mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-25 05:52:34 +00:00
docs(hermes_tools_mcp_server): align scope docstring with EXPOSED_TOOLS (#26603)
The top-of-file scope docstring listed delegate_task, memory, and session_search as exposed tools, but EXPOSED_TOOLS deliberately omits them (they're _AGENT_LOOP_TOOLS and require the running AIAgent context to dispatch — the inline comment block already explains this). Kanban tools, which ARE exposed, were missing from the docstring entirely. Rewrite the Scope / DO NOT expose sections to match the actual tuple: drop delegate_task/memory/session_search from 'expose', add the kanban_* family, move delegate_task/memory/session_search/todo into 'DO NOT expose' with the agent-loop rationale. Fixes #26567 (doc-only fix; option 2 — shimming memory/session_search through MemoryStore/SessionDB directly — left for a follow-up issue once the plugin-memory locking story is audited).
This commit is contained in:
parent
518f39557b
commit
032fb84222
1 changed files with 14 additions and 6 deletions
|
|
@ -14,20 +14,28 @@ the user gets full Hermes capability inside a Codex turn.
|
||||||
Scope (what we expose):
|
Scope (what we expose):
|
||||||
- web_search, web_extract — Firecrawl, no codex equivalent
|
- web_search, web_extract — Firecrawl, no codex equivalent
|
||||||
- browser_navigate / _click / _type / — Camofox/Browserbase automation
|
- browser_navigate / _click / _type / — Camofox/Browserbase automation
|
||||||
_snapshot / _screenshot / _scroll / _back / _press / _vision
|
_snapshot / _scroll / _back / _press /
|
||||||
- delegate_task — Hermes subagents
|
_get_images / _console / _vision
|
||||||
- vision_analyze — image inspection by vision model
|
- vision_analyze — image inspection by vision model
|
||||||
- image_generate — image generation
|
- image_generate — image generation
|
||||||
- memory — Hermes' persistent memory store
|
|
||||||
- skill_view, skills_list — Hermes' skill library
|
- skill_view, skills_list — Hermes' skill library
|
||||||
- session_search — cross-session search
|
|
||||||
- text_to_speech — TTS
|
- text_to_speech — TTS
|
||||||
|
- kanban_* (complete/block/comment/ — kanban worker + orchestrator
|
||||||
|
heartbeat/show/list/create/ handoff (stateless: read env var,
|
||||||
|
unblock/link) write ~/.hermes/kanban.db)
|
||||||
|
|
||||||
What we DO NOT expose (codex has equivalents):
|
What we DO NOT expose:
|
||||||
- terminal / shell — codex's own shell tool
|
- terminal / shell — codex's own shell tool
|
||||||
- read_file / write_file / patch — codex's apply_patch + shell
|
- read_file / write_file / patch — codex's apply_patch + shell
|
||||||
- search_files / process — codex's shell
|
- search_files / process — codex's shell
|
||||||
- clarify, todo — codex's own UX
|
- clarify — codex's own UX
|
||||||
|
- delegate_task / memory / — `_AGENT_LOOP_TOOLS` in Hermes
|
||||||
|
session_search / todo (model_tools.py). They require
|
||||||
|
the running AIAgent context to
|
||||||
|
dispatch (mid-loop state), so a
|
||||||
|
stateless MCP callback can't
|
||||||
|
drive them. See the inline
|
||||||
|
comment on EXPOSED_TOOLS below.
|
||||||
|
|
||||||
Run with: python -m agent.transports.hermes_tools_mcp_server
|
Run with: python -m agent.transports.hermes_tools_mcp_server
|
||||||
Spawned by: CodexAppServerSession.ensure_started() when the runtime is
|
Spawned by: CodexAppServerSession.ensure_started() when the runtime is
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue