fix(chat): align WebUI context with messaging sessions

CHANGELOG.md

@@ -9,7 +9,7 @@
 
 ### Changed
 
-- Add browser-surface session context to WebUI agent turns so the agent can distinguish a WebUI chat from messaging-platform transcripts while keeping the metadata ephemeral and out of saved history.
+- Add browser-surface session context to WebUI agent turns so the agent can distinguish a WebUI chat from messaging-platform transcripts while keeping the metadata ephemeral and out of saved history. WebUI progress guidance now explicitly preserves the normal Hermes messaging style instead of encouraging extra browser-only status chatter.
 
 ## [v0.51.90] — 2026-05-18 — Release BN (stage-383 — 10-PR full sweep batch — empty-gateway messaging history fix + previous-messaging-sessions setting + Kanban board switcher layout + UI/UX demo theme controls + Slice 3c queue/goal RFC gate + keyless custom endpoints + custom-provider remote model catalog parity + auto-compression elapsed timer + new-conversation cold-start guard + Kanban drag-drop detail open fix)
 

api/streaming.py

@@ -173,9 +173,10 @@ def _clarify_timeout_seconds(default: int = 120) -> int:
 _CANCEL_MARKER_PATTERNS = ('task cancelled', 'task canceled', 'response interrupted')
 
 
-_WEBUI_VISIBLE_PROGRESS_PROMPT = """
+_WEBUI_PROGRESS_PROMPT = """
-WebUI progress contract:
+WebUI progress guidance:
-- For multi-step work that uses tools, provide brief user-visible progress updates as normal assistant content before continuing with tool calls.
+- Match the normal Hermes messaging style; do not add extra status updates solely because this is a browser session.
+- For long multi-step work that uses tools, you may provide brief user-visible progress updates before continuing with tool calls.
 - Each update should say what you are about to check, what you just confirmed, or why the next tool call is needed.
 - Keep updates concise, factual, and in the user's language. One or two short sentences are enough.
 - Do not reveal hidden reasoning, chain-of-thought, private scratchpads, secrets, raw logs, or long tool output.
@@ -224,7 +225,7 @@ def _webui_ephemeral_system_prompt(
     surface_prompt = _webui_surface_context_prompt(surface_context)
     if surface_prompt:
         parts.append(surface_prompt)
-    parts.append(_WEBUI_VISIBLE_PROGRESS_PROMPT)
+    parts.append(_WEBUI_PROGRESS_PROMPT)
     return "\n\n".join(part for part in parts if part)
 
 

tests/test_sprint42.py

@@ -389,7 +389,8 @@ class TestRuntimeRouteInjection(unittest.TestCase):
         init_kwargs = captured["init_kwargs"]
         self.assertIsNotNone(init_kwargs["interim_assistant_callback"])
         self.assertTrue(callable(init_kwargs["interim_assistant_callback"]))
-        self.assertIn("WebUI progress contract", captured["agent"].ephemeral_system_prompt)
+        self.assertIn("WebUI progress guidance", captured["agent"].ephemeral_system_prompt)
+        self.assertIn("Match the normal Hermes messaging style", captured["agent"].ephemeral_system_prompt)
         self.assertIn("user-visible progress updates", captured["agent"].ephemeral_system_prompt)
 
         interim_events = []