follows the shell (OPE-232)

2026-10-28 22:29:10 +05:30

test_readonly_tier.py

feat(auto-approve): read-only shell commands run without a reviewer call on macOS/Linux (OPE-234)

2026-10-29 14:08:31 +05:30

test_reasoning_effort.py

Handle effort "none" on every provider: Anthropic omits it, OpenAI-compat sends it

2026-09-29 17:58:35 +05:30

test_reasoning_replay.py

Replay reasoning on the OpenAI-compatible path (OPE-178)

2026-09-09 19:19:55 +05:30

test_remote_home.py

Machine service: start after the OpenShell gateway; honest start-up messages

2026-09-29 21:27:19 -07:00

test_review_facts.py

fix(permissions): the secrets floor judges file contents, more key shapes and ordinary-named credential files (OPE-236)

2026-10-29 11:24:13 +05:30

test_reviewer_persona.py

Hold the SWE Lead back from the release picker

2026-09-29 21:23:31 -07:00

test_risk_overrides.py

OPE-136: MCP permission model — EXTERNAL floor, durable per-tool trust, run grants, honest approval plumbing

2026-08-31 08:06:14 +05:30

test_run_cli.py

run: the retry line gives the cause, and a stop signal ends the wait between retries

2026-10-04 15:46:50 -07:00

test_run_grant.py

OPE-136: MCP permission model — EXTERNAL floor, durable per-tool trust, run grants, honest approval plumbing

2026-08-31 08:06:14 +05:30

test_sandbox_credentials.py

Sandbox settings v6: allowed-sites tick list, three-row OpenShell setup

2026-09-28 16:45:49 -07:00

test_sandbox_lifetime.py

Sandbox lifetime: a dropped engine closes its sandbox; shutdown closes all; orphans reaped at start

2026-09-21 20:56:08 -07:00

test_sandbox_openshell.py

OpenShell setup on a Mac: show Docker Desktop's host networking in the app

2026-10-04 18:36:12 -07:00

test_sandbox_runner.py

Tool runner on Windows: the daemon listens on a named pipe

2026-09-21 21:51:26 -07:00

test_sandbox_seatbelt.py

A site allowed on the card opens on the running sandbox too

2026-10-03 11:03:37 -07:00

test_sandbox_selection.py

Sandbox refusal: no reconnect loop; image check follows the driver (docker or podman) and stays out of remote gateways

2026-09-26 21:54:54 +05:30

test_sandbox_settings.py

Settings: with OpenShell chosen, only the allow list is offered

2026-10-04 18:21:46 -07:00

test_sandbox_setup_job.py

OpenShell 0.1.2 on a Mac: check Docker Desktop's host networking and say where to turn it on

2026-10-04 18:19:12 -07:00

test_sandbox_toolchains.py

Sandbox page: links open the browser, real CLI logos, tools off by default

2026-09-28 17:16:29 -07:00

test_sandbox_tools.py

Sandbox starts at the first turn; Mac gateway restart; plain preparing line

2026-09-28 18:01:42 -07:00

test_sandbox_windows.py

Sandbox settings v6: allowed-sites tick list, three-row OpenShell setup

2026-09-28 16:45:49 -07:00

test_secrets_file_mode.py

Stored sign-ins: one lock across processes, and a sign-in is renewed once

2026-10-04 11:41:00 -07:00

test_secrets_floor.py

test(permissions): the backslash script path case runs under the PowerShell shell (OPE-236)

2026-10-29 14:08:26 +05:30

test_secrets_lock.py

Stored sign-ins: one lock across processes, and a sign-in is renewed once

2026-10-04 11:41:00 -07:00

test_secrets.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_security_bundles.py

Personas: requires_folder/subagents/scheduling traits replace family and the workspace enum

2026-08-20 21:19:56 -07:00

test_self_protection.py

Step 2: Auto-Approve mode - the reviewer, the hook, and the renames

2026-08-12 12:42:17 -07:00

test_self_wake.py

Test the end-turn hint on sleep_for and sleep_until

2026-10-25 13:56:10 -07:00

test_send_file.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_send_target_resolution.py

Merge pull request #488 from rkfshakti/fix/github-clone-pull-approval-gate

2026-08-23 13:05:52 -07:00

test_sender_attribution.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_served_by.py

Persist the upstream host a router reports on each reply (served_by)

2026-09-09 17:35:09 +05:30

test_server.py

feat(gui): show the changes auto-approve made without asking, at the end of a turn (OPE-238)

2026-10-29 14:08:30 +05:30

test_session_events.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_session_facts.py

Step 1: known world frozen at session start; ingestion facts to audit only

2026-08-12 12:16:45 -07:00

test_session_persona.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_session_socket_sandbox_build.py

Sandbox starts at the first turn; Mac gateway restart; plain preparing line

2026-09-28 18:01:42 -07:00

test_session_usage.py

Engine and server: worker grants, lead decisions, parked gates, reviewer, usage

2026-09-17 16:18:03 -07:00

test_settings.py

fix(settings): no Remove key for a provider key set by an environment variable (#742)

2026-10-07 17:42:34 +05:30

test_shadow_eval.py

chore(eval): one common schema for every reviewer corpus, owner-ruling re-keys and sealed fresh rows, old run reports out of the repo (OPE-225)

2026-10-29 16:54:24 +05:30

test_sharing_v1.py

personas: sharing v1 — export/import bundles, version + consent (OPE-7)

2026-08-11 12:12:24 -07:00

test_shell_env_isolation.py

Merge main and keep sidecar token out of direct shell

2026-09-26 03:58:04 +00:00

test_shell_non_utf8_output.py

Tolerate non-UTF-8 bytes in shell command output (OPE-204)

2026-10-02 15:11:22 +05:30

test_shell.py

test_shell: capped-wait test uses a silent command, so only the exit can end the wait

2026-10-29 19:55:41 +05:30

test_site_wall.py

A site allowed on the card opens on the running sandbox too

2026-10-03 11:03:37 -07:00

test_skills_api.py

OPE-136: MCP permission model — EXTERNAL floor, durable per-tool trust, run grants, honest approval plumbing

2026-08-31 08:06:14 +05:30

test_skills_sessions.py

Shipping lineup: remove Chat, ship Code disabled, gate unshipped personas

2026-08-20 17:59:48 -07:00

test_skills_store.py

OPE-136: MCP permission model — EXTERNAL floor, durable per-tool trust, run grants, honest approval plumbing

2026-08-31 08:06:14 +05:30

test_skills.py

Never let an unreadable skills dir abort a run

2026-10-01 12:38:03 +05:30

test_slack_approval_owners.py

security: harden Slack approval handling

2026-07-24 22:33:13 -07:00

test_slack_directory.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_slack_relay.py

Merge pull request #252 from Dhevenddra/fix/relay-tests-hermetic-name-lookup

2026-10-25 14:57:59 -07:00

test_slack_status.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_slack_workspaces.py

Connectors on machines: grant handoff, GitHub and Slack on a box, subscriptions

2026-09-06 10:19:23 -07:00

test_standing_approvals.py

Engine and server: worker grants, lead decisions, parked gates, reviewer, usage

2026-09-17 16:18:03 -07:00

test_statelock.py

Remote machines: identity, reverse channel, acceptor, sealed key wallet

2026-09-05 08:00:16 -07:00

test_subagent.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_subscription_sync.py

Connectors on machines: grant handoff, GitHub and Slack on a box, subscriptions

2026-09-06 10:19:23 -07:00

test_subscriptions.py

Connectors on machines: grant handoff, GitHub and Slack on a box, subscriptions

2026-09-06 10:19:23 -07:00

test_task_tool_grants.py

feat(automation): a routine can be trusted with a tool that has no target

2026-09-06 21:11:34 +02:00

test_team_allowlist.py

security: harden Slack approval handling

2026-07-24 22:33:13 -07:00

test_team_board.py

Add incremental board reads and immutable team artifacts

2026-09-20 23:09:47 -07:00

test_team_efficient_reads.py

Add incremental board reads and immutable team artifacts

2026-09-20 23:09:47 -07:00

test_team_file_artifacts.py

Add incremental board reads and immutable team artifacts

2026-09-20 23:09:47 -07:00

test_team_git_handoff.py

Clarify verified revision handoff to publish branch owner

2026-09-21 12:24:13 -07:00

test_team_journal.py

Drop the proposed state: boards hold only accepted work

2026-08-16 08:07:10 -07:00

test_team_live_gaps.py

Reconcile ordinary approval cards by exact tool call identity

2026-09-21 13:11:29 -07:00

test_team_open_surface.py

Add incremental board reads and immutable team artifacts

2026-09-20 23:09:47 -07:00

test_team_quiet_coordination.py

Make team coordination event driven and quiet

2026-09-21 06:02:41 -07:00

test_team_reader_recovery.py

Add incremental board reads and immutable team artifacts

2026-09-20 23:09:47 -07:00

test_team_rehearsal_fixes.py

Fix device provenance and linked worker denial recovery

2026-09-21 12:47:21 -07:00

test_team_store.py

fix(teams): enforce worker item visibility

2026-08-28 14:47:07 -07:00

test_team_view.py

Separate task details from worker conversations

2026-09-19 20:03:11 -07:00

test_team_wake.py

Add incremental board reads and immutable team artifacts

2026-09-20 23:09:47 -07:00

test_telegram_approval_bypass.py

security: enforce approval ownership on every transport, not just Slack

2026-08-26 08:24:30 -07:00

test_telegram_approval_owners.py

fix(connectors): telegram approval owners, bound-chat check and refusal reply (#712)

2026-10-02 14:59:42 +05:30

test_temp_workspace.py

coworker picker: setup chips above composer, folder pick at send (UX-029)

2026-08-10 21:43:02 -07:00

test_todo_tool.py

todo_write: rename the items param to todos

2026-07-21 15:45:26 -07:00

test_token_usage.py

Test expects Fireworks' 1,040,000 window for DeepSeek V4 Pro

2026-10-17 16:54:37 +05:30

test_tool_request.py

request_tool: non-catalog names never raise the install card

2026-08-20 22:14:02 -07:00

test_tool_result_cap.py

Tool results: multi-byte output never overshoots the byte cap

2026-10-01 16:12:42 +02:00

test_toolchain.py

Tool-request card: separate the product's facts from the coworker's ask

2026-08-14 23:50:51 -07:00

test_tools_permissions.py

fix: exclude exec-risk tools from session_allow_tools shortcut

2026-10-12 00:19:09 +05:30

test_triage_lead.py

Triage Lead: interview-first standing watch over incoming channels

2026-08-23 01:24:58 -07:00

test_truncation_continuation.py

Run both turns of the continuation reset test in one event loop (OPE-171)

2026-09-08 18:39:04 +05:30

test_tui.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_turn_summary.py

fix(gui): the turn summary counts changes that worked, and pairs results by call id (OPE-238)

2026-10-29 14:08:30 +05:30

test_ui_refresh_e2e.py

test: fix flaky ui-refresh e2e by quiescing the auto-title call before mute assertions

2026-07-26 12:46:06 -06:00

test_unattended.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

test_url_address_guard.py

Merge branch 'main' of https://github.com/andrewyng/openworker into feature/permission-modes

2026-08-22 08:11:32 +05:30

test_vertex_provider.py

Vertex: countTokens verify, global-location host, honest region help

2026-07-27 12:58:16 -07:00

test_wake_resume.py

Make the time a tool instead of a line in every turn (OPE-192, final fix)

2026-09-17 18:25:47 +05:30

test_web_fetch_via_provider.py

web_fetch can read pages through Exa, Firecrawl or Tavily

2026-10-25 19:06:58 -07:00

test_web_search.py

Web search settings: one key per provider, test-and-save, fetch switch

2026-10-25 19:06:58 -07:00

test_windows_wfp_layout.py

Windows sandbox: two accounts, loopback filters, and remove on the CLI

2026-09-25 10:54:17 -07:00

test_worker_connectors.py

Clarify team approvals and surface every pending request

2026-09-20 15:03:01 -07:00