mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(tui): ungate reasoning events so the Thinking panel shows live tokens

Browse source 
The gateway was gating `reasoning.delta` and `reasoning.available`
behind `_reasoning_visible(sid)` (true iff `display.show_reasoning:
true` or `tool_progress_mode: verbose`). With the default config,
neither was true — so reasoning events never reached the TUI,
`turn.reasoning` stayed empty, `reasoningTokens` stayed 0, and the
Thinking expander showed no token label for the whole turn. Tools
still reported tokens because `tool.start` had no such gate.

Then `message.complete` fired with `payload.reasoning` populated, the
TUI saved it into `msg.thinking`, and the finalized row's expander
sprouted "~36 tokens" post-hoc. That's the "tokens appear after the
turn" jank.

Remove the gate on emission. The TUI is responsible for whether to
display reasoning content (detailsMode + collapsed expander already
handle that). Token counting becomes continuous throughout the turn,
matching how tools work.

Also dropped the now-unused `_reasoning_visible` and
`_session_show_reasoning` helpers. `show_reasoning` config key stays
in place — it's still toggled via `/reasoning show|hide` and read
elsewhere for potential future TUI-side gating.
This commit is contained in:
Brooklyn Nicholson 2026-04-16 20:56:47 -05:00
parent 319aabbb80
commit 40f2368875
1 changed files with 2 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tui_gateway/server.py
View file

@ -388,18 +388,10 @@ def _load_enabled_toolsets() -> list[str] | None:
return None
def _session_show_reasoning(sid: str) -> bool:
return bool(_sessions.get(sid, {}).get("show_reasoning", False))
def _session_tool_progress_mode(sid: str) -> str:
return str(_sessions.get(sid, {}).get("tool_progress_mode", "all") or "all")
def _reasoning_visible(sid: str) -> bool:
return _session_show_reasoning(sid) or _session_tool_progress_mode(sid) == "verbose"
def _tool_progress_enabled(sid: str) -> bool:
return _session_tool_progress_mode(sid) != "off"
@ -705,7 +697,7 @@ def _on_tool_progress(
if event_type == "tool.started" and name:
_emit("tool.progress", sid, {"name": name, "preview": preview or ""})
return
if event_type == "reasoning.available" and preview and _reasoning_visible(sid):
if event_type == "reasoning.available" and preview:
_emit("reasoning.available", sid, {"text": str(preview)})
return
if event_type.startswith("subagent."):
@ -739,7 +731,7 @@ def _agent_cbs(sid: str) -> dict:
),
tool_gen_callback=lambda name: _tool_progress_enabled(sid) and _emit("tool.generating", sid, {"name": name}),
thinking_callback=lambda text: _emit("thinking.delta", sid, {"text": text}),
reasoning_callback=lambda text: _reasoning_visible(sid) and _emit("reasoning.delta", sid, {"text": text}),
reasoning_callback=lambda text: _emit("reasoning.delta", sid, {"text": text}),
status_callback=lambda kind, text=None: _status_update(sid, str(kind), None if text is None else str(text)),
clarify_callback=lambda q, c: _block("clarify.request", sid, {"question": q, "choices": c}),
)