hermes-bsd/tools
Teknium de9238d37e
feat(kanban): hallucination gate + recovery UX for worker-created-card claims (#20232)
Workers completing a kanban task can now claim the ids of cards they
created via an optional ``created_cards`` field on ``kanban_complete``.
The kernel verifies each id exists and was created by the completing
worker's profile; any phantom id blocks the completion with a
``HallucinatedCardsError`` and records a
``completion_blocked_hallucination`` event on the task so the rejected
attempt is auditable. Successful completions also get a non-blocking
prose-scan pass over their ``summary`` + ``result`` that emits a
``suspected_hallucinated_references`` event for any ``t_<hex>``
reference that doesn't resolve.

Closes #20017.

Recovery UX (kernel + CLI + dashboard)
--------------------------------------

A structural gate alone isn't enough — operators also need to see and
act on stuck workers, especially when a profile's model is the root
cause. This PR ships the full loop:

* ``kanban_db.reclaim_task(task_id)`` — operator-driven reclaim that
  releases an active worker claim immediately (unlike
  ``release_stale_claims`` which only acts after claim_expires has
  passed). Emits a ``reclaimed`` event with ``manual: True`` payload.
* ``kanban_db.reassign_task(task_id, profile, reclaim_first=...)`` —
  switch a task to a different profile, optionally reclaiming a stuck
  running worker in the same call.
* ``hermes kanban reclaim <id> [--reason ...]`` and
  ``hermes kanban reassign <id> <profile> [--reclaim] [--reason ...]``
  CLI subcommands wired through to the same helpers.
* ``POST /api/plugins/kanban/tasks/{id}/reclaim`` and
  ``POST /api/plugins/kanban/tasks/{id}/reassign`` endpoints on the
  dashboard plugin.

Dashboard surfacing
-------------------

* ⚠ **warning badge** on cards with active hallucination events.
* **attention strip** at the top of the board listing all flagged
  tasks; dismissible per session.
* **events callout** in the task drawer — hallucination events render
  with a red left border, amber icon, and phantom ids as styled chips.
* **recovery section** in the task drawer with three actions: Reclaim,
  Reassign (with profile picker + reclaim-first checkbox), and a
  copy-to-clipboard hint for ``hermes -p <profile> model`` since
  profile config lives on disk and can't be edited from the browser.
  Auto-opens when the task has warnings, collapsed otherwise.
  Keyed by task id so state doesn't leak between drawers.

Active-vs-stale rule: warnings clear when a clean ``completed`` or
``edited`` event supersedes the hallucination, so recovery is never
permanently stigmatising — the audit events persist for debugging but
the badge goes away once the worker succeeds.

Skill updates
-------------

* ``skills/devops/kanban-worker/SKILL.md`` documents the
  ``created_cards`` contract with good/bad examples.
* ``skills/devops/kanban-orchestrator/SKILL.md`` gains a "Recovering
  stuck workers" section with the three actions and when to use each.

Tests
-----

* Kernel gate: verified-cards manifest, phantom rejection + audit
  event, cross-worker rejection, prose scan positive + negative.
* Recovery helpers: reclaim on running task, reclaim on non-running
  returns False, reassign refuses running without reclaim_first,
  reassign with reclaim_first succeeds on running.
* API endpoints: warnings field present on /board and /tasks/:id,
  warnings cleared after clean completion, reclaim 200 + 409 paths,
  reassign 200 + 409 + reclaim_first paths.
* CLI smoke: reclaim + reassign subcommands.

Live-verified end-to-end on a dashboard with seeded scenarios:
attention strip renders, badges land on the right cards, drawer
callout shows phantom chips, Reclaim on a running task flips status to
ready + emits manual reclaimed event + refreshes the drawer,
Reassign swaps the assignee and triggers board refresh.

359/359 kanban-suite tests pass
(test_kanban_{db,cli,boards,core_functionality} + dashboard + tools).
2026-05-05 08:06:55 -07:00
..
browser_providers
environments fix(local): test root as ancestor candidate; use real pipe for fake stdout 2026-05-04 15:31:47 -07:00
neutts_samples
__init__.py
ansi_strip.py
approval.py feat(i18n): add display.language for static message translation (zh/ja/de/es) (#20231) 2026-05-05 08:03:07 -07:00
binary_extensions.py
browser_camofox.py refactor(config): add cfg_get() helper; migrate 20 nested-get call sites (#17304) 2026-04-28 23:17:39 -07:00
browser_camofox_state.py
browser_cdp_tool.py chore: remove unused imports and dead locals (ruff F401, F841) (#17010) 2026-04-28 06:46:45 -07:00
browser_dialog_tool.py
browser_supervisor.py fix(browser_supervisor): verify thread and loop health before returning cached supervisor 2026-04-30 20:33:33 -07:00
browser_tool.py fix(browser): inject --no-sandbox for root and AppArmor userns restrictions 2026-05-04 05:27:23 -07:00
budget_config.py
checkpoint_manager.py
clarify_tool.py
code_execution_tool.py fix(tools): serialize concurrent hermes_tools RPC calls from execute_code 2026-04-30 03:31:16 -07:00
credential_files.py refactor(config): add cfg_get() helper; migrate 20 nested-get call sites (#17304) 2026-04-28 23:17:39 -07:00
cronjob_tools.py feat(cron): add no_agent mode for script-only cron jobs (watchdog pattern) (#19709) 2026-05-04 12:31:01 -07:00
debug_helpers.py
delegate_tool.py fix(delegation): honor provider override for subagents 2026-05-04 05:22:35 -07:00
discord_tool.py fix(discord_tool): key capability cache by token instead of single global 2026-04-30 20:37:12 -07:00
env_passthrough.py refactor(config): add cfg_get() helper; migrate 20 nested-get call sites (#17304) 2026-04-28 23:17:39 -07:00
feishu_doc_tool.py
feishu_drive_tool.py
file_operations.py feat(file_tools): post-write delta lint on write_file + patch, add JSON/YAML/TOML/Python in-process linters (#20191) 2026-05-05 04:54:17 -07:00
file_state.py
file_tools.py feat(file_tools): post-write delta lint on write_file + patch, add JSON/YAML/TOML/Python in-process linters (#20191) 2026-05-05 04:54:17 -07:00
fuzzy_match.py
homeassistant_tool.py
image_generation_tool.py
interrupt.py
kanban_tools.py feat(kanban): hallucination gate + recovery UX for worker-created-card claims (#20232) 2026-05-05 08:06:55 -07:00
managed_tool_gateway.py
mcp_oauth.py fix(mcp): decouple AnyUrl import from mcp dependency 2026-05-04 04:42:18 -07:00
mcp_oauth_manager.py
mcp_tool.py fix(mcp): add periodic keepalive to _wait_for_lifecycle_event 2026-05-05 05:47:33 -07:00
memory_tool.py refactor: consolidate symlink-safe atomic replace into shared helper 2026-04-28 04:58:22 -07:00
mixture_of_agents_tool.py
neutts_synth.py
openrouter_client.py
osv_check.py
patch_parser.py
path_security.py
process_registry.py fix(terminal): guard background process spawn against deleted cwd (#19933) 2026-05-04 15:35:34 -07:00
registry.py perf(tools): memoize get_tool_definitions + TTL-cache check_fn results (#17098) 2026-04-28 18:20:17 -07:00
rl_training_tool.py
schema_sanitizer.py fix(tool-schemas): reactive strip of pattern/format on llama.cpp grammar 400s 2026-05-05 04:25:18 -07:00
send_message_tool.py fix(email): add required Date header to send_message_tool._send_email 2026-05-04 02:48:20 -07:00
session_search_tool.py fix(session-search): report source from resolved parent, not FTS5 child session (#15909) 2026-05-04 05:07:40 -07:00
skill_manager_tool.py fix(skills): pin protects against deletion only, not edits (#20220) 2026-05-05 05:43:10 -07:00
skill_provenance.py fix(curator): only mark agent-created for background-review sediment (#19621) 2026-05-04 02:42:16 -07:00
skill_usage.py fix(curator): protect hub skills by frontmatter name 2026-05-05 04:55:22 -07:00
skills_guard.py
skills_hub.py skills-hub: hash binary skill bundle files correctly 2026-05-04 01:28:12 -07:00
skills_sync.py refactor: consolidate symlink-safe atomic replace into shared helper 2026-04-28 04:58:22 -07:00
skills_tool.py fix(skills): also bump_use on skill_view tool invocation 2026-04-30 05:07:34 -07:00
slash_confirm.py feat(gateway,cli): confirm /reload-mcp to warn about prompt cache invalidation 2026-04-29 21:56:47 -07:00
terminal_tool.py fix(terminal): skip sudo prompt when local NOPASSWD sudo works 2026-04-30 20:38:09 -07:00
tirith_security.py
todo_tool.py
tool_backend_helpers.py
tool_output_limits.py
tool_result_storage.py
transcription_tools.py fix(ci): stabilize main test suite regressions (#17660) 2026-04-29 23:18:55 -07:00
tts_tool.py fix(tts): update MiniMax API endpoint to v1/text_to_speech 2026-05-04 12:36:09 -07:00
url_safety.py
vision_tools.py fix(vision): guard user_prompt type in video_analyze_tool before debug_call_data construction 2026-05-03 15:28:04 -07:00
voice_mode.py
web_tools.py perf(tools): memoize get_tool_definitions + TTL-cache check_fn results (#17098) 2026-04-28 18:20:17 -07:00
website_policy.py
xai_http.py
yuanbao_tools.py chore: remove unused imports and dead locals (ruff F401, F841) (#17010) 2026-04-28 06:46:45 -07:00