Shenrui Ma 4521e04add fix(evals): align Kanban probe with managed MCP overrides ...

Use hermes-tools for the probe's managed server configuration and tool-call target so it exercises the endpoint receiving worker overrides. Leave intentional user-defined hermes-mcp fixtures unchanged.

Scope-risk: narrow
Tested: Three complete isolated probe runs on macOS with Codex CLI 0.137.0; related regression selection 202 passed, 2 existing skips; Ruff and repository static checks
Not-tested: Full repository suite, native Linux/Windows, hosted CI, cloud-model turns

2026-09-15 19:05:29 -07:00

..

botmode-dm-delivery

fix(cron): keep deferred delivery exceptions from aborting ticks

2026-09-14 17:29:32 -07:00

botmode-dm-matrix

test(bot-mode): keep the reproducible mock patch whitespace-clean

2026-09-14 17:04:56 -07:00

browser_use

refactor: move live-model benchmark harnesses from scripts/ into evals/

2026-09-13 06:06:46 -07:00

codebase_navigability

…

codex_echo

…

compaction

…

core_tool_deferral

manage_connections covers local MCP servers; setup_mcp leaves the schema (NS-867, PR1) (#109517)

2026-09-15 00:41:13 +05:30

dashboard_auth

fix(dashboard-auth): one refresh single-flight for the cookie gate and the native route, off the event loop

2026-09-13 09:40:44 -07:00

delegation_group_schema

…

desktop_bug_campaign

…

desktop_mcp_oauth

…

desktop-pane-fixture

…

gateway

…

gateway_completion

…

gateway_failure_ownership

…

gateway_status_render

…

liveness

…

memory

…

native_compaction

…

openrouter_pkce_ab

test(auth): OpenRouter PKCE invariants, fake-authority A/B harness, docs, contributor map

2026-09-12 22:07:41 -07:00

postmortem

…

prompt_footprint

…

provider_fallback

…

provider_wire

…

providers

…

readtool

…

session_search_schema

fix(session_search): a bare session id never reads another profile's state.db

2026-09-11 06:24:11 -07:00

subagent_process_handoff

…

token_accounting

…

tool_search

refactor: move live-model benchmark harnesses from scripts/ into evals/

2026-09-13 06:06:46 -07:00

toolperf_abeval

refactor: move live-model benchmark harnesses from scripts/ into evals/

2026-09-13 06:06:46 -07:00

update_streaming

…

webhook_auth

…

__init__.py

…

acp_empty_session_wire.py

…

anthropic_proxy_thinking_replay.py

…

api_delegation_http_probe.py

test: verify API Runs continuation consumers over loopback HTTP

2026-09-09 10:55:32 -07:00

api_delegation_sync_probe.py

fix: persist API delegation units once without waking the model

2026-09-09 10:55:32 -07:00

approval_deny_dispatch.py

…

auth_pool_controls.py

…

auxiliary_resource_exhausted.py

…

cli_deferred_notice.py

…

cli_fallback_add_picker_error.py

…

codex_masked_replay_review.py

…

completion_backlog_probe.py

…

cron_error_diagnostics.py

…

cron_timeout_fork_race.py

…

delivery_flood_wire.py

…

desktop-reap-clock-pressure.cjs

…

fanout_resource_bench.py

…

gemini_type_array_probe.py

…

goal_command_parity.py

…

heartbeat_idle_wire.py

…

kanban_graph_identity.py

…

kanban_pr_acceptance_live.py

…

kanban_scope_probe.py

fix(evals): align Kanban probe with managed MCP overrides

2026-09-15 19:05:29 -07:00

key_cmd_picker_live.py

…

mcp_device_flow.py

test: device login through a later issuer-bound authorization server

2026-09-15 19:00:42 -07:00

output_caps_local_capture.py

…

output_caps_scope.md

…

output_caps_surfaces.py

…

process_result_receipt_probe.py

…

session_snapshot_removal.py

…

slack_stream_wire_contract.py

…

update_check_ssh_pty.py

…

update_obligation_identity.py

…

update_unit_client_budget.py

…

vault_fill_live_e2e.py

fix(vault): dogfood fixes — offer save-login on every backend, keep the model off passwords, bind to the login tab

2026-09-10 10:35:07 -07:00