fix(delegation): stream subagent progress per-tool so live windows update mid-run

Subagent tool activity relayed two kinds of events: subagent.tool fired
live per tool call, but the subagent.progress running summary was buffered
5-deep (_BATCH_SIZE=5) and only flushed once 5 tools accumulated, with any
remainder flushed at end-of-run via _flush().

Most subagents run fewer than 5 tools (e.g. a short research or single-edit
task), so the progress summary never reached the threshold mid-run and only
appeared when the child finished — the live subagent window stayed silent
until the very end ("subagent output just appears all at once").

Lower _BATCH_SIZE to 1 so each tool's progress summary streams in step with
the per-tool subagent.tool events. _flush() stays as a harmless end-of-run
safety net (now a no-op in the common case).

Converts the three batch-of-5 change-detector tests into invariant tests
that assert live per-tool streaming and per-child summary isolation.

.github/workflows/contributor-check.yml

@@ -1,11 +1,12 @@
 name: Contributor Attribution Check
 
 on:
+  pull_request:
+    branches: [main]
   # No paths filter — the job must always run so the required check
   # reports a status (path-gated workflows leave checks "pending" forever
   # when no matching files change, which blocks merge).
-  pull_request:
-    branches: [main]
+
 permissions:
   contents: read
 

.github/workflows/docker-lint.yml

@@ -18,12 +18,13 @@ on:
       - docker/**
       - .hadolint.yaml
       - .github/workflows/docker-lint.yml
-
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
   pull_request:
     branches: [main]
+    paths:
+      - Dockerfile
+      - docker/**
+      - .hadolint.yaml
+      - .github/workflows/docker-lint.yml
 
 permissions:
   contents: read

.github/workflows/docker-publish.yml

@@ -11,13 +11,16 @@ on:
       - 'docker/**'
       - '.github/workflows/docker-publish.yml'
       - '.github/actions/hermes-smoke-test/**'
-
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
   pull_request:
     branches: [main]
-
+    paths:
+      - '**/*.py'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - 'Dockerfile'
+      - 'docker/**'
+      - '.github/workflows/docker-publish.yml'
+      - '.github/actions/hermes-smoke-test/**'
   release:
     types: [published]
 

.github/workflows/docs-site-checks.yml

@@ -1,12 +1,10 @@
 name: Docs Site Checks
 
 on:
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
   pull_request:
-    branches: [main]
-
+    paths:
+      - 'website/**'
+      - '.github/workflows/docs-site-checks.yml'
   workflow_dispatch:
 
 permissions:
@@ -16,9 +14,9 @@ jobs:
   docs-site-checks:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
         with:
           node-version: 22
           cache: npm
@@ -28,9 +26,9 @@ jobs:
         run: npm ci
         working-directory: website
 
-      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
         with:
-          python-version: "3.11"
+          python-version: '3.11'
 
       - name: Install ascii-guard
         run: python -m pip install ascii-guard==2.3.0 pyyaml==6.0.3

.github/workflows/history-check.yml

@@ -14,9 +14,6 @@ name: History Check
 # the PR head and main to be non-empty.
 
 on:
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
   pull_request:
     branches: [main]
 
@@ -27,9 +24,9 @@ jobs:
   check-common-ancestor:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
-          fetch-depth: 0 # full history both sides for merge-base
+          fetch-depth: 0  # full history both sides for merge-base
 
       - name: Reject PRs with no common ancestor on main
         run: |

.github/workflows/lint.yml

@@ -15,12 +15,12 @@ on:
       - "**/*.md"
       - "docs/**"
       - "website/**"
-
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
   pull_request:
     branches: [main]
+    paths-ignore:
+      - "**/*.md"
+      - "docs/**"
+      - "website/**"
 
 permissions:
   contents: read
@@ -154,6 +154,7 @@ jobs:
               });
             }
 
+
   ruff-blocking:
     # Enforce the rules in pyproject.toml [tool.ruff.lint.select]. Currently
     # PLW1514 (unspecified-encoding) — catches bare ``open()`` /

.github/workflows/osv-scanner.yml

@@ -20,23 +20,29 @@ name: OSV-Scanner
 # vulnerabilities in pinned deps that we may need to patch deliberately.
 
 on:
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
   pull_request:
     branches: [main]
+    paths:
+      - 'uv.lock'
+      - 'pyproject.toml'
+      - 'package.json'
+      - 'package-lock.json'
+      - 'ui-tui/package.json'
+      - 'website/package.json'
+      - 'website/package-lock.json'
+      - '.github/workflows/osv-scanner.yml'
   push:
     branches: [main]
     paths:
-      - "uv.lock"
-      - "pyproject.toml"
-      - "package.json"
-      - "package-lock.json"
-      - "website/package-lock.json"
+      - 'uv.lock'
+      - 'pyproject.toml'
+      - 'package.json'
+      - 'package-lock.json'
+      - 'website/package-lock.json'
   schedule:
     # Weekly scan against main — catches CVEs published after merge for
     # deps that haven't changed since.
-    - cron: "0 9 * * 1"
+    - cron: '0 9 * * 1'
   workflow_dispatch:
 
 permissions:
@@ -48,7 +54,7 @@ permissions:
 jobs:
   scan:
     name: Scan lockfiles
-    uses: google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@9a498708959aeaef5ef730655706c5a1df1edbc2 # v2.3.8
+    uses: google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@9a498708959aeaef5ef730655706c5a1df1edbc2  # v2.3.8
     with:
       # Scan explicit lockfiles rather than recursing, so we only look at
       # the three sources of truth and skip vendored / test / worktree dirs.

.github/workflows/supply-chain-audit.yml

@@ -1,11 +1,11 @@
 name: Supply Chain Audit
 
 on:
+  pull_request:
+    types: [opened, synchronize, reopened]
   # No paths filter — the jobs must always run so required checks
   # report a status (path-gated workflows leave checks "pending" forever
   # when no matching files change, which blocks merge).
-  pull_request:
-    types: [opened, synchronize, reopened]
 
 permissions:
   pull-requests: write
@@ -32,7 +32,7 @@ jobs:
       # True when the curated MCP catalog / bundled MCP manifests changed.
       mcp_catalog: ${{ steps.filter.outputs.mcp_catalog }}
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           fetch-depth: 0
       - name: Check for relevant file changes
@@ -72,7 +72,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           fetch-depth: 0
 
@@ -207,7 +207,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           fetch-depth: 0
 
@@ -286,7 +286,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           fetch-depth: 0
 

.github/workflows/tests.yml

@@ -6,11 +6,11 @@ on:
     paths-ignore:
       - "**/*.md"
       - "docs/**"
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
   pull_request:
     branches: [main]
+    paths-ignore:
+      - "**/*.md"
+      - "docs/**"
 
 permissions:
   contents: read
@@ -219,4 +219,4 @@ jobs:
         env:
           OPENROUTER_API_KEY: ""
           OPENAI_API_KEY: ""
-          NOUS_API_KEY: ""
+          NOUS_API_KEY: ""

.github/workflows/typecheck.yml

@@ -4,9 +4,6 @@ name: Typecheck
 on:
   push:
     branches: [main]
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
   pull_request:
     branches: [main]
 

.github/workflows/uv-lockfile-check.yml

@@ -47,15 +47,15 @@ on:
   push:
     branches: [main]
     paths:
-      - "pyproject.toml"
-      - "uv.lock"
-      - ".github/workflows/uv-lockfile-check.yml"
-
-  # No paths filter — the job must always run so the required check
-  # reports a status (path-gated workflows leave checks "pending" forever
-  # when no matching files change, which blocks merge).
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - '.github/workflows/uv-lockfile-check.yml'
   pull_request:
     branches: [main]
+    paths:
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - '.github/workflows/uv-lockfile-check.yml'
 
 permissions:
   contents: read
@@ -71,10 +71,10 @@ jobs:
     timeout-minutes: 5
     steps:
       - name: Checkout code
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Install uv
-        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86 # v5
+        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
 
       # `uv lock --check` re-resolves the project from pyproject.toml and
       # compares the result to uv.lock, exiting non-zero if they disagree.

agent/agent_init.py

@@ -27,7 +27,7 @@ import threading
 import time
 import uuid
 from datetime import datetime
-from typing import Any, Callable, Dict, List, Optional
+from typing import Any, Dict, List, Optional
 from urllib.parse import urlparse, parse_qs, urlunparse
 
 from agent.context_compressor import ContextCompressor
@@ -195,7 +195,6 @@ def init_agent(
     status_callback: callable = None,
     notice_callback: callable = None,
     notice_clear_callback: callable = None,
-    event_callback: Optional[Callable[[str, dict], None]] = None,
     max_tokens: int = None,
     reasoning_config: Dict[str, Any] = None,
     service_tier: str = None,
@@ -300,7 +299,6 @@ def init_agent(
     # would mangle the escape sequences.  None = use builtins.print.
     agent._print_fn = None
     agent.background_review_callback = None  # Optional sync callback for gateway delivery
-    agent.memory_notifications = "on"  # Memory update notifications: "off", "on", "verbose"
     agent.skip_context_files = skip_context_files
     agent.load_soul_identity = load_soul_identity
     agent.pass_session_id = pass_session_id
@@ -427,7 +425,6 @@ def init_agent(
     agent.status_callback = status_callback
     agent.notice_callback = notice_callback
     agent.notice_clear_callback = notice_clear_callback
-    agent.event_callback = event_callback
     agent.tool_gen_callback = tool_gen_callback
 
     
@@ -599,7 +596,6 @@ def init_agent(
     # (e.g. CLI voice mode adds a temporary prefix for the live call only).
     agent._persist_user_message_idx = None
     agent._persist_user_message_override = None
-    agent._persist_user_message_timestamp = None
 
     # Cache anthropic image-to-text fallbacks per image payload/URL so a
     # single tool loop does not repeatedly re-run auxiliary vision on the

agent/auxiliary_client.py

@@ -3079,20 +3079,23 @@ def _try_configured_fallback_chain(
         if not fb_provider or fb_provider.lower() == skip:
             continue
         fb_model = str(entry.get("model", "")).strip() or None
+        fb_base_url = str(entry.get("base_url", "")).strip() or None
+        fb_api_key = str(entry.get("api_key", "")).strip() or None
 
         label = f"fallback_chain[{i}]({fb_provider})"
 
         try:
-            fb_client, resolved_model = _resolve_fallback_entry(entry)
+            fb_client = _resolve_single_provider(
+                fb_provider, fb_model, fb_base_url, fb_api_key)
         except Exception:
-            fb_client, resolved_model = None, None
+            fb_client = None
 
         if fb_client is not None:
             logger.info(
                 "Auxiliary %s: %s on %s — configured fallback to %s (%s)",
-                task, reason, failed_provider, label, resolved_model or fb_model or "default",
+                task, reason, failed_provider, label, fb_model or "default",
             )
-            return fb_client, resolved_model or fb_model, label
+            return fb_client, fb_model, label
         tried.append(label)
 
     if tried:
@@ -3103,103 +3106,6 @@ def _try_configured_fallback_chain(
     return None, None, ""
 
 
-def _fallback_entry_api_key(entry: Dict[str, Any]) -> Optional[str]:
-    """Resolve inline or env-backed API key from a fallback-chain entry."""
-    explicit = str(entry.get("api_key") or "").strip()
-    if explicit:
-        return explicit
-    key_env = str(entry.get("key_env") or entry.get("api_key_env") or "").strip()
-    if key_env:
-        return os.getenv(key_env, "").strip() or None
-    return None
-
-
-def _resolve_fallback_entry(entry: Dict[str, Any]) -> Tuple[Optional[Any], Optional[str]]:
-    """Resolve one fallback entry through the central provider router."""
-    provider = str(entry.get("provider") or "").strip()
-    model = str(entry.get("model") or "").strip() or None
-    if not provider or not model:
-        return None, None
-    base_url = str(entry.get("base_url") or "").strip() or None
-    api_key = _fallback_entry_api_key(entry)
-    api_mode = str(entry.get("api_mode") or entry.get("transport") or "").strip() or None
-    return resolve_provider_client(
-        provider,
-        model=model,
-        explicit_base_url=base_url,
-        explicit_api_key=api_key,
-        api_mode=api_mode,
-    )
-
-
-def _try_main_fallback_chain(
-    task: Optional[str],
-    failed_provider: str = "",
-    reason: str = "error",
-) -> Tuple[Optional[Any], Optional[str], str]:
-    """Try the top-level main-agent fallback chain for an auxiliary call.
-
-    ``provider: auto`` auxiliary tasks should respect the user's declared
-    main fallback policy before dropping into Hermes' built-in discovery
-    chain. The top-level chain is read through ``get_fallback_chain`` so
-    both modern ``fallback_providers`` and legacy ``fallback_model`` entries
-    participate in the same order as the main agent.
-    """
-    try:
-        from hermes_cli.config import load_config
-        from hermes_cli.fallback_config import get_fallback_chain
-
-        chain = get_fallback_chain(load_config())
-    except Exception as exc:
-        logger.debug("Auxiliary %s: could not load main fallback chain: %s", task or "call", exc)
-        return None, None, ""
-
-    if not chain:
-        return None, None, ""
-
-    failed_norm = (failed_provider or "").strip().lower()
-    main_norm = (_read_main_provider() or "").strip().lower()
-    skip = {p for p in (failed_norm, main_norm, "auto") if p}
-    tried: List[str] = []
-
-    for i, entry in enumerate(chain):
-        if not isinstance(entry, dict):
-            continue
-        fb_provider = str(entry.get("provider") or "").strip()
-        fb_model = str(entry.get("model") or "").strip()
-        if not fb_provider or not fb_model:
-            continue
-        fb_norm = fb_provider.lower()
-        label = f"fallback_providers[{i}]({fb_provider})"
-        if fb_norm in skip:
-            tried.append(f"{label} (skipped)")
-            continue
-        if _is_provider_unhealthy(fb_norm):
-            _log_skip_unhealthy(fb_norm, task)
-            tried.append(f"{label} (unhealthy)")
-            continue
-        try:
-            fb_client, resolved_model = _resolve_fallback_entry(entry)
-        except Exception as exc:
-            logger.debug("Auxiliary %s: main fallback %s failed to resolve: %s", task or "call", label, exc)
-            fb_client, resolved_model = None, None
-        if fb_client is not None:
-            logger.info(
-                "Auxiliary %s: %s on %s — main fallback chain to %s (%s)",
-                task or "call", reason, failed_provider or "auto", label,
-                resolved_model or fb_model,
-            )
-            return fb_client, resolved_model or fb_model, fb_provider
-        tried.append(label)
-
-    if tried:
-        logger.debug(
-            "Auxiliary %s: main fallback chain exhausted (tried: %s)",
-            task or "call", ", ".join(tried),
-        )
-    return None, None, ""
-
-
 def _resolve_single_provider(
     provider: str,
     model: Optional[str] = None,
@@ -3210,19 +3116,16 @@ def _resolve_single_provider(
 
     Uses the existing provider resolution infrastructure where possible.
     """
-    # Reuse resolve_provider_client which handles provider→client mapping.
+    # Reuse resolve_provider_client which handles provider→client mapping
     client, resolved_model = resolve_provider_client(
         provider=provider,
         model=model,
-        explicit_base_url=base_url,
-        explicit_api_key=api_key,
+        base_url=base_url,
+        api_key=api_key,
     )
     return client
 
-def _resolve_auto(
-    main_runtime: Optional[Dict[str, Any]] = None,
-    task: Optional[str] = None,
-) -> Tuple[Optional[OpenAI], Optional[str]]:
+def _resolve_auto(main_runtime: Optional[Dict[str, Any]] = None) -> Tuple[Optional[OpenAI], Optional[str]]:
     """Full auto-detection chain.
 
     Priority:
@@ -3320,22 +3223,7 @@ def _resolve_auto(
                             main_provider, resolved or main_model)
                 return client, resolved or main_model
 
-    # ── Step 2: user-configured fallback policy ─────────────────────────
-    # In auto mode, respect the task-specific fallback chain first, then the
-    # main agent's top-level fallback_providers/fallback_model chain. The
-    # hardcoded provider discovery chain below is only the convenience default
-    # for users who have not declared a fallback policy.
-    if task:
-        fb_client, fb_model, _fb_label = _try_configured_fallback_chain(
-            task, main_provider or "auto", reason="main provider unavailable")
-        if fb_client is not None:
-            return fb_client, fb_model
-    fb_client, fb_model, _fb_label = _try_main_fallback_chain(
-        task, main_provider or "auto", reason="main provider unavailable")
-    if fb_client is not None:
-        return fb_client, fb_model
-
-    # ── Step 3: aggregator / fallback chain ──────────────────────────────
+    # ── Step 2: aggregator / fallback chain ──────────────────────────────
     tried = []
     for label, try_fn in _get_provider_chain():
         if _is_provider_unhealthy(label):
@@ -3456,7 +3344,6 @@ def resolve_provider_client(
     api_mode: str = None,
     main_runtime: Optional[Dict[str, Any]] = None,
     is_vision: bool = False,
-    task: Optional[str] = None,
 ) -> Tuple[Optional[Any], Optional[str]]:
     """Central router: given a provider name and optional model, return a
     configured client with the correct auth, base URL, and API format.
@@ -3577,7 +3464,7 @@ def resolve_provider_client(
 
     # ── Auto: try all providers in priority order ────────────────────
     if provider == "auto":
-        client, resolved = _resolve_auto(main_runtime=main_runtime, task=task)
+        client, resolved = _resolve_auto(main_runtime=main_runtime)
         if client is None:
             return None, None
         # When auto-detection lands on a non-OpenRouter provider (e.g. a
@@ -4470,16 +4357,11 @@ def _client_cache_key(
     api_mode: Optional[str] = None,
     main_runtime: Optional[Dict[str, Any]] = None,
     is_vision: bool = False,
-    task: Optional[str] = None,
 ) -> tuple:
     runtime = _normalize_main_runtime(main_runtime)
     runtime_key = tuple(runtime.get(field, "") for field in _MAIN_RUNTIME_FIELDS) if provider == "auto" else ()
-    # `auto` can now resolve through task-specific or main fallback policy,
-    # so the task participates in the cache key. Non-auto providers keep the
-    # old cache shape because the explicit provider/model tuple is sufficient.
-    task_key = (task or "") if provider == "auto" else ""
     pool_hint = _pool_cache_hint(provider, main_runtime=main_runtime)
-    return (provider, async_mode, base_url or "", api_key or "", api_mode or "", runtime_key, is_vision, task_key, pool_hint)
+    return (provider, async_mode, base_url or "", api_key or "", api_mode or "", runtime_key, is_vision, pool_hint)
 
 
 def _store_cached_client(cache_key: tuple, client: Any, default_model: Optional[str], *, bound_loop: Any = None) -> None:
@@ -4672,7 +4554,6 @@ def _get_cached_client(
     api_mode: str = None,
     main_runtime: Optional[Dict[str, Any]] = None,
     is_vision: bool = False,
-    task: Optional[str] = None,
 ) -> Tuple[Optional[Any], Optional[str]]:
     """Get or create a cached client for the given provider.
 
@@ -4710,7 +4591,6 @@ def _get_cached_client(
         api_mode=api_mode,
         main_runtime=main_runtime,
         is_vision=is_vision,
-        task=task,
     )
     with _client_cache_lock:
         if cache_key in _client_cache:
@@ -4755,7 +4635,6 @@ def _get_cached_client(
         api_mode=api_mode,
         main_runtime=runtime,
         is_vision=is_vision,
-        task=task,
     )
     if client is not None:
         # For async clients, remember which loop they were created on so we
@@ -5261,7 +5140,7 @@ def call_llm(
             if not resolved_base_url:
                 logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
                             task or "call", resolved_provider)
-                client, final_model = _get_cached_client("auto", main_runtime=main_runtime, task=task)
+                client, final_model = _get_cached_client("auto", main_runtime=main_runtime)
         if client is None:
             raise RuntimeError(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -5587,19 +5466,14 @@ def call_llm(
 
             # Fallback order (#26882, #26803):
             #   1. User-configured fallback_chain (per-task) if set
-            #   2. For auto: top-level main fallback_providers/fallback_model
-            #   3. For auto: built-in auxiliary discovery chain
-            #   4. For explicit aux providers: main agent model safety net
+            #   2. Main agent model (last-resort safety net)
+            # For auto users (no explicit aux provider), use the full
+            # auto-detection chain instead — its Step 1 IS the main agent
+            # model, so users on `auto` already get main-model fallback.
             fb_client, fb_model, fb_label = (None, None, "")
             if is_auto:
-                fb_client, fb_model, fb_label = _try_configured_fallback_chain(
-                    task, resolved_provider or "auto", reason=reason)
-                if fb_client is None:
-                    fb_client, fb_model, fb_label = _try_main_fallback_chain(
-                        task, resolved_provider or "auto", reason=reason)
-                if fb_client is None:
-                    fb_client, fb_model, fb_label = _try_payment_fallback(
-                        resolved_provider, task, reason=reason)
+                fb_client, fb_model, fb_label = _try_payment_fallback(
+                    resolved_provider, task, reason=reason)
             else:
                 fb_client, fb_model, fb_label = _try_configured_fallback_chain(
                     task, resolved_provider or "auto", reason=reason)
@@ -5762,7 +5636,7 @@ async def async_call_llm(
             if not resolved_base_url:
                 logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
                             task or "call", resolved_provider)
-                client, final_model = _get_cached_client("auto", async_mode=True, main_runtime=main_runtime, task=task)
+                client, final_model = _get_cached_client("auto", async_mode=True)
         if client is None:
             raise RuntimeError(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -6030,19 +5904,13 @@ async def async_call_llm(
 
             # Fallback order (#26882, #26803):
             #   1. User-configured fallback_chain (per-task) if set
-            #   2. For auto: top-level main fallback_providers/fallback_model
-            #   3. For auto: built-in auxiliary discovery chain
-            #   4. For explicit aux providers: main agent model safety net
+            #   2. Main agent model (last-resort safety net)
+            # Auto users get the full auto-detection chain instead — its
+            # Step 1 IS the main agent model.
             fb_client, fb_model, fb_label = (None, None, "")
             if is_auto:
-                fb_client, fb_model, fb_label = _try_configured_fallback_chain(
-                    task, resolved_provider or "auto", reason=reason)
-                if fb_client is None:
-                    fb_client, fb_model, fb_label = _try_main_fallback_chain(
-                        task, resolved_provider or "auto", reason=reason)
-                if fb_client is None:
-                    fb_client, fb_model, fb_label = _try_payment_fallback(
-                        resolved_provider, task, reason=reason)
+                fb_client, fb_model, fb_label = _try_payment_fallback(
+                    resolved_provider, task, reason=reason)
             else:
                 fb_client, fb_model, fb_label = _try_configured_fallback_chain(
                     task, resolved_provider or "auto", reason=reason)

agent/background_review.py

@@ -237,25 +237,18 @@ _COMBINED_REVIEW_PROMPT = (
 def summarize_background_review_actions(
     review_messages: List[Dict],
     prior_snapshot: List[Dict],
-    notification_mode: str = "on",
 ) -> List[str]:
     """Build the human-facing action summary for a background review pass.
 
-    Walks the review agent's session messages and collects successful memory
-    and skill-management actions to surface to the user. Tool messages already
-    present in ``prior_snapshot`` are skipped so stale inherited results are
-    not re-surfaced as fresh background work (issue #14944).
+    Walks the review agent's session messages and collects "successful tool
+    action" descriptions to surface to the user (e.g. "Memory updated").
+    Tool messages already present in ``prior_snapshot`` are skipped so we
+    don't re-surface stale results from the prior conversation that the
+    review agent inherited via ``conversation_history`` (issue #14944).
 
-    ``notification_mode`` controls display detail:
-    - ``off``: return no actions.
-    - ``on``: generic "Memory updated"/tool messages.
-    - ``verbose``: include compact content previews from tool-call arguments.
+    Matching is by ``tool_call_id`` when available, with a content-equality
+    fallback for tool messages that lack one.
     """
-    mode = str(notification_mode or "on").lower()
-    if mode == "off":
-        return []
-    verbose = mode == "verbose"
-
     existing_tool_call_ids = set()
     existing_tool_contents = set()
     for prior in prior_snapshot or []:
@@ -269,42 +262,6 @@ def summarize_background_review_actions(
             if isinstance(content, str):
                 existing_tool_contents.add(content)
 
-    # Map review-agent tool results back to the calls that produced them.  The
-    # result JSON only says "Entry added"; the call arguments contain action,
-    # target, and content previews.  Restricting to notify_tools also prevents
-    # helper tools from surfacing as memory work just because they succeeded.
-    notify_tools = {"memory", "skill_manage"}
-    all_tool_call_ids: set = set()
-    call_details: dict = {}
-    for msg in review_messages or []:
-        if not isinstance(msg, dict) or msg.get("role") != "assistant":
-            continue
-        for tc in msg.get("tool_calls", []) or []:
-            if not isinstance(tc, dict):
-                continue
-            fn = tc.get("function", {}) or {}
-            fn_name = fn.get("name", "")
-            tcid = tc.get("id")
-            if tcid:
-                all_tool_call_ids.add(tcid)
-            if fn_name not in notify_tools:
-                continue
-            try:
-                args = json.loads(fn.get("arguments", "{}"))
-            except (json.JSONDecodeError, TypeError):
-                args = {}
-            if tcid:
-                call_details[tcid] = {
-                    "tool": fn_name,
-                    "action": args.get("action", "?"),
-                    "target": args.get("target", "memory"),
-                    "content": args.get("content", ""),
-                    "old_text": args.get("old_text", ""),
-                    "name": args.get("name", ""),
-                    "old_string": args.get("old_string", ""),
-                    "new_string": args.get("new_string", ""),
-                }
-
     actions: List[str] = []
     for msg in review_messages or []:
         if not isinstance(msg, dict) or msg.get("role") != "tool":
@@ -316,8 +273,6 @@ def summarize_background_review_actions(
             content_str = msg.get("content")
             if isinstance(content_str, str) and content_str in existing_tool_contents:
                 continue
-        if tcid and all_tool_call_ids and tcid not in call_details:
-            continue
         try:
             data = json.loads(msg.get("content", "{}"))
         except (json.JSONDecodeError, TypeError):
@@ -325,75 +280,19 @@ def summarize_background_review_actions(
         if not isinstance(data, dict) or not data.get("success"):
             continue
         message = data.get("message", "")
-        detail = call_details.get(tcid, {})
-        target = data.get("target", "") or detail.get("target", "")
-        is_skill = detail.get("tool") == "skill_manage"
-
-        message_lower = message.lower()
-        if not verbose:
-            if "created" in message_lower:
-                actions.append(message)
-                continue
-            if "updated" in message_lower:
-                actions.append(message)
-                continue
-            if is_skill and "patched" in message_lower:
-                actions.append(message)
-                continue
-
-        if is_skill:
-            label = "Skill"
-        elif target:
+        target = data.get("target", "")
+        if "created" in message.lower():
+            actions.append(message)
+        elif "updated" in message.lower():
+            actions.append(message)
+        elif "added" in message.lower() or (target and "add" in message.lower()):
+            label = "Memory" if target == "memory" else "User profile" if target == "user" else target
+            actions.append(f"{label} updated")
+        elif "Entry added" in message:
+            label = "Memory" if target == "memory" else "User profile" if target == "user" else target
+            actions.append(f"{label} updated")
+        elif "removed" in message.lower() or "replaced" in message.lower():
             label = "Memory" if target == "memory" else "User profile" if target == "user" else target
-        else:
-            continue
-
-        if verbose:
-            action = detail.get("action", "")
-            content = detail.get("content", "")
-            old_text = detail.get("old_text", "")
-            skill_name = detail.get("name", "")
-            max_preview = 120
-            if is_skill:
-                change = data.get("_change", {})
-                old_string = change.get("old", "") or detail.get("old_string", "")
-                new_string = change.get("new", "") or detail.get("new_string", "")
-                description = change.get("description", "")
-                if action == "patch" and (old_string or new_string):
-                    old_preview = old_string[:80].replace("\n", " ") + (
-                        "…" if len(old_string) > 80 else ""
-                    )
-                    new_preview = new_string[:80].replace("\n", " ") + (
-                        "…" if len(new_string) > 80 else ""
-                    )
-                    actions.append(
-                        f"📝 Skill '{skill_name}' patched: "
-                        f"\"{old_preview}\" → \"{new_preview}\""
-                    )
-                elif action == "create" and description:
-                    actions.append(f"📝 Skill '{skill_name}' created: {description}")
-                elif action == "edit" and description:
-                    actions.append(f"📝 Skill '{skill_name}' rewritten: {description}")
-                else:
-                    actions.append(f"📝 {message}" if message else f"Skill {action}")
-            elif action == "add" and content:
-                preview = content[:max_preview] + ("…" if len(content) > max_preview else "")
-                actions.append(f"{label} ➕ {preview}")
-            elif action == "replace" and content:
-                preview = content[:max_preview] + ("…" if len(content) > max_preview else "")
-                actions.append(f"{label} ✏️ {preview}")
-            elif action == "remove" and old_text:
-                preview = old_text[:60] + ("…" if len(old_text) > 60 else "")
-                actions.append(f"{label} ➖ {preview}")
-            else:
-                actions.append(f"{label} updated")
-        elif (
-            "added" in message_lower
-            or "replaced" in message_lower
-            or "removed" in message_lower
-            or (target and "add" in message.lower())
-            or "Entry added" in message
-        ):
             actions.append(f"{label} updated")
     return actions
 
@@ -623,7 +522,6 @@ def _run_review_in_thread(
         actions = summarize_background_review_actions(
             review_messages,
             messages_snapshot,
-            notification_mode=getattr(agent, "memory_notifications", "on"),
         )
 
         if actions:

agent/conversation_compression.py

@@ -603,20 +603,6 @@ def compress_context(
             force=True,
         )
 
-    # Emit session:compress event so hooks (e.g. MemPalace sync) can ingest
-    # the completed old session before its details are lost.
-    _old_sid_for_event = locals().get("old_session_id")
-    if getattr(agent, "event_callback", None):
-        try:
-            agent.event_callback("session:compress", {
-                "platform": agent.platform or "",
-                "session_id": agent.session_id,
-                "old_session_id": _old_sid_for_event or "",
-                "compression_count": agent.context_compressor.compression_count,
-            })
-        except Exception as e:
-            logger.debug("event_callback error on session:compress: %s", e)
-
     # Keep the post-compression rough estimate for diagnostics, but do not
     # treat it as provider-reported prompt usage. Schema-heavy rough estimates
     # can remain above threshold even after the next real API request fits.

agent/conversation_loop.py

@@ -300,20 +300,11 @@ def _restore_or_build_system_prompt(agent, system_message, conversation_history)
                 agent.session_id, exc,
             )
 
-    if stored_prompt and _stored_prompt_matches_runtime(agent, stored_prompt):
+    if stored_prompt:
         # Continuing session — reuse the exact system prompt from the
         # previous turn so the Anthropic cache prefix matches.
         agent._cached_system_prompt = stored_prompt
         return
-    if stored_prompt:
-        stored_state = "stale_runtime"
-        logger.info(
-            "Stored system prompt for session %s has stale runtime identity; "
-            "rebuilding for model=%s provider=%s.",
-            agent.session_id,
-            getattr(agent, "model", "") or "",
-            getattr(agent, "provider", "") or "",
-        )
 
     if conversation_history and stored_state in ("null", "empty"):
         # Continuing session whose stored prompt is unusable.  The
@@ -375,30 +366,6 @@ def _restore_or_build_system_prompt(agent, system_message, conversation_history)
             )
 
 
-def _stored_prompt_matches_runtime(agent, prompt: str) -> bool:
-    """Return False when the persisted Model/Provider lines are stale."""
-
-    def line_value(label: str) -> str:
-        prefix = f"{label}:"
-        value = ""
-        for line in prompt.splitlines():
-            if line.startswith(prefix):
-                value = line[len(prefix):].strip()
-        return value
-
-    stored_model = line_value("Model")
-    current_model = str(getattr(agent, "model", "") or "").strip()
-    if stored_model and current_model and stored_model != current_model:
-        return False
-
-    stored_provider = line_value("Provider")
-    current_provider = str(getattr(agent, "provider", "") or "").strip()
-    if stored_provider and current_provider and stored_provider != current_provider:
-        return False
-
-    return True
-
-
 def _get_continuation_prompt(is_partial_stub: bool, dropped_tools: Optional[List[str]] = None) -> str:
     if is_partial_stub and dropped_tools:
         tool_list = ", ".join(dropped_tools[:3])
@@ -474,7 +441,6 @@ def run_conversation(
     task_id: str = None,
     stream_callback: Optional[callable] = None,
     persist_user_message: Optional[str] = None,
-    persist_user_timestamp: Optional[float] = None,
 ) -> Dict[str, Any]:
     """
     Run a complete conversation with tool calling until completion.
@@ -490,8 +456,6 @@ def run_conversation(
         persist_user_message: Optional clean user message to store in
             transcripts/history when user_message contains API-only
             synthetic prefixes.
-        persist_user_timestamp: Optional platform event timestamp to store
-            as metadata on that persisted user message.
                 or queuing follow-up prefetch work.
 
     Returns:
@@ -513,7 +477,6 @@ def run_conversation(
         task_id,
         stream_callback,
         persist_user_message,
-        persist_user_timestamp,
         restore_or_build_system_prompt=_restore_or_build_system_prompt,
         install_safe_stdio=_install_safe_stdio,
         sanitize_surrogates=_sanitize_surrogates,

agent/memory_manager.py

@@ -33,7 +33,6 @@ from concurrent.futures import ThreadPoolExecutor
 from typing import Any, Dict, List, Optional
 
 from agent.memory_provider import MemoryProvider
-from agent.skill_commands import extract_user_instruction_from_skill_message
 from tools.registry import tool_error
 
 logger = logging.getLogger(__name__)
@@ -431,37 +430,16 @@ class MemoryManager:
 
     # -- Prefetch / recall ---------------------------------------------------
 
-    @staticmethod
-    def _strip_skill_scaffolding(text: str) -> Optional[str]:
-        """Return memory-worthy user text, or None to skip the turn.
-
-        When a user invokes a /skill or /bundle, Hermes expands the turn into
-        a model-facing message that embeds the entire skill body. Feeding that
-        verbatim to memory providers pollutes their stores/embeddings with
-        prompt scaffolding instead of what the user actually asked. We recover
-        just the user's instruction here, once, for every provider — so this
-        is fixed for the whole provider fan-out, not per backend.
-
-        - Non-skill messages pass through unchanged.
-        - Skill turns with a user instruction return that instruction.
-        - Bare skill invocations (no instruction) return None → callers skip
-          the turn, since there is no user content worth remembering.
-        """
-        return extract_user_instruction_from_skill_message(text)
-
     def prefetch_all(self, query: str, *, session_id: str = "") -> str:
         """Collect prefetch context from all providers.
 
         Returns merged context text labeled by provider. Empty providers
         are skipped. Failures in one provider don't block others.
         """
-        clean_query = self._strip_skill_scaffolding(query)
-        if not clean_query:
-            return ""
         parts = []
         for provider in self._providers:
             try:
-                result = provider.prefetch(clean_query, session_id=session_id)
+                result = provider.prefetch(query, session_id=session_id)
                 if result and result.strip():
                     parts.append(result)
             except Exception as e:
@@ -482,14 +460,10 @@ class MemoryManager:
         if not providers:
             return
 
-        clean_query = self._strip_skill_scaffolding(query)
-        if not clean_query:
-            return
-
         def _run() -> None:
             for provider in providers:
                 try:
-                    provider.queue_prefetch(clean_query, session_id=session_id)
+                    provider.queue_prefetch(query, session_id=session_id)
                 except Exception as e:
                     logger.debug(
                         "Memory provider '%s' queue_prefetch failed (non-fatal): %s",
@@ -541,11 +515,6 @@ class MemoryManager:
         if not providers:
             return
 
-        clean_user_content = self._strip_skill_scaffolding(user_content)
-        if not clean_user_content:
-            return
-        user_content = clean_user_content
-
         def _run() -> None:
             for provider in providers:
                 try:

agent/prompt_builder.py

@@ -8,7 +8,6 @@ import json
 import logging
 import os
 import threading
-import contextvars
 from collections import OrderedDict
 from pathlib import Path
 
@@ -959,52 +958,6 @@ CONTEXT_TRUNCATE_HEAD_RATIO = 0.7
 CONTEXT_TRUNCATE_TAIL_RATIO = 0.2
 
 
-def _get_context_file_max_chars() -> int:
-    """Return the configured context-file truncation limit.
-
-    ``CONTEXT_FILE_MAX_CHARS`` remains the upstream-compatible default and
-    fallback. Users with larger context windows can raise
-    ``context_file_max_chars`` in config.yaml without patching Hermes.
-    """
-    try:
-        from hermes_cli.config import load_config
-
-        val = load_config().get("context_file_max_chars")
-        if isinstance(val, (int, float)) and val > 0:
-            return int(val)
-    except Exception as e:
-        logger.debug("Could not read context_file_max_chars from config: %s", e)
-    return CONTEXT_FILE_MAX_CHARS
-
-# Collect truncation warnings so the caller (run_agent) can surface them.
-# A ContextVar (not a module-global list) isolates accumulation per thread /
-# per async task, so concurrent gateway-session prompt builds can't drain or
-# clear each other's pending warnings (cross-session leak). Each build runs in
-# its own context, collects its own warnings, and drains them synchronously.
-_truncation_warnings: "contextvars.ContextVar[Optional[list]]" = contextvars.ContextVar(
-    "context_file_truncation_warnings", default=None
-)
-
-
-def _record_truncation_warning(msg: str) -> None:
-    """Append a truncation warning to the current context's accumulator."""
-    warnings = _truncation_warnings.get()
-    if warnings is None:
-        warnings = []
-        _truncation_warnings.set(warnings)
-    warnings.append(msg)
-
-
-def drain_truncation_warnings() -> list:
-    """Return and clear any truncation warnings accumulated in this context."""
-    warnings = _truncation_warnings.get()
-    if not warnings:
-        return []
-    drained = list(warnings)
-    warnings.clear()
-    return drained
-
-
 # =========================================================================
 # Skills prompt cache
 # =========================================================================
@@ -1510,19 +1463,10 @@ def build_nous_subscription_prompt(valid_tool_names: "set[str] | None" = None) -
 # Context files (SOUL.md, AGENTS.md, .cursorrules)
 # =========================================================================
 
-def _truncate_content(content: str, filename: str, max_chars: Optional[int] = None) -> str:
+def _truncate_content(content: str, filename: str, max_chars: int = CONTEXT_FILE_MAX_CHARS) -> str:
     """Head/tail truncation with a marker in the middle."""
-    if max_chars is None:
-        max_chars = _get_context_file_max_chars()
     if len(content) <= max_chars:
         return content
-    msg = (
-        f"⚠️  Context file {filename} TRUNCATED: "
-        f"{len(content)} chars exceeds limit of {max_chars} — "
-        f"increase context_file_max_chars or trim the file!"
-    )
-    logger.warning(msg)
-    _record_truncation_warning(msg)
     head_chars = int(max_chars * CONTEXT_TRUNCATE_HEAD_RATIO)
     tail_chars = int(max_chars * CONTEXT_TRUNCATE_TAIL_RATIO)
     head = content[:head_chars]

agent/skill_commands.py

@@ -26,91 +26,6 @@ _skill_commands_platform: Optional[str] = None
 _SKILL_INVALID_CHARS = re.compile(r"[^a-z0-9-]")
 _SKILL_MULTI_HYPHEN = re.compile(r"-{2,}")
 
-# ---------------------------------------------------------------------------
-# Skill-scaffolding markers and the canonical extractor.
-#
-# When a user invokes a /skill (or /bundle), Hermes expands the turn into a
-# model-facing message that embeds the full skill body plus scaffolding. That
-# expanded text is what flows into the agent loop — and into memory providers
-# via MemoryManager. Providers that store or embed the raw user turn (mem0,
-# openviking, hindsight, retaindb, byterover, honcho, supermemory) would
-# otherwise capture the entire skill body instead of what the user actually
-# asked. ``extract_user_instruction_from_skill_message`` recovers just the
-# user's instruction so memory stays clean.
-#
-# These markers MUST stay byte-identical to the builders below
-# (``_build_skill_message`` here, ``build_bundle_invocation_message`` in
-# agent/skill_bundles.py). They are co-located with the single-skill builder
-# on purpose, and the bundle markers are asserted against the bundle builder in
-# tests/openviking_plugin/test_openviking.py::test_skill_markers_match_hermes_scaffolding.
-# ---------------------------------------------------------------------------
-_SKILL_INVOCATION_PREFIX = "[IMPORTANT: The user has invoked the "
-_SINGLE_SKILL_MARKER = "The full skill content is loaded below.]"
-_SINGLE_SKILL_INSTRUCTION = (
-    "The user has provided the following instruction alongside the skill invocation: "
-)
-_RUNTIME_NOTE = "\n\n[Runtime note:"
-_BUNDLE_MARKER = " skill bundle,"
-_BUNDLE_USER_INSTRUCTION = "\nUser instruction: "
-_BUNDLE_FIRST_SKILL_BLOCK = "\n\n[Loaded as part of the "
-
-
-def extract_user_instruction_from_skill_message(content: Any) -> Optional[str]:
-    """Recover the user's instruction from a slash-skill-expanded turn.
-
-    Returns:
-        - The original string unchanged when it is NOT skill scaffolding
-          (a normal user message passes straight through).
-        - The extracted user instruction when the scaffolding carried one.
-        - ``None`` when the content is skill scaffolding with no user
-          instruction (i.e. a bare ``/skill`` invocation). Callers that feed
-          memory providers should skip the turn in that case — there is no
-          user content worth storing.
-    """
-    if not isinstance(content, str):
-        return None
-
-    if not content.startswith(_SKILL_INVOCATION_PREFIX):
-        return content
-
-    if _BUNDLE_MARKER in content:
-        return _extract_bundle_user_instruction(content)
-
-    if _SINGLE_SKILL_MARKER in content:
-        return _extract_single_skill_user_instruction(content)
-
-    return None
-
-
-def _extract_single_skill_user_instruction(message: str) -> Optional[str]:
-    # Single-skill format appends the user instruction after the skill body, so
-    # the last occurrence is the user-provided one; the body may quote this text.
-    marker_idx = message.rfind(_SINGLE_SKILL_INSTRUCTION)
-    if marker_idx < 0:
-        return None
-
-    instruction = message[marker_idx + len(_SINGLE_SKILL_INSTRUCTION):]
-    runtime_idx = instruction.find(_RUNTIME_NOTE)
-    if runtime_idx >= 0:
-        instruction = instruction[:runtime_idx]
-    instruction = instruction.strip()
-    return instruction or None
-
-
-def _extract_bundle_user_instruction(message: str) -> Optional[str]:
-    # Bundle format puts the user instruction before the loaded skills, so the
-    # first occurrence is the user-provided one.
-    marker_idx = message.find(_BUNDLE_USER_INSTRUCTION)
-    if marker_idx < 0:
-        return None
-
-    instruction = message[marker_idx + len(_BUNDLE_USER_INSTRUCTION):]
-    first_skill_idx = instruction.find(_BUNDLE_FIRST_SKILL_BLOCK)
-    if first_skill_idx >= 0:
-        instruction = instruction[:first_skill_idx]
-    instruction = instruction.strip()
-    return instruction or None
-
 
 def _resolve_skill_commands_platform() -> Optional[str]:
     """Return the current platform scope used for disabled-skill filtering.

agent/skill_utils.py

@@ -43,20 +43,14 @@ EXCLUDED_SKILL_DIRS = frozenset(
     )
 )
 
-# Supporting files live inside a skill package and are loaded explicitly via
-# skill_view(skill, file_path=...). They are not standalone skills and must not
-# be scanned for active SKILL.md/DESCRIPTION.md entries, even if a Curator or
-# archive workflow preserves a complete old skill package under references/.
-SKILL_SUPPORT_DIRS = frozenset(("references", "templates", "assets", "scripts"))
-
 
 def is_excluded_skill_path(path) -> bool:
-    """True if *path* should be skipped by active skill scanners.
+    """True if any component of *path* is in EXCLUDED_SKILL_DIRS.
 
-    Use this on every ``SKILL.md`` path produced by direct ``rglob`` scans to
-    prune dependency, virtualenv, VCS, cache, and progressive-disclosure
-    support-package paths. Centralising the check here keeps every
-    skill-scanning site in sync with the shared exclusion set.
+    Use this on every SKILL.md path produced by ``rglob`` to prune
+    dependency, virtualenv, VCS, and cache directories. Centralising the
+    check here keeps every skill-scanning site in sync with the shared
+    exclusion set.
 
     Accepts a Path or string.
     """
@@ -65,36 +59,7 @@ def is_excluded_skill_path(path) -> bool:
     except AttributeError:
         from pathlib import PurePath
         parts = PurePath(str(path)).parts
-    return any(part in EXCLUDED_SKILL_DIRS for part in parts) or is_skill_support_path(
-        path
-    )
-
-
-def is_skill_support_path(path) -> bool:
-    """True if *path* is under a support dir of an actual skill root.
-
-    ``references/``, ``templates/``, ``assets/``, and ``scripts/`` are
-    progressive-disclosure support areas when they sit directly inside a skill
-    directory containing ``SKILL.md``. They are not active discovery roots for
-    standalone skills. A preserved package such as
-    ``some-skill/references/old-skill-package/SKILL.md`` is documentation data
-    unless the caller explicitly loads it via ``file_path``.
-
-    Legitimate categories or skill names such as ``skills/scripts/foo`` remain
-    discoverable because their ``scripts`` component is not directly under a
-    directory that contains ``SKILL.md``.
-    """
-    path_obj = path if isinstance(path, Path) else Path(str(path))
-    parts = path_obj.parts
-    # Last component may be a file or candidate skill directory name. Only
-    # components before the leaf can be containing support directories.
-    for idx, part in enumerate(parts[:-1]):
-        if part not in SKILL_SUPPORT_DIRS or idx == 0:
-            continue
-        skill_root = Path(*parts[:idx])
-        if (skill_root / "SKILL.md").exists():
-            return True
-    return False
+    return any(part in EXCLUDED_SKILL_DIRS for part in parts)
 
 
 # ── Lazy YAML loader ─────────────────────────────────────────────────────
@@ -696,21 +661,12 @@ def extract_skill_description(frontmatter: Dict[str, Any]) -> str:
 def iter_skill_index_files(skills_dir: Path, filename: str):
     """Walk skills_dir yielding sorted paths matching *filename*.
 
-    Excludes Hermes metadata, VCS, virtualenv/dependency, cache, and skill
-    support directories. Support directories (references/templates/assets/
-    scripts) can contain arbitrary markdown and even archived package
-    ``SKILL.md`` files, but they are progressive-disclosure data loaded through
-    ``skill_view(..., file_path=...)`` rather than active skill roots.
+    Excludes Hermes metadata, VCS, virtualenv/dependency, and cache
+    directories so dependencies cannot register nested skills.
     """
     matches = []
     for root, dirs, files in os.walk(skills_dir, followlinks=True):
-        has_skill_md = "SKILL.md" in files
-        dirs[:] = [
-            d
-            for d in dirs
-            if d not in EXCLUDED_SKILL_DIRS
-            and not (has_skill_md and d in SKILL_SUPPORT_DIRS)
-        ]
+        dirs[:] = [d for d in dirs if d not in EXCLUDED_SKILL_DIRS]
         if filename in files:
             matches.append(Path(root) / filename)
     for path in sorted(matches, key=lambda p: str(p.relative_to(skills_dir))):

agent/system_prompt.py

@@ -40,7 +40,6 @@ from agent.prompt_builder import (
     TASK_COMPLETION_GUIDANCE,
     TOOL_USE_ENFORCEMENT_GUIDANCE,
     TOOL_USE_ENFORCEMENT_MODELS,
-    drain_truncation_warnings,
 )
 from agent.runtime_cwd import resolve_context_cwd
 
@@ -401,14 +400,7 @@ def build_system_prompt(agent: Any, system_message: Optional[str] = None) -> str
     warm across turns.
     """
     parts = build_system_prompt_parts(agent, system_message=system_message)
-    joined = "\n\n".join(p for p in (parts["stable"], parts["context"], parts["volatile"]) if p)
-
-    # Surface context-file truncation warnings through the normal agent status
-    # channel so gateway/CLI users see them in chat instead of only in logs.
-    for warning in drain_truncation_warnings():
-        agent._emit_status(warning)
-
-    return joined
+    return "\n\n".join(p for p in (parts["stable"], parts["context"], parts["volatile"]) if p)
 
 
 def invalidate_system_prompt(agent: Any) -> None:

agent/turn_context.py

@@ -69,7 +69,6 @@ def build_turn_context(
     task_id: Optional[str],
     stream_callback,
     persist_user_message: Optional[str],
-    persist_user_timestamp: Optional[float] = None,
     *,
     restore_or_build_system_prompt,
     install_safe_stdio,
@@ -122,7 +121,6 @@ def build_turn_context(
     agent._stream_callback = stream_callback
     agent._persist_user_message_idx = None
     agent._persist_user_message_override = persist_user_message
-    agent._persist_user_message_timestamp = persist_user_timestamp
     # Generate unique task_id if not provided to isolate VMs between tasks.
     effective_task_id = task_id or str(uuid.uuid4())
     agent._current_task_id = effective_task_id

apps/desktop/README.md

@@ -34,7 +34,7 @@ It builds and launches the GUI against your existing install — same config, ke
 
 ### Prebuilt installers
 
-Prebuilt installers are built and distributed via [the Hermes Desktop website.](https://hermes-agent.nousresearch.com/).
+Prebuilt installers are built and distributed via [the Hermes Desktop website.](https://hermes-agent.nousresearch.com/desktop).
 
 ---
 

apps/desktop/electron/connection-config.cjs

@@ -166,39 +166,6 @@ function profileRemoteOverride(config, profile) {
   return { url, authMode: normAuthMode(entry.authMode), token: entry.token }
 }
 
-/**
- * In global-remote mode one backend serves every Desktop profile, so REST calls
- * that are scoped by renderer-side `request.profile` must carry that scope as a
- * query parameter. Local pooled backends and per-profile remote overrides do not
- * need this: they already run against a backend scoped to the target profile.
- */
-function pathWithGlobalRemoteProfile(path, profile, opts = {}) {
-  const scopedProfile = connectionScopeKey(profile)
-  if (!scopedProfile || !opts.globalRemote || opts.profileRemoteOverride) {
-    return path
-  }
-
-  const rawPath = String(path || '')
-  if (!rawPath) {
-    return path
-  }
-
-  let parsed
-  try {
-    parsed = new URL(rawPath, 'http://hermes.local')
-  } catch {
-    return path
-  }
-
-  if (parsed.searchParams.has('profile')) {
-    return path
-  }
-
-  parsed.searchParams.set('profile', scopedProfile)
-
-  return `${parsed.pathname}${parsed.search}${parsed.hash}`
-}
-
 function tokenPreview(value) {
   const raw = String(value || '')
 
@@ -280,7 +247,6 @@ module.exports = {
   cookiesHaveLiveSession,
   normAuthMode,
   normalizeRemoteBaseUrl,
-  pathWithGlobalRemoteProfile,
   profileRemoteOverride,
   resolveAuthMode,
   resolveTestWsUrl,

apps/desktop/electron/connection-config.test.cjs

@@ -24,7 +24,6 @@ const {
   cookiesHaveLiveSession,
   normAuthMode,
   normalizeRemoteBaseUrl,
-  pathWithGlobalRemoteProfile,
   profileRemoteOverride,
   resolveAuthMode,
   resolveTestWsUrl,
@@ -91,72 +90,6 @@ test('profileRemoteOverride tolerates a missing/!object profiles map', () => {
   assert.equal(profileRemoteOverride(null, 'coder'), null)
 })
 
-// --- pathWithGlobalRemoteProfile ---
-
-test('pathWithGlobalRemoteProfile appends profile in global remote mode', () => {
-  assert.equal(
-    pathWithGlobalRemoteProfile('/api/model/info', 'iris', {
-      globalRemote: true,
-      profileRemoteOverride: false
-    }),
-    '/api/model/info?profile=iris'
-  )
-})
-
-test('pathWithGlobalRemoteProfile preserves existing query params', () => {
-  assert.equal(
-    pathWithGlobalRemoteProfile('/api/model/options?force=1', 'iris', {
-      globalRemote: true,
-      profileRemoteOverride: false
-    }),
-    '/api/model/options?force=1&profile=iris'
-  )
-})
-
-test('pathWithGlobalRemoteProfile does not replace an explicit profile query', () => {
-  assert.equal(
-    pathWithGlobalRemoteProfile('/api/model/info?profile=default', 'iris', {
-      globalRemote: true,
-      profileRemoteOverride: false
-    }),
-    '/api/model/info?profile=default'
-  )
-})
-
-test('pathWithGlobalRemoteProfile skips local and per-profile remote override paths', () => {
-  assert.equal(
-    pathWithGlobalRemoteProfile('/api/model/info', 'iris', {
-      globalRemote: false,
-      profileRemoteOverride: false
-    }),
-    '/api/model/info'
-  )
-  assert.equal(
-    pathWithGlobalRemoteProfile('/api/model/info', 'iris', {
-      globalRemote: true,
-      profileRemoteOverride: true
-    }),
-    '/api/model/info'
-  )
-})
-
-test('pathWithGlobalRemoteProfile skips empty profile/path safely', () => {
-  assert.equal(
-    pathWithGlobalRemoteProfile('/api/model/info', '', {
-      globalRemote: true,
-      profileRemoteOverride: false
-    }),
-    '/api/model/info'
-  )
-  assert.equal(
-    pathWithGlobalRemoteProfile('', 'iris', {
-      globalRemote: true,
-      profileRemoteOverride: false
-    }),
-    ''
-  )
-})
-
 // --- normalizeRemoteBaseUrl ---
 
 test('normalizeRemoteBaseUrl strips trailing slashes, hash, and query', () => {

apps/desktop/electron/main.cjs

@@ -39,7 +39,6 @@ const { waitForDashboardPort } = require('./backend-ready.cjs')
 const { serializeJsonBody, setJsonRequestHeaders } = require('./oauth-net-request.cjs')
 const { fetchMarketplaceThemes, searchMarketplaceThemes } = require('./vscode-marketplace.cjs')
 const { buildDesktopBackendEnv, normalizeHermesHomeRoot } = require('./backend-env.cjs')
-const { readWindowsUserEnvVar } = require('./windows-user-env.cjs')
 const { readDirForIpc } = require('./fs-read-dir.cjs')
 const { gitRootForIpc } = require('./git-root.cjs')
 const { worktreesForIpc } = require('./git-worktrees.cjs')
@@ -63,7 +62,6 @@ const {
   cookiesHaveLiveSession,
   normAuthMode,
   normalizeRemoteBaseUrl,
-  pathWithGlobalRemoteProfile,
   profileRemoteOverride,
   resolveAuthMode,
   resolveTestWsUrl,
@@ -244,16 +242,6 @@ if (INSTALL_STAMP) {
 function resolveHermesHome() {
   if (process.env.HERMES_HOME) return normalizeHermesHomeRoot(process.env.HERMES_HOME)
   if (USER_DATA_OVERRIDE) return path.join(path.resolve(USER_DATA_OVERRIDE), 'hermes-home')
-  if (IS_WINDOWS) {
-    // A GUI app launched from Explorer inherits the environment block captured
-    // at login, so a HERMES_HOME set via `setx` AFTER login is invisible in
-    // process.env even though the CLI (a fresh shell) sees it. Without this the
-    // backend silently falls back to %LOCALAPPDATA%\hermes and reports "No
-    // inference provider configured" despite a valid configured home (#45471).
-    // Consult the live User-scoped registry value before the default below.
-    const fromRegistry = readWindowsUserEnvVar('HERMES_HOME')
-    if (fromRegistry) return normalizeHermesHomeRoot(fromRegistry)
-  }
   if (IS_WINDOWS && process.env.LOCALAPPDATA) {
     const localappdata = path.join(process.env.LOCALAPPDATA, 'hermes')
     const legacy = path.join(app.getPath('home'), '.hermes')
@@ -5084,75 +5072,65 @@ function focusWindow(win) {
   win.focus()
 }
 
-function spawnSecondaryWindow({ sessionId, watch, newSession } = {}) {
-  const icon = getAppIconPath()
-  const win = new BrowserWindow({
-    width: SESSION_WINDOW_MIN_WIDTH,
-    height: SESSION_WINDOW_MIN_HEIGHT,
-    minWidth: SESSION_WINDOW_MIN_WIDTH,
-    minHeight: SESSION_WINDOW_MIN_HEIGHT,
-    title: 'Hermes',
-    titleBarStyle: 'hidden',
-    titleBarOverlay: getTitleBarOverlayOptions(),
-    trafficLightPosition: IS_MAC ? WINDOW_BUTTON_POSITION : undefined,
-    vibrancy: IS_MAC ? 'sidebar' : undefined,
-    opacity: windowOpacity(),
-    icon,
-    // Don't show until the renderer's first themed paint is ready. macOS
-    // `vibrancy` ignores `backgroundColor` and paints a translucent OS
-    // material (which follows the OS appearance, not the app theme), so a
-    // dark-themed app on a light-mode Mac flashes white until the renderer
-    // covers it. ready-to-show fires after the boot-time paint in
-    // themes/context.tsx, so the window appears already themed.
-    show: false,
-    backgroundColor: getWindowBackgroundColor(),
-    webPreferences: {
-      preload: path.join(__dirname, 'preload.cjs'),
-      contextIsolation: true,
-      webviewTag: true,
-      sandbox: true,
-      nodeIntegration: false,
-      devTools: true
-    }
-  })
-
-  if (IS_MAC) {
-    win.setWindowButtonPosition?.(WINDOW_BUTTON_POSITION)
-  }
-
-  win.once('ready-to-show', () => {
-    if (!win.isDestroyed()) win.show()
-  })
-
-  win.on('will-enter-full-screen', () => sendWindowStateChanged(true))
-  win.on('enter-full-screen', () => sendWindowStateChanged(true))
-  win.on('will-leave-full-screen', () => sendWindowStateChanged(false))
-  win.on('leave-full-screen', () => sendWindowStateChanged(false))
-
-  wireCommonWindowHandlers(win)
-
-  win.loadURL(
-    buildSessionWindowUrl(sessionId, {
-      devServer: DEV_SERVER,
-      rendererIndexPath: DEV_SERVER ? undefined : resolveRendererIndex(),
-      watch,
-      newSession
-    })
-  )
-
-  return win
-}
-
 // Open (or focus) a standalone window for a single chat session.
 function createSessionWindow(sessionId, { watch = false } = {}) {
-  return sessionWindows.openOrFocus(sessionId, () => spawnSecondaryWindow({ sessionId, watch }))
-}
+  return sessionWindows.openOrFocus(sessionId, () => {
+    const icon = getAppIconPath()
+    const win = new BrowserWindow({
+      width: SESSION_WINDOW_MIN_WIDTH,
+      height: SESSION_WINDOW_MIN_HEIGHT,
+      minWidth: SESSION_WINDOW_MIN_WIDTH,
+      minHeight: SESSION_WINDOW_MIN_HEIGHT,
+      title: 'Hermes',
+      titleBarStyle: 'hidden',
+      titleBarOverlay: getTitleBarOverlayOptions(),
+      trafficLightPosition: IS_MAC ? WINDOW_BUTTON_POSITION : undefined,
+      vibrancy: IS_MAC ? 'sidebar' : undefined,
+      opacity: windowOpacity(),
+      icon,
+      // Don't show until the renderer's first themed paint is ready. macOS
+      // `vibrancy` ignores `backgroundColor` and paints a translucent OS
+      // material (which follows the OS appearance, not the app theme), so a
+      // dark-themed app on a light-mode Mac flashes white until the renderer
+      // covers it. ready-to-show fires after the boot-time paint in
+      // themes/context.tsx, so the window appears already themed.
+      show: false,
+      backgroundColor: getWindowBackgroundColor(),
+      webPreferences: {
+        preload: path.join(__dirname, 'preload.cjs'),
+        contextIsolation: true,
+        webviewTag: true,
+        sandbox: true,
+        nodeIntegration: false,
+        devTools: true
+      }
+    })
 
-// Open a fresh compact window on the new-session draft (#/). Not registry-keyed:
-// like ⌘N in a browser, every press opens a new window — and a draft window that
-// later converts to a real session must not get refocused as if it were blank.
-function createNewSessionWindow() {
-  return spawnSecondaryWindow({ newSession: true })
+    if (IS_MAC) {
+      win.setWindowButtonPosition?.(WINDOW_BUTTON_POSITION)
+    }
+
+    win.once('ready-to-show', () => {
+      if (!win.isDestroyed()) win.show()
+    })
+
+    win.on('will-enter-full-screen', () => sendWindowStateChanged(true))
+    win.on('enter-full-screen', () => sendWindowStateChanged(true))
+    win.on('will-leave-full-screen', () => sendWindowStateChanged(false))
+    win.on('leave-full-screen', () => sendWindowStateChanged(false))
+
+    wireCommonWindowHandlers(win)
+
+    win.loadURL(
+      buildSessionWindowUrl(sessionId, {
+        devServer: DEV_SERVER,
+        rendererIndexPath: DEV_SERVER ? undefined : resolveRendererIndex(),
+        watch
+      })
+    )
+
+    return win
+  })
 }
 
 function createWindow() {
@@ -5339,11 +5317,6 @@ ipcMain.handle('hermes:window:openSession', async (_event, sessionId, opts) => {
 
   return { ok: true }
 })
-ipcMain.handle('hermes:window:openNewSession', async () => {
-  createNewSessionWindow()
-
-  return { ok: true }
-})
 ipcMain.handle('hermes:bootstrap:reset', async () => {
   // Renderer's "Reload and retry" path. Clear the latched failure and
   // reset connection state so the next startHermes() call restarts the
@@ -5613,14 +5586,9 @@ ipcMain.handle('hermes:api', async (_event, request) => {
 
   await prepareProfileDeleteRequest(request)
 
-  const profile = request?.profile
-  const connection = await ensureBackend(profile)
+  const connection = await ensureBackend(request?.profile)
   const timeoutMs = resolveTimeoutMs(request?.timeoutMs, DEFAULT_FETCH_TIMEOUT_MS)
-  const requestPath = pathWithGlobalRemoteProfile(request.path, profile, {
-    globalRemote: globalRemoteActive(),
-    profileRemoteOverride: profileHasRemoteOverride(profile)
-  })
-  const url = `${connection.baseUrl}${requestPath}`
+  const url = `${connection.baseUrl}${request.path}`
   // OAuth gateways authenticate REST via the HttpOnly session cookie held in
   // the OAuth partition — route through Electron's net stack bound to that
   // session so the cookie attaches automatically. Token/local modes keep using

apps/desktop/electron/preload.cjs

@@ -6,7 +6,6 @@ contextBridge.exposeInMainWorld('hermesDesktop', {
   touchBackend: profile => ipcRenderer.invoke('hermes:backend:touch', profile),
   getGatewayWsUrl: profile => ipcRenderer.invoke('hermes:gateway:ws-url', profile),
   openSessionWindow: (sessionId, opts) => ipcRenderer.invoke('hermes:window:openSession', sessionId, opts),
-  openNewSessionWindow: () => ipcRenderer.invoke('hermes:window:openNewSession'),
   getBootProgress: () => ipcRenderer.invoke('hermes:boot-progress:get'),
   getConnectionConfig: profile => ipcRenderer.invoke('hermes:connection-config:get', profile),
   saveConnectionConfig: payload => ipcRenderer.invoke('hermes:connection-config:save', payload),

apps/desktop/electron/session-windows.cjs

@@ -15,13 +15,12 @@ const SESSION_WINDOW_MIN_HEIGHT = 620
 // flag MUST sit in the query string BEFORE the '#': anything after the '#' is
 // treated as the route by HashRouter and would break routeSessionId(). The
 // renderer reads the flag from window.location.search to suppress the install /
-// onboarding overlays and the global session sidebar. `new=1` marks the compact
-// scratch window; `watch=1` marks a spectator window (e.g. a running subagent's
-// session): the renderer resumes it lazily so the gateway never builds an agent
-// just to stream into it.
-function buildSessionWindowUrl(sessionId, { devServer, rendererIndexPath, watch, newSession } = {}) {
-  const query = `?win=secondary${newSession ? '&new=1' : ''}${watch ? '&watch=1' : ''}`
-  const route = newSession ? '#/' : `#/${encodeURIComponent(sessionId)}`
+// onboarding overlays and the global session sidebar. `watch=1` marks a
+// spectator window (e.g. a running subagent's session): the renderer resumes
+// it lazily so the gateway never builds an agent just to stream into it.
+function buildSessionWindowUrl(sessionId, { devServer, rendererIndexPath, watch } = {}) {
+  const query = `?win=secondary${watch ? '&watch=1' : ''}`
+  const route = `#/${encodeURIComponent(sessionId)}`
 
   if (devServer) {
     const base = devServer.endsWith('/') ? devServer.slice(0, -1) : devServer

apps/desktop/electron/session-windows.test.cjs

@@ -82,12 +82,6 @@ test('buildSessionWindowUrl adds the watch flag for spectator windows, before th
   assert.equal(url, 'http://localhost:5173/?win=secondary&watch=1#/abc')
 })
 
-test('buildSessionWindowUrl routes new-session windows to the draft (#/)', () => {
-  const url = buildSessionWindowUrl(null, { devServer: 'http://localhost:5173', newSession: true })
-
-  assert.equal(url, 'http://localhost:5173/?win=secondary&new=1#/')
-})
-
 test('registry opens one window per session and focuses on re-open', () => {
   const registry = createSessionWindowRegistry()
   let built = 0

apps/desktop/electron/windows-user-env.cjs

@@ -1,76 +0,0 @@
-// windows-user-env.cjs
-//
-// Read a User-scoped environment variable straight from the Windows registry
-// (HKCU\Environment).
-//
-// A GUI app launched from Explorer inherits the environment block captured at
-// login, so a variable set via `setx` AFTER login is invisible in process.env
-// even though a fresh shell — and the Hermes CLI — sees it immediately. The
-// desktop's HERMES_HOME resolution relies on process.env, so that stale-snapshot
-// gap silently sends the backend to the default %LOCALAPPDATA%\hermes. Reading
-// the live registry value closes the gap. See #45471.
-
-const { execFileSync } = require('node:child_process')
-
-// Parse the output of `reg query HKCU\Environment /v <name>`, which looks like:
-//
-//   HKEY_CURRENT_USER\Environment
-//       HERMES_HOME    REG_SZ    F:\Hermes\data
-//
-// Returns the raw value string (spaces inside the value preserved), or null when
-// the requested value line isn't present.
-function parseRegQueryValue(stdout, name) {
-  if (!stdout || !name) return null
-  const typePattern =
-    /^(\S+)\s+(?:REG_SZ|REG_EXPAND_SZ|REG_MULTI_SZ|REG_DWORD|REG_QWORD|REG_BINARY|REG_NONE)\s+(.*)$/
-  for (const rawLine of String(stdout).split(/\r?\n/)) {
-    const line = rawLine.trim()
-    const match = line.match(typePattern)
-    if (match && match[1].toLowerCase() === name.toLowerCase()) {
-      return match[2]
-    }
-  }
-  return null
-}
-
-// Expand %VAR% references against an env map. REG_EXPAND_SZ values store
-// unexpanded references; plain REG_SZ paths have none, so this is a no-op for
-// the common F:\... case. Unknown references are left verbatim.
-function expandWindowsEnvRefs(value, env = process.env) {
-  if (!value) return value
-  return value.replace(/%([^%]+)%/g, (whole, name) => {
-    const key = Object.keys(env).find(k => k.toUpperCase() === String(name).toUpperCase())
-    return key != null && env[key] != null ? env[key] : whole
-  })
-}
-
-// Read a User-scoped env var from HKCU\Environment. Windows-only: returns null
-// off-Windows (without spawning), on any spawn error, when `reg` exits non-zero
-// (the value doesn't exist), or when the value is empty.
-function readWindowsUserEnvVar(
-  name,
-  { platform = process.platform, env = process.env, exec = execFileSync } = {}
-) {
-  if (platform !== 'win32' || !name) return null
-  let stdout
-  try {
-    stdout = exec('reg', ['query', 'HKCU\\Environment', '/v', name], {
-      encoding: 'utf8',
-      windowsHide: true,
-      timeout: 5000
-    })
-  } catch {
-    // `reg` missing, or value absent (reg exits 1) — caller falls back.
-    return null
-  }
-  const raw = parseRegQueryValue(stdout, name)
-  if (raw == null) return null
-  const expanded = expandWindowsEnvRefs(raw, env).trim()
-  return expanded || null
-}
-
-module.exports = {
-  expandWindowsEnvRefs,
-  parseRegQueryValue,
-  readWindowsUserEnvVar
-}

apps/desktop/electron/windows-user-env.test.cjs

@@ -1,90 +0,0 @@
-const assert = require('node:assert/strict')
-const { test } = require('node:test')
-
-const {
-  expandWindowsEnvRefs,
-  parseRegQueryValue,
-  readWindowsUserEnvVar
-} = require('./windows-user-env.cjs')
-
-// ── parseRegQueryValue ─────────────────────────────────────────────────────
-
-test('parseRegQueryValue extracts a REG_SZ value', () => {
-  const out = [
-    '',
-    'HKEY_CURRENT_USER\\Environment',
-    '    HERMES_HOME    REG_SZ    F:\\Hermes\\data',
-    ''
-  ].join('\r\n')
-  assert.equal(parseRegQueryValue(out, 'HERMES_HOME'), 'F:\\Hermes\\data')
-})
-
-test('parseRegQueryValue matches the name case-insensitively', () => {
-  const out = 'HKEY_CURRENT_USER\\Environment\r\n    Hermes_Home    REG_EXPAND_SZ    %USERPROFILE%\\h\r\n'
-  assert.equal(parseRegQueryValue(out, 'HERMES_HOME'), '%USERPROFILE%\\h')
-})
-
-test('parseRegQueryValue preserves spaces inside the value', () => {
-  const out = '    HERMES_HOME    REG_SZ    C:\\Program Files\\Hermes\r\n'
-  assert.equal(parseRegQueryValue(out, 'HERMES_HOME'), 'C:\\Program Files\\Hermes')
-})
-
-test('parseRegQueryValue returns null when the value line is absent', () => {
-  const out = 'HKEY_CURRENT_USER\\Environment\r\n    Path    REG_SZ    C:\\x\r\n'
-  assert.equal(parseRegQueryValue(out, 'HERMES_HOME'), null)
-  assert.equal(parseRegQueryValue('', 'HERMES_HOME'), null)
-  assert.equal(parseRegQueryValue('garbage', 'HERMES_HOME'), null)
-})
-
-// ── expandWindowsEnvRefs ───────────────────────────────────────────────────
-
-test('expandWindowsEnvRefs expands %VAR% case-insensitively', () => {
-  assert.equal(
-    expandWindowsEnvRefs('%UserProfile%\\h', { USERPROFILE: 'C:\\Users\\jeff' }),
-    'C:\\Users\\jeff\\h'
-  )
-})
-
-test('expandWindowsEnvRefs leaves literal paths and unknown refs intact', () => {
-  assert.equal(expandWindowsEnvRefs('F:\\Hermes\\data', {}), 'F:\\Hermes\\data')
-  assert.equal(expandWindowsEnvRefs('%NOPE%\\x', {}), '%NOPE%\\x')
-})
-
-// ── readWindowsUserEnvVar ──────────────────────────────────────────────────
-
-test('readWindowsUserEnvVar returns null off Windows without spawning', () => {
-  let spawned = false
-  const exec = () => {
-    spawned = true
-    return ''
-  }
-  assert.equal(readWindowsUserEnvVar('HERMES_HOME', { platform: 'linux', exec }), null)
-  assert.equal(spawned, false)
-})
-
-test('readWindowsUserEnvVar queries HKCU\\Environment and expands the value', () => {
-  const calls = []
-  const exec = (cmd, args) => {
-    calls.push([cmd, args])
-    return 'HKEY_CURRENT_USER\\Environment\r\n    HERMES_HOME    REG_EXPAND_SZ    %DRIVE%\\Hermes\r\n'
-  }
-  const value = readWindowsUserEnvVar('HERMES_HOME', {
-    platform: 'win32',
-    env: { DRIVE: 'F:' },
-    exec
-  })
-  assert.equal(value, 'F:\\Hermes')
-  assert.deepEqual(calls, [['reg', ['query', 'HKCU\\Environment', '/v', 'HERMES_HOME']]])
-})
-
-test('readWindowsUserEnvVar returns null when reg exits non-zero (value missing)', () => {
-  const exec = () => {
-    throw new Error('reg exited 1')
-  }
-  assert.equal(readWindowsUserEnvVar('HERMES_HOME', { platform: 'win32', exec }), null)
-})
-
-test('readWindowsUserEnvVar returns null for an empty value', () => {
-  const exec = () => '    HERMES_HOME    REG_SZ    \r\n'
-  assert.equal(readWindowsUserEnvVar('HERMES_HOME', { platform: 'win32', exec }), null)
-})

apps/desktop/package.json

@@ -20,7 +20,6 @@
     "start": "npm run build && electron .",
     "build": "node scripts/assert-root-install.cjs && node scripts/write-build-stamp.cjs && node scripts/stage-native-deps.cjs && tsc -b && vite build && npm run postbuild",
     "postbuild": "node scripts/assert-dist-built.cjs",
-    "prebuilder": "node scripts/patch-electron-builder-mac-binary.cjs",
     "builder": "cross-env NODE_OPTIONS=--max-old-space-size=16384 electron-builder",
     "pack": "npm run build && npm run builder -- --dir",
     "dist": "npm run build && npm run builder",
@@ -37,7 +36,7 @@
     "test:desktop:nsis": "node scripts/test-desktop.mjs nsis",
     "test:desktop:existing": "node scripts/test-desktop.mjs existing",
     "test:desktop:fresh": "node scripts/test-desktop.mjs fresh",
-    "test:desktop:platforms": "node --test electron/bootstrap-platform.test.cjs electron/hardening.test.cjs electron/backend-env.test.cjs electron/backend-probes.test.cjs electron/bootstrap-runner.test.cjs electron/connection-config.test.cjs electron/dashboard-token.test.cjs electron/gateway-ws-probe.test.cjs electron/oauth-net-request.test.cjs electron/desktop-uninstall.test.cjs electron/session-windows.test.cjs electron/workspace-cwd.test.cjs electron/fs-read-dir.test.cjs electron/git-root.test.cjs electron/windows-child-process.test.cjs electron/update-remote.test.cjs electron/windows-user-env.test.cjs",
+    "test:desktop:platforms": "node --test electron/bootstrap-platform.test.cjs electron/hardening.test.cjs electron/backend-env.test.cjs electron/backend-probes.test.cjs electron/bootstrap-runner.test.cjs electron/connection-config.test.cjs electron/dashboard-token.test.cjs electron/gateway-ws-probe.test.cjs electron/oauth-net-request.test.cjs electron/desktop-uninstall.test.cjs electron/session-windows.test.cjs electron/workspace-cwd.test.cjs electron/fs-read-dir.test.cjs electron/git-root.test.cjs electron/windows-child-process.test.cjs electron/update-remote.test.cjs",
     "typecheck": "tsc -p . --noEmit",
     "lint": "eslint src/ electron/",
     "lint:fix": "eslint src/ electron/ --fix",
@@ -135,7 +134,6 @@
   },
   "build": {
     "electronVersion": "40.9.3",
-    "electronDist": "../../node_modules/electron/dist",
     "appId": "com.nousresearch.hermes",
     "productName": "Hermes",
     "executableName": "Hermes",

apps/desktop/scripts/patch-electron-builder-mac-binary.cjs

@@ -1,59 +0,0 @@
-const fs = require('node:fs')
-const path = require('node:path')
-
-if (process.platform !== 'darwin') {
-  process.exit(0)
-}
-
-const desktopRoot = path.resolve(__dirname, '..')
-const repoRoot = path.resolve(desktopRoot, '..', '..')
-const electronMacPath = path.join(repoRoot, 'node_modules', 'app-builder-lib', 'out', 'electron', 'electronMac.js')
-
-const marker = 'hermes-macos-electron-binary-fallback'
-const needle = `    await Promise.all([
-        doRename(path.join(contentsPath, "MacOS"), electronBranding.productName, appPlist.CFBundleExecutable),
-        (0, builder_util_1.unlinkIfExists)(path.join(appOutDir, "LICENSE")),
-        (0, builder_util_1.unlinkIfExists)(path.join(appOutDir, "LICENSES.chromium.html")),
-    ]);`
-const replacement = `    // ${marker}: electron-builder 26.8.x can sometimes copy
-    // Electron.app without its main MacOS/Electron binary before this rename.
-    // Restore it from the installed Electron runtime so local desktop installs
-    // do not fail with ENOENT during macOS arm64 packaging.
-    const macosDir = path.join(contentsPath, "MacOS");
-    const bundledElectronBinary = path.join(macosDir, electronBranding.productName);
-    if (!fs.existsSync(bundledElectronBinary)) {
-        const candidates = [
-            path.join(packager.info.framework.distMacOsAppName, "Contents", "MacOS", electronBranding.productName),
-            path.join(process.cwd(), "..", "..", "node_modules", "electron", "dist", "Electron.app", "Contents", "MacOS", electronBranding.productName),
-        ];
-        const sourceBinary = candidates.find(candidate => fs.existsSync(candidate));
-        if (sourceBinary == null) {
-            throw new Error("Electron binary missing from packaged app and Electron runtime: " + bundledElectronBinary);
-        }
-        await (0, promises_1.copyFile)(sourceBinary, bundledElectronBinary);
-        await (0, promises_1.chmod)(bundledElectronBinary, 0o755);
-    }
-    await Promise.all([
-        doRename(macosDir, electronBranding.productName, appPlist.CFBundleExecutable),
-        (0, builder_util_1.unlinkIfExists)(path.join(appOutDir, "LICENSE")),
-        (0, builder_util_1.unlinkIfExists)(path.join(appOutDir, "LICENSES.chromium.html")),
-    ]);`
-
-if (!fs.existsSync(electronMacPath)) {
-  console.warn(`[patch-electron-builder] skipped: ${electronMacPath} not found`)
-  process.exit(0)
-}
-
-const source = fs.readFileSync(electronMacPath, 'utf8')
-if (source.includes(marker)) {
-  console.log('[patch-electron-builder] macOS Electron binary fallback already applied')
-  process.exit(0)
-}
-
-if (!source.includes(needle)) {
-  console.warn('[patch-electron-builder] skipped: expected electronMac.js shape not found')
-  process.exit(0)
-}
-
-fs.writeFileSync(electronMacPath, source.replace(needle, replacement))
-console.log('[patch-electron-builder] applied macOS Electron binary fallback')

apps/desktop/src/app/artifacts/index.tsx

@@ -23,7 +23,6 @@ import { type Translations, useI18n } from '@/i18n'
 import { sessionTitle } from '@/lib/chat-runtime'
 import { ExternalLink, ExternalLinkIcon, hostPathLabel, urlSlugTitleLabel, useLinkTitle } from '@/lib/external-link'
 import { FileImage, FileText, FolderOpen, Link2 } from '@/lib/icons'
-import { mediaExternalUrl } from '@/lib/media'
 import { cn } from '@/lib/utils'
 import { notifyError } from '@/store/notifications'
 import type { SessionInfo, SessionMessage } from '@/types/hermes'
@@ -125,12 +124,17 @@ function artifactKind(value: string): ArtifactKind {
 }
 
 function artifactHref(value: string): string {
-  if (value.startsWith('http://') || value.startsWith('https://') || value.startsWith('data:')) {
+  if (
+    value.startsWith('http://') ||
+    value.startsWith('https://') ||
+    value.startsWith('file://') ||
+    value.startsWith('data:')
+  ) {
     return value
   }
 
-  if (value.startsWith('file://') || value.startsWith('/')) {
-    return mediaExternalUrl(value)
+  if (value.startsWith('/')) {
+    return `file://${encodeURI(value)}`
   }
 
   return value

apps/desktop/src/app/chat/composer/controls.tsx

@@ -9,7 +9,6 @@ import { formatCombo } from '@/lib/keybinds/combo'
 import { cn } from '@/lib/utils'
 
 import type { ConversationStatus } from './hooks/use-voice-conversation'
-import { ModelPill } from './model-pill'
 import type { ChatBarState, VoiceStatus } from './types'
 
 export const ICON_BTN = 'size-(--composer-control-size) shrink-0 rounded-md'
@@ -67,7 +66,6 @@ export function ComposerControls({
   const c = t.composer
   const steerCombo = formatCombo('mod+enter')
   const steerLabel = `${c.steer} (${steerCombo})`
-
   const steerTip = (
     <span className="inline-flex items-center gap-1.5">
       {c.steer}
@@ -83,10 +81,8 @@ export function ComposerControls({
 
   return (
     <div className="ml-auto flex shrink-0 items-center gap-(--composer-control-gap)">
-      <ModelPill disabled={disabled} model={state.model} />
-      {/* While the agent runs and the user is typing, steer takes over the mic's
-          slot rather than crowding the row with an extra button. */}
-      {canSteer ? (
+      <DictationButton disabled={disabled} onToggle={onDictate} state={state.voice} status={voiceStatus} />
+      {canSteer && (
         <Tip label={steerTip}>
           <Button
             aria-label={steerLabel}
@@ -100,8 +96,6 @@ export function ComposerControls({
             <SteeringWheel size={16} />
           </Button>
         </Tip>
-      ) : (
-        <DictationButton disabled={disabled} onToggle={onDictate} state={state.voice} status={voiceStatus} />
       )}
       {showVoicePrimary ? (
         <Tip label={c.startVoice}>

apps/desktop/src/app/chat/composer/model-pill.tsx

@@ -1,86 +0,0 @@
-import { useStore } from '@nanostores/react'
-import { useState } from 'react'
-
-import { ModelMenuCloseContext } from '@/app/shell/model-menu-panel'
-import { Button } from '@/components/ui/button'
-import { DropdownMenu, DropdownMenuContent, DropdownMenuTrigger } from '@/components/ui/dropdown-menu'
-import { GlyphSpinner } from '@/components/ui/glyph-spinner'
-import { useI18n } from '@/i18n'
-import { ChevronDown } from '@/lib/icons'
-import { formatModelStatusLabel } from '@/lib/model-status-label'
-import { cn } from '@/lib/utils'
-import {
-  $currentFastMode,
-  $currentModel,
-  $currentProvider,
-  $currentReasoningEffort,
-  setModelPickerOpen
-} from '@/store/session'
-
-import type { ChatBarState } from './types'
-
-const PILL = cn(
-  'h-(--composer-control-size) max-w-40 shrink-0 gap-1 rounded-md px-2 text-xs font-normal',
-  'text-(--ui-text-tertiary) hover:bg-(--chrome-action-hover) hover:text-foreground'
-)
-
-/**
- * Composer model selector — the relocated status-bar pill. Reuses the live
- * `model.options` dropdown (`modelMenuContent`) verbatim; falls back to the
- * full picker when the gateway is closed and no live menu exists.
- */
-export function ModelPill({ disabled, model }: { disabled: boolean; model: ChatBarState['model'] }) {
-  const copy = useI18n().t.shell.statusbar
-  const currentModel = useStore($currentModel)
-  const currentProvider = useStore($currentProvider)
-  const fastMode = useStore($currentFastMode)
-  const reasoningEffort = useStore($currentReasoningEffort)
-  const [open, setOpen] = useState(false)
-
-  // The model resolves a beat after the gateway/session comes up. Rather than
-  // flash a literal "No model", show a quiet loader (inherits the pill text
-  // color at half opacity) until a model lands.
-  const label = (
-    <>
-      {currentModel.trim() ? (
-        <span className="truncate">{formatModelStatusLabel(currentModel, { fastMode, reasoningEffort })}</span>
-      ) : (
-        <GlyphSpinner className="opacity-50" spinner="braille" />
-      )}
-      <ChevronDown className="size-2.5 shrink-0 opacity-50" />
-    </>
-  )
-
-  const title = currentProvider ? copy.modelTitle(currentProvider, currentModel || copy.modelNone) : copy.switchModel
-
-  if (!model.modelMenuContent) {
-    return (
-      <Button
-        aria-label={copy.openModelPicker}
-        className={PILL}
-        disabled={disabled}
-        onClick={() => setModelPickerOpen(true)}
-        title={copy.openModelPicker}
-        type="button"
-        variant="ghost"
-      >
-        {label}
-      </Button>
-    )
-  }
-
-  return (
-    <DropdownMenu onOpenChange={setOpen} open={open}>
-      <DropdownMenuTrigger asChild>
-        <Button aria-label={title} className={PILL} disabled={disabled} title={title} type="button" variant="ghost">
-          {label}
-        </Button>
-      </DropdownMenuTrigger>
-      <DropdownMenuContent align="end" className="w-64 p-0" side="top" sideOffset={8}>
-        <ModelMenuCloseContext.Provider value={() => setOpen(false)}>
-          {model.modelMenuContent}
-        </ModelMenuCloseContext.Provider>
-      </DropdownMenuContent>
-    </DropdownMenu>
-  )
-}

apps/desktop/src/app/chat/composer/types.ts

@@ -1,5 +1,3 @@
-import type { ReactNode } from 'react'
-
 import type { HermesGateway } from '@/hermes'
 import type { ComposerAttachment } from '@/store/composer'
 
@@ -24,8 +22,6 @@ export interface ChatBarState {
     canSwitch: boolean
     loading?: boolean
     quickModels?: QuickModelOption[]
-    /** Reused status-bar dropdown (built with gateway + selectModel upstream). */
-    modelMenuContent?: ReactNode
   }
   tools: { enabled: boolean; label: string; suggestions?: ContextSuggestion[] }
   voice: { enabled: boolean; active: boolean }

apps/desktop/src/app/chat/index.tsx

@@ -42,7 +42,6 @@ import {
   $sessions,
   sessionPinId
 } from '@/store/session'
-import { isSecondaryWindow } from '@/store/windows'
 import type { ModelOptionsResponse } from '@/types/hermes'
 
 import { routeSessionId } from '../routes'
@@ -62,7 +61,6 @@ import { threadLoadingState } from './thread-loading'
 
 interface ChatViewProps extends Omit<React.ComponentProps<'div'>, 'onSubmit'> {
   gateway: HermesGateway | null
-  modelMenuContent?: React.ReactNode
   onToggleSelectedPin: () => void
   onDeleteSelectedSession: () => void
   onCancel: () => Promise<void> | void
@@ -121,10 +119,10 @@ function ChatHeader({
       ? pinnedSessionIds.includes(selectedSessionId)
       : false
 
-  // Secondary windows (new-session scratch, subagent watch, cmd-click pop-out)
-  // are compact side panels — they drop the session-actions header + border
-  // entirely. A brand-new draft has nothing to pin/delete/rename either.
-  if (isSecondaryWindow() || (!selectedSessionId && !activeSessionId && !isRoutedSessionView)) {
+  // A brand-new session has no session to pin/delete/rename, so the header is
+  // just a dead "New session" label + chevron. Drop it (and its border)
+  // entirely until there's a real session to act on.
+  if (!selectedSessionId && !activeSessionId && !isRoutedSessionView) {
     return null
   }
 
@@ -251,7 +249,6 @@ function ChatRuntimeBoundary({
 export function ChatView({
   className,
   gateway,
-  modelMenuContent,
   onToggleSelectedPin,
   onDeleteSelectedSession,
   onCancel,
@@ -305,10 +302,7 @@ export function ChatView({
   // waiting for the resume effect (which paints a frame later) to clear them.
   const routeSessionMismatch = isRoutedSessionView && routedSessionId !== selectedSessionId
 
-  // The compact new-session pop-out skips the wordmark/tagline intro — it's a
-  // scratch window, not the full-height empty state.
-  const showIntro =
-    !isSecondaryWindow() && freshDraftReady && !isRoutedSessionView && !selectedSessionId && !activeSessionId && messagesEmpty
+  const showIntro = freshDraftReady && !isRoutedSessionView && !selectedSessionId && !activeSessionId && messagesEmpty
 
   // Session is still loading if the route references a session we haven't
   // resumed yet. Once `activeSessionId` is set (runtime has resumed), the
@@ -348,7 +342,6 @@ export function ChatView({
         provider: currentProvider,
         canSwitch: gatewayOpen,
         loading: !gatewayOpen || (!currentModel && !currentProvider),
-        modelMenuContent,
         quickModels
       },
       tools: {
@@ -361,7 +354,7 @@ export function ChatView({
         active: false
       }
     }),
-    [contextSuggestions, currentModel, currentProvider, gatewayOpen, modelMenuContent, quickModels]
+    [contextSuggestions, currentModel, currentProvider, gatewayOpen, quickModels]
   )
 
   // Drop files anywhere in the conversation area, not just on the composer

apps/desktop/src/app/desktop-controller.tsx

@@ -77,7 +77,6 @@ import {
   setSessionsLoading,
   setSessionsTotal
 } from '../store/session'
-import { onSessionsChanged } from '../store/session-sync'
 import { clearSessionTodos, setSessionTodos, todoListActive } from '../store/todos'
 import { openUpdatesWindow, startUpdatePoller, stopUpdatePoller } from '../store/updates'
 import { isSecondaryWindow } from '../store/windows'
@@ -465,17 +464,6 @@ export function DesktopController() {
     void refreshSessions()
   }, [refreshSessions])
 
-  // Another window mutated the shared session list (e.g. a chat started in the
-  // pop-out). Re-pull so the sidebar reflects it. Pop-outs have no sidebar, so
-  // only real windows bother.
-  useEffect(() => {
-    if (isSecondaryWindow()) {
-      return
-    }
-
-    return onSessionsChanged(() => void refreshSessions().catch(() => undefined))
-  }, [refreshSessions])
-
   // ALL-profiles view pages one profile at a time: fetch that profile's next
   // page and merge it in place, leaving every other profile's rows untouched.
   const loadMoreSessionsForProfile = useCallback(async (profile: string) => {
@@ -711,9 +699,7 @@ export function DesktopController() {
     }
 
     lastGatewayProfileRef.current = activeGatewayProfile
-    // Force: the new profile has its own default, so reseed even if the composer
-    // already shows the previous profile's model.
-    void refreshCurrentModel(true)
+    void refreshCurrentModel()
     void refreshActiveProfile()
   }, [activeGatewayProfile, refreshCurrentModel])
 
@@ -861,6 +847,7 @@ export function DesktopController() {
     gatewayLogLines,
     gatewayState,
     inferenceStatus,
+    modelMenuContent,
     openAgents,
     freshDraftReady,
     openCommandCenterSection,
@@ -982,7 +969,6 @@ export function DesktopController() {
     <ChatView
       gateway={gatewayRef.current}
       maxVoiceRecordingSeconds={voiceMaxRecordingSeconds}
-      modelMenuContent={modelMenuContent}
       onAddContextRef={composer.addContextRefAttachment}
       onAddUrl={url => composer.addContextRefAttachment(`@url:${formatRefValue(url)}`, url)}
       onAttachDroppedItems={composer.attachDroppedItems}

apps/desktop/src/app/hooks/use-keybinds.ts

@@ -37,7 +37,6 @@ import {
   switcherActive,
   switcherJustClosed
 } from '@/store/session-switcher'
-import { openNewSessionInNewWindow } from '@/store/windows'
 import { useTheme } from '@/themes/context'
 
 import { requestComposerFocus } from '../chat/composer/focus'
@@ -133,7 +132,6 @@ export function useKeybinds(deps: KeybindRuntimeDeps): void {
       deps.startFreshSession()
       window.dispatchEvent(new CustomEvent('hermes:new-session-shortcut'))
     },
-    'session.newWindow': () => void openNewSessionInNewWindow(),
     'session.next': () => stepSession(1),
     'session.prev': () => stepSession(-1),
     ...sessionSlotHandlers,

apps/desktop/src/app/right-sidebar/index.test.tsx

@@ -1,75 +0,0 @@
-import { cleanup, fireEvent, render, screen, waitFor } from '@testing-library/react'
-import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
-
-import type { HermesReadDirResult } from '@/global'
-import { $connection, setCurrentCwd } from '@/store/session'
-
-import { resetProjectTreeState } from './files/use-project-tree'
-
-import { RightSidebarPane } from './index'
-
-const readDir = vi.fn<(path: string) => Promise<HermesReadDirResult>>()
-const selectPaths = vi.fn()
-
-function ok(entries: { name: string; path: string; isDirectory: boolean }[]): HermesReadDirResult {
-  return { entries }
-}
-
-function installBridge() {
-  ;(
-    window as unknown as {
-      hermesDesktop: {
-        readDir: typeof readDir
-        selectPaths: typeof selectPaths
-      }
-    }
-  ).hermesDesktop = { readDir, selectPaths }
-}
-
-describe('RightSidebarPane', () => {
-  beforeEach(() => {
-    $connection.set(null)
-    resetProjectTreeState()
-    setCurrentCwd('/repo')
-    readDir.mockReset()
-    selectPaths.mockReset()
-    readDir.mockResolvedValue(ok([{ name: 'README.md', path: '/repo/README.md', isDirectory: false }]))
-    selectPaths.mockResolvedValue(['/repo-next'])
-    installBridge()
-  })
-
-  afterEach(() => {
-    cleanup()
-    $connection.set(null)
-    setCurrentCwd('')
-    resetProjectTreeState()
-    delete (window as unknown as { hermesDesktop?: unknown }).hermesDesktop
-  })
-
-  it('refreshes the current tree without opening the folder picker', async () => {
-    const onChangeCwd = vi.fn()
-
-    render(<RightSidebarPane onActivateFile={vi.fn()} onActivateFolder={vi.fn()} onChangeCwd={onChangeCwd} />)
-
-    await waitFor(() => expect(screen.getByRole('button', { name: 'Refresh tree' }).hasAttribute('disabled')).toBe(false))
-
-    readDir.mockClear()
-
-    fireEvent.click(screen.getByRole('button', { name: 'Refresh tree' }))
-
-    await waitFor(() => expect(readDir).toHaveBeenCalledWith('/repo'))
-    expect(selectPaths).not.toHaveBeenCalled()
-
-    fireEvent.click(screen.getByRole('button', { name: 'Open folder' }))
-
-    await waitFor(() =>
-      expect(selectPaths).toHaveBeenCalledWith({
-        defaultPath: '/repo',
-        directories: true,
-        multiple: false,
-        title: 'Change working directory'
-      })
-    )
-    await waitFor(() => expect(onChangeCwd).toHaveBeenCalledWith('/repo-next'))
-  })
-})

apps/desktop/src/app/right-sidebar/index.tsx

@@ -126,12 +126,12 @@ interface FilesystemTabProps extends FileTreeBodyProps {
   onRefresh: () => void
 }
 
-// Sidebar palette + hover-reveal: header actions stay reachable while moving
-// from the project label to the action buttons.
+// Sidebar palette + hover-reveal: refresh tracks label hover; collapse-all
+// stays visible while any folder is expanded.
 const HEADER_ACTION_CLASS =
   'text-sidebar-foreground/70 hover:bg-sidebar-accent! hover:text-sidebar-accent-foreground! focus-visible:ring-sidebar-ring'
 
-const HEADER_ACTION_LABEL_REVEAL = `${HEADER_ACTION_CLASS} pointer-events-none opacity-0 transition-opacity focus-visible:pointer-events-auto focus-visible:opacity-100 group-focus-within/project-header:pointer-events-auto group-focus-within/project-header:opacity-100 group-hover/project-header:pointer-events-auto group-hover/project-header:opacity-100`
+const HEADER_ACTION_LABEL_REVEAL = `${HEADER_ACTION_CLASS} pointer-events-none opacity-0 transition-opacity focus-visible:pointer-events-auto focus-visible:opacity-100 peer-focus-visible/project-label:pointer-events-auto peer-focus-visible/project-label:opacity-100 peer-hover/project-label:pointer-events-auto peer-hover/project-label:opacity-100`
 
 function FilesystemTab({
   canCollapse,
@@ -158,7 +158,7 @@ function FilesystemTab({
   return (
     <div className="flex min-h-0 flex-1 flex-col">
       <RightSidebarSectionHeader>
-        <div className="flex min-w-0 flex-1">
+        <div className="peer/project-label flex min-w-0 flex-1">
           <button
             className="flex w-full min-w-0 items-center rounded-md text-left hover:text-(--ui-text-secondary)"
             onClick={() => void onChangeFolder()}
@@ -216,7 +216,7 @@ function FilesystemTab({
 }
 
 export function RightSidebarSectionHeader({ children }: { children: ReactNode }) {
-  return <div className="group/project-header flex h-7 shrink-0 items-center px-2.5">{children}</div>
+  return <div className="flex h-7 shrink-0 items-center px-2.5">{children}</div>
 }
 
 interface FileTreeBodyProps {

apps/desktop/src/app/right-sidebar/store.ts

@@ -9,22 +9,3 @@ export const $terminalTakeover = atom(storedBoolean(TAKEOVER_KEY, false))
 $terminalTakeover.subscribe(active => persistBoolean(TAKEOVER_KEY, active))
 
 export const setTerminalTakeover = (active: boolean) => $terminalTakeover.set(active)
-
-/** A command queued to run in the embedded terminal. The terminal pane flushes
- *  (and clears) it once its session is live, so a value set before the pane
- *  mounts still runs. Cleared after flush so a later remount can't replay it. */
-export const $terminalInjection = atom<null | string>(null)
-
-/** Open the terminal pane and run a command in it. Used to disconnect external
- *  (CLI-managed) providers, which Hermes can't clear via the API — the user
- *  sees exactly what runs instead of Hermes silently deleting their creds. */
-export const runInTerminal = (command: string) => {
-  const trimmed = command.trim()
-
-  if (!trimmed) {
-    return
-  }
-
-  setTerminalTakeover(true)
-  $terminalInjection.set(trimmed)
-}

apps/desktop/src/app/right-sidebar/terminal/use-terminal-session.ts

@@ -10,8 +10,6 @@ import { triggerHaptic } from '@/lib/haptics'
 import { $filePreviewTarget, $previewTarget } from '@/store/preview'
 import { useTheme } from '@/themes/context'
 
-import { $terminalInjection } from '../store'
-
 import { makeTerminalReader, setActiveTerminalReader } from './buffer'
 import {
   isAddSelectionShortcut,
@@ -677,28 +675,6 @@ export function useTerminalSession({ cwd, onAddSelectionToChat }: UseTerminalSes
     return () => cancelAnimationFrame(raf)
   }, [activeTheme, themeName])
 
-  // Flush a queued command (e.g. a provider-disconnect) into the live session.
-  // Only active while open; the subscribe fires immediately, so a command set
-  // before this pane mounted runs as soon as the session is ready. Clearing the
-  // atom after writing stops a later remount from replaying a stale command.
-  useEffect(() => {
-    if (status !== 'open') {
-      return
-    }
-
-    return $terminalInjection.subscribe(command => {
-      const id = sessionIdRef.current
-
-      if (!command || !id) {
-        return
-      }
-
-      void window.hermesDesktop?.terminal?.write(id, `${command}\r`)
-      $terminalInjection.set(null)
-      termRef.current?.focus()
-    })
-  }, [status])
-
   return {
     addSelectionToChat,
     hostRef,

apps/desktop/src/app/session/hooks/use-message-stream.ts

@@ -47,7 +47,6 @@ import {
   setTurnStartedAt,
   setYoloActive
 } from '@/store/session'
-import { broadcastSessionsChanged } from '@/store/session-sync'
 import { clearSessionSubagents, pruneDelegateFallbackSubagents, upsertSubagent } from '@/store/subagents'
 import { setSessionTodos } from '@/store/todos'
 import { recordToolDiff } from '@/store/tool-diffs'
@@ -642,9 +641,6 @@ export function useMessageStream({
       })
 
       void refreshSessions().catch(() => undefined)
-      // Sync the freshly-titled row to other windows (e.g. main, when the turn
-      // ran in the pop-out).
-      broadcastSessionsChanged()
 
       if (compactedTurnRef.current.delete(sessionId)) {
         shouldHydrate = false

apps/desktop/src/app/session/hooks/use-model-controls.test.tsx

@@ -1,5 +1,5 @@
+import { renderHook } from '@testing-library/react'
 import { QueryClient } from '@tanstack/react-query'
-import { cleanup, render, renderHook } from '@testing-library/react'
 import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
 
 import { getGlobalModelInfo } from '@/hermes'
@@ -13,51 +13,12 @@ import {
 
 import { useModelControls } from './use-model-controls'
 
-const setGlobalModel = vi.fn()
-const notifyError = vi.fn()
-
 vi.mock('@/hermes', () => ({
   getGlobalModelInfo: vi.fn(),
-  setGlobalModel: (...args: Parameters<typeof setGlobalModel>) => setGlobalModel(...args)
+  setGlobalModel: vi.fn()
 }))
 
-vi.mock('@/i18n', () => ({
-  useI18n: () => ({
-    t: {
-      desktop: {
-        modelSwitchFailed: 'Model switch failed'
-      }
-    }
-  })
-}))
-
-vi.mock('@/store/notifications', () => ({
-  notifyError: (...args: Parameters<typeof notifyError>) => notifyError(...args)
-}))
-
-type Controls = ReturnType<typeof useModelControls>
-
-function Harness({
-  activeSessionId,
-  onReady,
-  requestGateway
-}: {
-  activeSessionId: string | null
-  onReady: (controls: Controls) => void
-  requestGateway: <T = unknown>(method: string, params?: Record<string, unknown>) => Promise<T>
-}) {
-  const controls = useModelControls({
-    activeSessionId,
-    queryClient: new QueryClient(),
-    requestGateway
-  })
-
-  onReady(controls)
-
-  return null
-}
-
-describe('useModelControls', () => {
+describe('useModelControls.refreshCurrentModel', () => {
   beforeEach(() => {
     $activeSessionId.set(null)
     setCurrentModel('')
@@ -65,7 +26,6 @@ describe('useModelControls', () => {
   })
 
   afterEach(() => {
-    cleanup()
     vi.restoreAllMocks()
     $activeSessionId.set(null)
     setCurrentModel('')
@@ -114,85 +74,4 @@ describe('useModelControls', () => {
     expect($currentModel.get()).toBe('deepseek/deepseek-v4-pro')
     expect($currentProvider.get()).toBe('deepseek')
   })
-
-  it('routes active-session picker changes through config.set with an explicit provider', async () => {
-    const requestGateway = vi.fn(async () => ({ key: 'model', value: 'claude-sonnet-4.6' }) as never)
-    let controls!: Controls
-
-    render(
-      <Harness
-        activeSessionId="session-1"
-        onReady={value => (controls = value)}
-        requestGateway={requestGateway}
-      />
-    )
-
-    await expect(
-      controls.selectModel({
-        model: 'claude-sonnet-4.6',
-        provider: 'anthropic'
-      })
-    ).resolves.toBe(true)
-
-    expect(requestGateway).toHaveBeenCalledWith('config.set', {
-      session_id: 'session-1',
-      key: 'model',
-      value: 'claude-sonnet-4.6 --provider anthropic'
-    })
-    expect(requestGateway).not.toHaveBeenCalledWith('slash.exec', expect.anything())
-  })
-
-  it('stores a no-session pick as UI state with no gateway or global write', async () => {
-    const requestGateway = vi.fn()
-    let controls!: Controls
-
-    render(
-      <Harness
-        activeSessionId={null}
-        onReady={value => (controls = value)}
-        requestGateway={requestGateway}
-      />
-    )
-
-    await expect(
-      controls.selectModel({
-        model: 'claude-sonnet-4.6',
-        provider: 'anthropic'
-      })
-    ).resolves.toBe(true)
-
-    // The pick is plain UI state; session.create ships it later. Nothing touches
-    // the gateway or the profile default here.
-    expect($currentModel.get()).toBe('claude-sonnet-4.6')
-    expect($currentProvider.get()).toBe('anthropic')
-    expect(requestGateway).not.toHaveBeenCalled()
-    expect(setGlobalModel).not.toHaveBeenCalled()
-  })
-
-  it('seeds an empty composer model from global but never clobbers a pick', async () => {
-    vi.mocked(getGlobalModelInfo).mockResolvedValue({ model: 'openai/gpt-5.5', provider: 'openai-codex' })
-
-    const { result } = renderHook(() =>
-      useModelControls({
-        activeSessionId: null,
-        queryClient: new QueryClient(),
-        requestGateway: vi.fn()
-      })
-    )
-
-    // Empty → seeds the default.
-    await result.current.refreshCurrentModel()
-    expect($currentModel.get()).toBe('openai/gpt-5.5')
-
-    // A user pick must survive the lifecycle refreshes that fire on boot / fresh
-    // draft / session events.
-    setCurrentModel('anthropic/claude-sonnet-4.6')
-    setCurrentProvider('anthropic')
-    await result.current.refreshCurrentModel()
-    expect($currentModel.get()).toBe('anthropic/claude-sonnet-4.6')
-
-    // A profile swap forces a reseed to the new profile's default.
-    await result.current.refreshCurrentModel(true)
-    expect($currentModel.get()).toBe('openai/gpt-5.5')
-  })
 })

apps/desktop/src/app/session/hooks/use-model-controls.ts

@@ -1,7 +1,7 @@
 import { type QueryClient } from '@tanstack/react-query'
 import { useCallback } from 'react'
 
-import { getGlobalModelInfo } from '@/hermes'
+import { getGlobalModelInfo, setGlobalModel } from '@/hermes'
 import { useI18n } from '@/i18n'
 import { notifyError } from '@/store/notifications'
 import {
@@ -15,6 +15,7 @@ import type { ModelOptionsResponse } from '@/types/hermes'
 
 interface ModelSelection {
   model: string
+  persistGlobal: boolean
   provider: string
 }
 
@@ -27,7 +28,6 @@ interface ModelControlsOptions {
 export function useModelControls({ activeSessionId, queryClient, requestGateway }: ModelControlsOptions) {
   const { t } = useI18n()
   const copy = t.desktop
-
   const updateModelOptionsCache = useCallback(
     (provider: string, model: string, includeGlobal: boolean) => {
       const patch = (prev: ModelOptionsResponse | undefined) => ({ ...(prev ?? {}), provider, model })
@@ -41,24 +41,14 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
     [activeSessionId, queryClient]
   )
 
-  // Seed the composer's model state from the profile default. `force` reseeds
-  // for a profile swap (the new profile has its own default); otherwise this
-  // only fills an EMPTY selection so a user's pick (plain UI state in
-  // $currentModel) survives the lifecycle refreshes that fire on boot / fresh
-  // draft / session events. A live session owns the footer, so skip entirely.
-  const refreshCurrentModel = useCallback(async (force = false) => {
+  const refreshCurrentModel = useCallback(async () => {
     try {
-      if ($activeSessionId.get()) {
-        return
-      }
-
-      if (!force && $currentModel.get()) {
-        return
-      }
-
       const result = await getGlobalModelInfo()
 
-      if ($activeSessionId.get() || (!force && $currentModel.get())) {
+      // A resumed/live session owns the footer model state. Global config
+      // refreshes (gateway boot, profile swap, settings save) must not clobber
+      // the active chat's runtime model/provider in the status bar.
+      if ($activeSessionId.get()) {
         return
       }
 
@@ -74,14 +64,12 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
     }
   }, [])
 
-  // Returns whether the switch succeeded so callers can await it before applying
-  // follow-up changes. The composer model is plain UI state: with no live
-  // session it's just stored (and shipped on the next session.create); with one
-  // it's scoped to that session via config.set. It NEVER writes the profile
-  // default — that lives in Settings → Model — so picking a model here can't
-  // silently mutate global config.
+  // Returns whether the switch succeeded so callers can await it before
+  // applying follow-up changes (e.g. editing a model's reasoning/fast must land
+  // on the right active model — bail rather than write to the previous one).
   const selectModel = useCallback(
     async (selection: ModelSelection): Promise<boolean> => {
+      const includeGlobal = selection.persistGlobal || !activeSessionId
       // Snapshot for rollback: the switch is applied optimistically, so a
       // failure must restore the prior model/provider (store + query cache)
       // rather than leave the UI showing a model the backend never selected.
@@ -90,34 +78,41 @@ export function useModelControls({ activeSessionId, queryClient, requestGateway
 
       setCurrentModel(selection.model)
       setCurrentProvider(selection.provider)
-      updateModelOptionsCache(selection.provider, selection.model, !activeSessionId)
-
-      // No live session yet: the pick is pure UI state. session.create reads
-      // $currentModel/$currentProvider and applies it as that session's override.
-      if (!activeSessionId) {
-        return true
-      }
+      updateModelOptionsCache(selection.provider, selection.model, includeGlobal)
 
       try {
-        await requestGateway('config.set', {
-          session_id: activeSessionId,
-          key: 'model',
-          value: `${selection.model} --provider ${selection.provider}`
-        })
+        if (activeSessionId) {
+          await requestGateway('slash.exec', {
+            session_id: activeSessionId,
+            command: `/model ${selection.model} --provider ${selection.provider}${selection.persistGlobal ? ' --global' : ''}`
+          })
 
-        void queryClient.invalidateQueries({ queryKey: ['model-options', activeSessionId] })
+          if (selection.persistGlobal) {
+            void refreshCurrentModel()
+          }
+
+          void queryClient.invalidateQueries({
+            queryKey: selection.persistGlobal ? ['model-options'] : ['model-options', activeSessionId]
+          })
+
+          return true
+        }
+
+        await setGlobalModel(selection.provider, selection.model)
+        void refreshCurrentModel()
+        void queryClient.invalidateQueries({ queryKey: ['model-options'] })
 
         return true
       } catch (err) {
         setCurrentModel(prevModel)
         setCurrentProvider(prevProvider)
-        updateModelOptionsCache(prevProvider, prevModel, !activeSessionId)
+        updateModelOptionsCache(prevProvider, prevModel, includeGlobal)
         notifyError(err, copy.modelSwitchFailed)
 
         return false
       }
     },
-    [activeSessionId, copy.modelSwitchFailed, queryClient, requestGateway, updateModelOptionsCache]
+    [activeSessionId, copy.modelSwitchFailed, queryClient, refreshCurrentModel, requestGateway, updateModelOptionsCache]
   )
 
   return { refreshCurrentModel, selectModel, updateModelOptionsCache }

apps/desktop/src/app/session/hooks/use-prompt-actions.ts

@@ -58,7 +58,6 @@ import { clearSessionTodos } from '@/store/todos'
 
 import type {
   ClientSessionState,
-  BrowserManageResponse,
   FileAttachResponse,
   HandoffFailResponse,
   HandoffRequestResponse,
@@ -1142,81 +1141,6 @@ export function usePromptActions({
           } catch (err) {
             renderSlashOutput(`error: ${err instanceof Error ? err.message : String(err)}`)
           }
-        },
-        // /browser connect|disconnect|status manages the live CDP connection on
-        // the gateway host, mirroring the TUI's browser.manage RPC. It mutates
-        // BROWSER_CDP_URL (and may launch Chrome) in the gateway process — only
-        // meaningful when that process runs on this machine, so it's gated to
-        // local connections. A remote gateway would act on the wrong host.
-        browser: async ctx => {
-          const resolved = await withSlashOutput(ctx)
-
-          if (!resolved) {
-            return
-          }
-
-          const { render: renderSlashOutput, sessionId } = resolved
-
-          if ($connection.get()?.mode === 'remote') {
-            renderSlashOutput(
-              '/browser manages a Chromium-family browser on the gateway host — only available when connected to a local gateway.'
-            )
-
-            return
-          }
-
-          const [rawAction = 'status', ...rest] = ctx.arg.trim().split(/\s+/).filter(Boolean)
-          const cmdAction = rawAction.toLowerCase()
-
-          if (!['connect', 'disconnect', 'status'].includes(cmdAction)) {
-            renderSlashOutput(
-              'usage: /browser [connect|disconnect|status] [url] · persistent: set browser.cdp_url in config.yaml'
-            )
-
-            return
-          }
-
-          const url = cmdAction === 'connect' ? rest.join(' ').trim() || 'http://127.0.0.1:9222' : undefined
-
-          if (url) {
-            renderSlashOutput(`checking Chromium-family browser remote debugging at ${url}...`)
-          }
-
-          try {
-            const result = await requestGateway<BrowserManageResponse>('browser.manage', {
-              action: cmdAction,
-              session_id: sessionId,
-              ...(url && { url })
-            })
-
-            // Without a streamed session subscription, the gateway bundles its
-            // progress lines into `messages` — flush them inline.
-            result?.messages?.forEach(message => renderSlashOutput(message))
-
-            if (cmdAction === 'status') {
-              renderSlashOutput(
-                result?.connected
-                  ? `browser connected: ${result.url || '(url unavailable)'}`
-                  : 'browser not connected (try /browser connect <url> or set browser.cdp_url in config.yaml)'
-              )
-
-              return
-            }
-
-            if (cmdAction === 'disconnect') {
-              renderSlashOutput('browser disconnected')
-
-              return
-            }
-
-            if (result?.connected) {
-              renderSlashOutput('Browser connected to live Chromium-family browser via CDP')
-              renderSlashOutput(`Endpoint: ${result.url || '(url unavailable)'}`)
-              renderSlashOutput('next browser tool call will use this CDP endpoint')
-            }
-          } catch (err) {
-            renderSlashOutput(`error: ${err instanceof Error ? err.message : String(err)}`)
-          }
         }
       }
 

apps/desktop/src/app/session/hooks/use-session-actions.ts

@@ -15,10 +15,6 @@ import { requestDesktopOnboarding } from '@/store/onboarding'
 import { $activeGatewayProfile, $newChatProfile, $profiles, ensureGatewayProfile, normalizeProfileKey } from '@/store/profile'
 import {
   $currentCwd,
-  $currentFastMode,
-  $currentModel,
-  $currentProvider,
-  $currentReasoningEffort,
   $messages,
   $sessions,
   $yoloActive,
@@ -46,7 +42,6 @@ import {
   setYoloActive,
   workspaceCwdForNewSession
 } from '@/store/session'
-import { broadcastSessionsChanged } from '@/store/session-sync'
 import { reportBackendContract } from '@/store/updates'
 import { isWatchWindow } from '@/store/windows'
 import type { SessionCreateResponse, SessionInfo, SessionResumeResponse, SessionRuntimeInfo, UsageStats } from '@/types/hermes'
@@ -411,13 +406,13 @@ export function useSessionActions({
       })
       setSessionStartedAt(null)
       setTurnStartedAt(null)
-      // The composer's model/effort/fast is sticky UI state (persisted in
-      // localStorage) — a new chat FOLLOWS your last pick instead of snapping
-      // back to the profile default, so we deliberately don't reset it here. The
-      // profile default still owns first-run seeding and profile switches (see
-      // refreshCurrentModel). Only $currentServiceTier (a live-session mirror)
-      // is cleared.
+      // New chats start in the configured default project dir when set,
+      // otherwise the sticky last-used workspace (PR #37586).
+      setCurrentModel('')
+      setCurrentProvider('')
+      setCurrentReasoningEffort('')
       setCurrentServiceTier('')
+      setCurrentFastMode(false)
       setYoloActive(false)
       setCurrentCwd(workspaceCwdForNewSession())
       setCurrentBranch('')
@@ -447,23 +442,11 @@ export function useSessionActions({
         const newChatProfile = $newChatProfile.get() ?? normalizeProfileKey($activeGatewayProfile.get())
         await ensureGatewayProfile(newChatProfile)
         const cwd = $currentCwd.get().trim() || workspaceCwdForNewSession()
-        // The composer's model/effort/fast is sticky UI state ($currentModel,
-        // $currentProvider, $currentReasoningEffort, $currentFastMode). Ship it
-        // with every session.create so the new chat opens on whatever the picker
-        // shows — applied as per-session overrides, never written to the profile
-        // default (that lives in Settings → Model).
-        const uiModel = $currentModel.get().trim()
-        const uiProvider = $currentProvider.get().trim()
-        const uiEffort = $currentReasoningEffort.get().trim()
-        const uiFast = $currentFastMode.get()
 
         const created = await requestGateway<SessionCreateResponse>('session.create', {
           cols: 96,
           ...(cwd && { cwd }),
-          ...(newChatProfile ? { profile: newChatProfile } : {}),
-          ...(uiModel ? { model: uiModel, ...(uiProvider ? { provider: uiProvider } : {}) } : {}),
-          ...(uiEffort ? { reasoning_effort: uiEffort } : {}),
-          ...(uiFast ? { fast: true } : {})
+          ...(newChatProfile ? { profile: newChatProfile } : {})
         })
 
         const stored = created.stored_session_id ?? null
@@ -489,9 +472,6 @@ export function useSessionActions({
           // server later returns its own preview/title and supersedes this.
           upsertOptimisticSession(created, stored, null, preview?.trim() || null)
           navigate(sessionRoute(stored), { replace: true })
-          // Other windows (e.g. the main window when this is the pop-out) can't
-          // see this session until they re-pull the shared list.
-          broadcastSessionsChanged()
         }
 
         setFreshDraftReady(false)

apps/desktop/src/app/settings/index.tsx

@@ -228,7 +228,7 @@ export function SettingsView({ gateway, onClose, onConfigSaved, onMainModelChang
               onMainModelChanged={onMainModelChanged}
             />
           ) : activeView === 'providers' ? (
-            <ProvidersSettings onClose={onClose} onViewChange={setProviderView} view={providerView} />
+            <ProvidersSettings onViewChange={setProviderView} view={providerView} />
           ) : activeView === 'keys' ? (
             <KeysSettings view={keysView} />
           ) : activeView === 'mcp' ? (

apps/desktop/src/app/settings/model-settings.test.tsx

@@ -16,8 +16,6 @@ const getAuxiliaryModels = vi.fn()
 const setModelAssignment = vi.fn()
 const getRecommendedDefaultModel = vi.fn()
 const setEnvVar = vi.fn()
-const getHermesConfigRecord = vi.fn()
-const saveHermesConfig = vi.fn()
 const startManualProviderOAuth = vi.fn()
 
 vi.mock('@/hermes', () => ({
@@ -26,9 +24,7 @@ vi.mock('@/hermes', () => ({
   getAuxiliaryModels: () => getAuxiliaryModels(),
   setModelAssignment: (body: unknown) => setModelAssignment(body),
   getRecommendedDefaultModel: (slug: string) => getRecommendedDefaultModel(slug),
-  setEnvVar: (key: string, value: string) => setEnvVar(key, value),
-  getHermesConfigRecord: () => getHermesConfigRecord(),
-  saveHermesConfig: (config: unknown) => saveHermesConfig(config)
+  setEnvVar: (key: string, value: string) => setEnvVar(key, value)
 }))
 
 vi.mock('@/store/onboarding', () => ({
@@ -39,13 +35,7 @@ beforeEach(() => {
   getGlobalModelInfo.mockResolvedValue({ provider: 'nous', model: 'hermes-4' })
   getGlobalModelOptions.mockResolvedValue({
     providers: [
-      {
-        name: 'Nous',
-        slug: 'nous',
-        models: ['hermes-4', 'hermes-4-mini'],
-        authenticated: true,
-        capabilities: { 'hermes-4': { reasoning: true, fast: true } }
-      },
+      { name: 'Nous', slug: 'nous', models: ['hermes-4', 'hermes-4-mini'], authenticated: true },
       // An unconfigured api_key provider — surfaced by the full-universe payload.
       { name: 'DeepSeek', slug: 'deepseek', models: [], authenticated: false, auth_type: 'api_key', key_env: 'DEEPSEEK_API_KEY' }
     ]
@@ -57,8 +47,6 @@ beforeEach(() => {
   setModelAssignment.mockResolvedValue({ provider: 'nous', model: 'hermes-4', gateway_tools: [] })
   getRecommendedDefaultModel.mockResolvedValue({ provider: 'deepseek', model: 'deepseek-chat', free_tier: null })
   setEnvVar.mockResolvedValue({ ok: true })
-  getHermesConfigRecord.mockResolvedValue({ agent: { reasoning_effort: 'medium', service_tier: 'normal' } })
-  saveHermesConfig.mockResolvedValue({ ok: true })
 })
 
 afterEach(() => {
@@ -112,31 +100,6 @@ describe('ModelSettings', () => {
     await waitFor(() => expect(setEnvVar).toHaveBeenCalledWith('DEEPSEEK_API_KEY', 'sk-test-123'))
   })
 
-  it('writes the profile default speed (service_tier) when the fast switch is toggled', async () => {
-    await renderModelSettings()
-    await waitFor(() => expect(getHermesConfigRecord).toHaveBeenCalled())
-
-    const fastSwitch = await screen.findByRole('switch')
-    fireEvent.click(fastSwitch)
-
-    await waitFor(() =>
-      expect(saveHermesConfig).toHaveBeenCalledWith(
-        expect.objectContaining({ agent: expect.objectContaining({ service_tier: 'fast' }) })
-      )
-    )
-  })
-
-  it('hides the reasoning/speed defaults when the main model reports no capabilities', async () => {
-    getGlobalModelOptions.mockResolvedValueOnce({
-      providers: [{ name: 'Nous', slug: 'nous', models: ['hermes-4'], authenticated: true, capabilities: { 'hermes-4': { reasoning: false, fast: false } } }]
-    })
-
-    await renderModelSettings()
-    await waitFor(() => expect(getHermesConfigRecord).toHaveBeenCalled())
-
-    expect(screen.queryByRole('switch')).toBeNull()
-  })
-
   it('renders the auxiliary task rows', async () => {
     await renderModelSettings()
 

apps/desktop/src/app/settings/model-settings.tsx

@@ -3,14 +3,11 @@ import { useCallback, useEffect, useMemo, useState } from 'react'
 import { Button } from '@/components/ui/button'
 import { Input } from '@/components/ui/input'
 import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '@/components/ui/select'
-import { Switch } from '@/components/ui/switch'
 import {
   getAuxiliaryModels,
   getGlobalModelInfo,
   getGlobalModelOptions,
-  getHermesConfigRecord,
   getRecommendedDefaultModel,
-  saveHermesConfig,
   setEnvVar,
   setModelAssignment
 } from '@/hermes'
@@ -18,26 +15,11 @@ import type { AuxiliaryModelsResponse, ModelOptionProvider, StaleAuxAssignment }
 import { useI18n } from '@/i18n'
 import { AlertTriangle, Cpu, Loader2 } from '@/lib/icons'
 import { cn } from '@/lib/utils'
-import { notifyError } from '@/store/notifications'
 import { startManualLocalEndpoint, startManualProviderOAuth } from '@/store/onboarding'
-import type { HermesConfigRecord } from '@/types/hermes'
 
 import { CONTROL_TEXT } from './constants'
-import { getNested, setNested } from './helpers'
 import { ListRow, LoadingState, Pill, SectionHeading } from './primitives'
 
-// Hermes' reasoning levels (VALID_REASONING_EFFORTS); `none` = thinking off.
-// Empty config = Hermes default (medium), shown as Medium.
-const EFFORT_VALUES = ['none', 'minimal', 'low', 'medium', 'high', 'xhigh'] as const
-
-// agent.service_tier stores "fast"/"priority"/"on" for fast; anything else is
-// normal (mirrors tui_gateway _load_service_tier).
-const isFastTier = (tier: unknown): boolean =>
-  ['fast', 'priority', 'on'].includes(String(tier ?? '').trim().toLowerCase())
-
-// Reuse the composer's effort labels (`xhigh` shows as "Max", else 1:1).
-const effortLabelKey = (v: string) => (v === 'xhigh' ? 'max' : v) as 'high' | 'low' | 'max' | 'medium' | 'minimal'
-
 // A provider row is "ready" to pick a model from when it reports models. The
 // backend now surfaces the full `hermes model` universe (every canonical
 // provider), so unconfigured providers come back with `authenticated:false`
@@ -115,9 +97,6 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
   const [selectedProvider, setSelectedProvider] = useState('')
   const [selectedModel, setSelectedModel] = useState('')
   const [auxiliary, setAuxiliary] = useState<AuxiliaryModelsResponse | null>(null)
-  // Full profile config, kept so the reasoning/speed defaults round-trip
-  // (read agent.* → write back the whole record) like the generic config page.
-  const [config, setConfig] = useState<HermesConfigRecord | null>(null)
   const [applying, setApplying] = useState(false)
   const [editingAuxTask, setEditingAuxTask] = useState<null | string>(null)
   const [auxDraft, setAuxDraft] = useState<{ model: string; provider: string }>({ model: '', provider: '' })
@@ -134,11 +113,10 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
     setError('')
 
     try {
-      const [modelInfo, modelOptions, auxiliaryModels, cfg] = await Promise.all([
+      const [modelInfo, modelOptions, auxiliaryModels] = await Promise.all([
         getGlobalModelInfo(),
         getGlobalModelOptions(),
-        getAuxiliaryModels(),
-        getHermesConfigRecord()
+        getAuxiliaryModels()
       ])
 
       setMainModel({ model: modelInfo.model, provider: modelInfo.provider })
@@ -146,7 +124,6 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
       setSelectedProvider(prev => prev || modelInfo.provider)
       setSelectedModel(prev => prev || modelInfo.model)
       setAuxiliary(auxiliaryModels)
-      setConfig(cfg)
     } catch (err) {
       setError(err instanceof Error ? err.message : String(err))
     } finally {
@@ -204,42 +181,6 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
       .map(entry => ({ task: entry.task, provider: entry.provider, model: entry.model }))
   }, [auxiliary, mainModel])
 
-  // Capabilities of the APPLIED main model — gates the profile-default
-  // reasoning/speed controls the same way the composer picker gates per-model
-  // edits (reasoning defaults on, fast defaults off when unreported).
-  const mainCaps = useMemo(() => {
-    const row = providers.find(provider => provider.slug === mainModel?.provider)
-
-    return mainModel ? row?.capabilities?.[mainModel.model] : undefined
-  }, [providers, mainModel])
-
-  const reasoningSupported = mainCaps?.reasoning ?? true
-  const fastSupported = mainCaps?.fast ?? false
-  const effortValue = String(getNested(config ?? {}, 'agent.reasoning_effort') ?? '').trim().toLowerCase() || 'medium'
-  const fastOn = isFastTier(getNested(config ?? {}, 'agent.service_tier'))
-
-  // Persist a single agent.* default by round-tripping the whole config record
-  // (PUT /api/config replaces it) — optimistic, with rollback on failure.
-  const writeAgentDefault = useCallback(
-    async (key: string, value: string) => {
-      if (!config) {
-        return
-      }
-
-      const prev = config
-      const next = setNested(config, key, value)
-      setConfig(next)
-
-      try {
-        await saveHermesConfig(next)
-      } catch (err) {
-        setConfig(prev)
-        notifyError(err, m.defaultsFailed)
-      }
-    },
-    [config, m.defaultsFailed]
-  )
-
   // Paste an API key for the selected `api_key` provider, persist it, then
   // refresh so the now-authenticated provider's models populate. Auto-selects
   // the recommended default model so the user can Apply in one more click.
@@ -492,38 +433,6 @@ export function ModelSettings({ onMainModelChanged }: ModelSettingsProps) {
               : `${selectedProviderRow?.name} signs in through your browser — Hermes runs the flow for you.`}
           </p>
         )}
-        {config && mainModel && (reasoningSupported || fastSupported) && (
-          <div className="mt-3 flex flex-wrap items-center gap-x-6 gap-y-3">
-            <span className="text-xs text-muted-foreground">{m.defaultsLabel}</span>
-            {reasoningSupported && (
-              <div className="flex items-center gap-2 text-xs">
-                {m.reasoning}
-                <Select onValueChange={value => void writeAgentDefault('agent.reasoning_effort', value)} value={effortValue}>
-                  <SelectTrigger className={cn('min-w-28', CONTROL_TEXT)}>
-                    <SelectValue />
-                  </SelectTrigger>
-                  <SelectContent>
-                    {EFFORT_VALUES.map(value => (
-                      <SelectItem key={value} value={value}>
-                        {value === 'none' ? m.reasoningOff : t.shell.modelOptions[effortLabelKey(value)]}
-                      </SelectItem>
-                    ))}
-                  </SelectContent>
-                </Select>
-              </div>
-            )}
-            {fastSupported && (
-              <label className="flex items-center gap-2 text-xs">
-                {t.shell.modelOptions.fast}
-                <Switch
-                  checked={fastOn}
-                  onCheckedChange={checked => void writeAgentDefault('agent.service_tier', checked ? 'fast' : 'normal')}
-                  size="xs"
-                />
-              </label>
-            )}
-          </div>
-        )}
         {error && <div className="mt-2 text-xs text-destructive">{error}</div>}
         {switchStaleAux.length > 0 && (
           <div className="mt-2">

apps/desktop/src/app/settings/providers-settings.test.tsx

@@ -55,7 +55,7 @@ afterEach(() => {
 async function renderProvidersSettings() {
   const { ProvidersSettings } = await import('./providers-settings')
 
-  return render(<ProvidersSettings onClose={vi.fn()} onViewChange={vi.fn()} view="accounts" />)
+  return render(<ProvidersSettings onViewChange={vi.fn()} view="accounts" />)
 }
 
 describe('ProvidersSettings', () => {
@@ -95,6 +95,6 @@ describe('ProvidersSettings', () => {
 
     expect(await screen.findByText('Qwen Code')).toBeTruthy()
     expect(screen.queryByRole('button', { name: 'Remove Qwen Code' })).toBeNull()
-    expect(screen.getByText(/managed by its own CLI/)).toBeTruthy()
+    expect(screen.getByText(/managed outside Hermes/)).toBeTruthy()
   })
 })

apps/desktop/src/app/settings/providers-settings.tsx

@@ -1,8 +1,6 @@
 import { useStore } from '@nanostores/react'
-import type { ReactNode } from 'react'
 import { useCallback, useEffect, useMemo, useState } from 'react'
 
-import { runInTerminal } from '@/app/right-sidebar/store'
 import {
   FEATURED_ID,
   FeaturedProviderRow,
@@ -25,20 +23,6 @@ import { SettingsCategoryHeading, useEnvCredentials } from './env-credentials'
 import { providerGroup, providerMeta, providerPriority } from './helpers'
 import { LoadingState, SettingsContent } from './primitives'
 
-// The embedded terminal (and thus the "run disconnect command" path) only
-// exists in the Electron desktop shell, not the web dashboard.
-const canRunInTerminal = () => typeof window !== 'undefined' && Boolean(window.hermesDesktop?.terminal)
-
-// Parallel group headers ("Connected", "Other providers") so the expanded list
-// reads as its own section instead of bleeding into the connected group.
-function GroupLabel({ children }: { children: ReactNode }) {
-  return (
-    <p className="mt-3 px-0.5 text-[length:var(--conversation-caption-font-size)] font-medium text-(--ui-text-tertiary)">
-      {children}
-    </p>
-  )
-}
-
 // Sub-views surfaced as a sidebar subnav: account sign-in vs raw API keys.
 export const PROVIDER_VIEWS = ['accounts', 'keys'] as const
 
@@ -106,13 +90,11 @@ function buildProviderKeyGroups(vars: Record<string, EnvVarInfo>): ProviderKeyGr
 function OAuthPicker({
   disconnecting,
   onDisconnect,
-  onTerminalDisconnect,
   onWantApiKey,
   providers
 }: {
   disconnecting: null | string
   onDisconnect: (provider: OAuthProvider) => void
-  onTerminalDisconnect: (provider: OAuthProvider) => void
   onWantApiKey: () => void
   providers: OAuthProvider[]
 }) {
@@ -156,14 +138,15 @@ function OAuthPicker({
       {featured && <FeaturedProviderRow onSelect={select} provider={featured} />}
       {connected.length > 0 && (
         <>
-          <GroupLabel>{p.connected}</GroupLabel>
+          <p className="mt-1 px-0.5 text-[length:var(--conversation-caption-font-size)] font-medium text-(--ui-text-tertiary)">
+            {p.connected}
+          </p>
           {connected.map(p => (
             <ConnectedProviderRow
               disconnecting={disconnecting === p.id}
               key={p.id}
               onDisconnect={onDisconnect}
               onSelect={select}
-              onTerminalDisconnect={onTerminalDisconnect}
               provider={p}
             />
           ))}
@@ -171,7 +154,6 @@ function OAuthPicker({
       )}
       {showOthers && (
         <>
-          {connected.length > 0 && <GroupLabel>{p.otherProviders}</GroupLabel>}
           {others.map(p => (
             <ProviderRow key={p.id} onSelect={select} provider={p} />
           ))}
@@ -198,26 +180,21 @@ function ConnectedProviderRow({
   disconnecting,
   onDisconnect,
   onSelect,
-  onTerminalDisconnect,
   provider
 }: {
   disconnecting: boolean
   onDisconnect: (provider: OAuthProvider) => void
   onSelect: (provider: OAuthProvider) => void
-  onTerminalDisconnect: (provider: OAuthProvider) => void
   provider: OAuthProvider
 }) {
   const { t } = useI18n()
-  const copy = t.settings.providers
   const title = providerTitle(provider)
   const Trail = provider.flow === 'external' ? Terminal : ChevronRight
-  // Hermes can clear this provider's creds via the API.
   const canDisconnect = provider.disconnectable ?? provider.flow !== 'external'
-  // External (CLI-managed) provider Hermes can't clear via the API, but ships a
-  // command we can run in the embedded terminal (Electron shell only).
-  const terminalDisconnect = !canDisconnect && Boolean(provider.disconnect_command) && canRunInTerminal()
-  // Only fall back to a static "remove it elsewhere" hint when we offer no button.
-  const showHint = !canDisconnect && !terminalDisconnect
+
+  const disconnectHint = provider.flow === 'external'
+    ? t.settings.providers.removeExternal(title, provider.cli_command)
+    : t.settings.providers.removeKeyManaged(title)
 
   return (
     <div className="group grid grid-cols-[minmax(0,1fr)_auto] items-center gap-1 rounded-[6px] transition-colors hover:bg-(--ui-control-hover-background)">
@@ -226,13 +203,13 @@ function ConnectedProviderRow({
           <span className="truncate text-[length:var(--conversation-text-font-size)] font-semibold">{title}</span>
           <span className="inline-flex shrink-0 items-center gap-1 bg-primary/10 px-2 py-0.5 text-xs font-medium text-primary">
             <Check className="size-3" />
-            {copy.connected}
+            {t.settings.providers.connected}
           </span>
         </div>
         <p className="mt-1 text-xs leading-5 text-muted-foreground">{t.onboarding.flowSubtitles[provider.flow]}</p>
-        {showHint && (
+        {!canDisconnect && (
           <p className="mt-0.5 truncate text-[0.68rem] leading-5 text-muted-foreground/70">
-            {provider.flow === 'external' ? copy.removeExternalGeneric(title) : copy.removeKeyManaged(title)}
+            {disconnectHint}
           </p>
         )}
       </button>
@@ -251,18 +228,6 @@ function ConnectedProviderRow({
             {disconnecting ? <Loader2 className="size-3 animate-spin" /> : <Trash2 className="size-3" />}
           </Button>
         )}
-        {terminalDisconnect && (
-          <Button
-            aria-label={`${copy.disconnect} ${title}`}
-            onClick={() => onTerminalDisconnect(provider)}
-            size="icon-xs"
-            title={copy.disconnectInTerminal}
-            type="button"
-            variant="ghost"
-          >
-            <Trash2 className="size-3" />
-          </Button>
-        )}
       </div>
     </div>
   )
@@ -278,7 +243,7 @@ function NoProviderKeys() {
   )
 }
 
-export function ProvidersSettings({ onClose, onViewChange, view }: ProvidersSettingsProps) {
+export function ProvidersSettings({ onViewChange, view }: ProvidersSettingsProps) {
   const { t } = useI18n()
   const { rowProps, vars } = useEnvCredentials()
   const [oauthProviders, setOauthProviders] = useState<OAuthProvider[]>([])
@@ -317,29 +282,6 @@ export function ProvidersSettings({ onClose, onViewChange, view }: ProvidersSett
     return () => void (cancelled = true)
   }, [onboardingActive])
 
-  // External (CLI-managed) providers can't be cleared via the API by design —
-  // Hermes never deletes creds another tool owns behind a silent API call.
-  // Instead we run the documented removal command in the embedded terminal so
-  // the user sees exactly what executes, then return them to chat to watch it.
-  function handleTerminalDisconnect(provider: OAuthProvider) {
-    const command = provider.disconnect_command
-
-    if (!command) {
-      return
-    }
-
-    const name = providerTitle(provider)
-
-    if (!window.confirm(t.settings.providers.removeTerminalConfirm(name, command))) {
-      return
-    }
-
-    // Leave the settings overlay so the terminal pane (chat-only) is visible.
-    onClose()
-    runInTerminal(command)
-    notify({ kind: 'info', title: t.settings.providers.removedTitle, message: t.settings.providers.removeTerminalRunning(name) })
-  }
-
   async function handleDisconnect(provider: OAuthProvider) {
     const name = providerTitle(provider)
 
@@ -399,7 +341,6 @@ export function ProvidersSettings({ onClose, onViewChange, view }: ProvidersSett
       <OAuthPicker
         disconnecting={disconnecting}
         onDisconnect={provider => void handleDisconnect(provider)}
-        onTerminalDisconnect={handleTerminalDisconnect}
         onWantApiKey={() => onViewChange('keys')}
         providers={oauthProviders}
       />
@@ -418,7 +359,6 @@ interface ProviderKeyGroup {
 }
 
 interface ProvidersSettingsProps {
-  onClose: () => void
   onViewChange: (view: ProviderView) => void
   view: ProviderView
 }

apps/desktop/src/app/shell/app-shell.tsx

@@ -80,10 +80,6 @@ export function AppShell({
   const connection = useStore($connection)
   const viewportFullscreen = useSyncExternalStore(subscribeWindowSize, viewportIsFullscreen, () => false)
   const isFullscreen = Boolean(connection?.isFullscreen) || viewportFullscreen
-  // Every secondary window (new-session scratch, subagent watch, cmd-click
-  // pop-out) is a compact side panel — none of them carry the full titlebar
-  // tool cluster. Gate on isSecondaryWindow, never the narrower new-session flag.
-  const hideTitlebarControls = isSecondaryWindow()
   const titlebarControls = titlebarControlsPosition(connection?.windowButtonPosition, isFullscreen)
   // Width Windows/Linux reserve for the OS-painted min/max/close overlay (zero
   // on macOS, where window controls sit on the left and are reported via
@@ -166,9 +162,7 @@ export function AppShell({
         } as CSSProperties
       }
     >
-      {!hideTitlebarControls && (
-        <TitlebarControls leftTools={leftTitlebarTools} onOpenSettings={onOpenSettings} tools={titlebarTools} />
-      )}
+      <TitlebarControls leftTools={leftTitlebarTools} onOpenSettings={onOpenSettings} tools={titlebarTools} />
 
       <main className="relative z-3 flex min-h-0 w-full flex-1 flex-col overflow-hidden transition-none">
         <PaneShell className="min-h-0 flex-1">
@@ -189,9 +183,7 @@ export function AppShell({
             the panes' z-20 resize handles, keeping every pane resizable. */}
         {mainOverlays}
 
-        {/* The compact pop-out drops the statusbar — it's a scratch window, not
-            the full shell. */}
-        {!isSecondaryWindow() && <StatusbarControls items={statusbarItems} leftItems={leftStatusbarItems} />}
+        <StatusbarControls items={statusbarItems} leftItems={leftStatusbarItems} />
       </main>
 
       {overlays}

apps/desktop/src/app/shell/hooks/use-statusbar-items.tsx

@@ -1,4 +1,5 @@
 import { useStore } from '@nanostores/react'
+import type { ReactNode } from 'react'
 import { useCallback, useMemo } from 'react'
 
 import type { CommandCenterSection } from '@/app/command-center'
@@ -8,6 +9,7 @@ import { useI18n } from '@/i18n'
 import {
   Activity,
   AlertCircle,
+  ChevronDown,
   Clock,
   Command,
   Hash,
@@ -17,6 +19,7 @@ import {
   Zap,
   ZapFilled
 } from '@/lib/icons'
+import { formatModelStatusLabel } from '@/lib/model-status-label'
 import type { RuntimeReadinessResult } from '@/lib/runtime-readiness'
 import { contextBarLabel, LiveDuration, usageContextLabel } from '@/lib/statusbar'
 import { cn } from '@/lib/utils'
@@ -27,11 +30,16 @@ import {
   $activeSessionId,
   $busy,
   $connection,
+  $currentFastMode,
+  $currentModel,
+  $currentProvider,
+  $currentReasoningEffort,
   $currentUsage,
   $sessionStartedAt,
   $turnStartedAt,
   $workingSessionIds,
   $yoloActive,
+  setModelPickerOpen,
   setYoloActive
 } from '@/store/session'
 import { $subagentsBySession, activeSubagentCount } from '@/store/subagents'
@@ -57,6 +65,7 @@ interface StatusbarItemsOptions {
   gatewayLogLines: readonly string[]
   gatewayState: string
   inferenceStatus: RuntimeReadinessResult | null
+  modelMenuContent?: ReactNode
   openAgents: () => void
   openCommandCenterSection: (section: CommandCenterSection) => void
   freshDraftReady: boolean
@@ -74,6 +83,7 @@ export function useStatusbarItems({
   gatewayLogLines,
   gatewayState,
   inferenceStatus,
+  modelMenuContent,
   openAgents,
   openCommandCenterSection,
   freshDraftReady,
@@ -87,6 +97,10 @@ export function useStatusbarItems({
   const terminalTakeover = useStore($terminalTakeover)
   const yoloActive = useStore($yoloActive)
   const busy = useStore($busy)
+  const currentFastMode = useStore($currentFastMode)
+  const currentModel = useStore($currentModel)
+  const currentProvider = useStore($currentProvider)
+  const currentReasoningEffort = useStore($currentReasoningEffort)
   const currentUsage = useStore($currentUsage)
   const desktopActionTasks = useStore($desktopActionTasks)
   const previewServerRestartStatus = useStore($previewServerRestartStatus)
@@ -402,6 +416,37 @@ export function useStatusbarItems({
         title: yoloActive ? copy.yoloOn : copy.yoloOff,
         variant: 'action'
       },
+      {
+        id: 'model-summary',
+        label: (
+          <span className="inline-flex min-w-0 items-center gap-0.5">
+            <span className="truncate">
+              {formatModelStatusLabel(currentModel, {
+                fastMode: currentFastMode,
+                reasoningEffort: currentReasoningEffort
+              })}
+            </span>
+            <ChevronDown className="size-2.5 shrink-0 opacity-50" />
+          </span>
+        ),
+        ...(modelMenuContent
+          ? {
+              menuAlign: 'end' as const,
+              menuClassName: 'w-64',
+              menuContent: modelMenuContent,
+              title: currentProvider
+                ? copy.modelTitle(currentProvider, currentModel || copy.modelNone)
+                : copy.switchModel,
+              variant: 'menu' as const
+            }
+          : {
+              onSelect: () => setModelPickerOpen(true),
+              title: currentProvider
+                ? copy.providerModelTitle(currentProvider, currentModel || copy.noModel)
+                : copy.openModelPicker,
+              variant: 'action' as const
+            })
+      },
       {
         className: `w-7 justify-center px-0${terminalTakeover ? ' bg-accent/55 text-foreground' : ''}`,
         hidden: !chatOpen,
@@ -420,6 +465,11 @@ export function useStatusbarItems({
       contextBar,
       contextUsage,
       copy,
+      currentFastMode,
+      currentModel,
+      currentProvider,
+      currentReasoningEffort,
+      modelMenuContent,
       sessionStartedAt,
       showYoloToggle,
       terminalTakeover,

apps/desktop/src/app/shell/model-edit-submenu.test.tsx

@@ -1,84 +0,0 @@
-import { cleanup, fireEvent, render, screen } from '@testing-library/react'
-import { afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest'
-
-import { DropdownMenu, DropdownMenuContent, DropdownMenuSub, DropdownMenuSubTrigger } from '@/components/ui/dropdown-menu'
-import { $modelPresets, getModelPreset } from '@/store/model-presets'
-import { $activeSessionId } from '@/store/session'
-
-import { type FastControl, ModelEditSubmenu } from './model-edit-submenu'
-
-// Radix calls these on open; jsdom doesn't implement them.
-beforeAll(() => {
-  Element.prototype.scrollIntoView = vi.fn()
-  Element.prototype.hasPointerCapture = vi.fn(() => false)
-  Element.prototype.releasePointerCapture = vi.fn()
-})
-
-beforeEach(() => {
-  $modelPresets.set({})
-  $activeSessionId.set(null)
-})
-
-afterEach(() => {
-  cleanup()
-  vi.clearAllMocks()
-})
-
-// Render the submenu inside an open menu/sub so its content (switches) mounts.
-function renderSubmenu(opts: { fastControl: FastControl; reasoning: boolean; requestGateway: () => Promise<unknown> }) {
-  return render(
-    <DropdownMenu open>
-      <DropdownMenuContent>
-        <DropdownMenuSub open>
-          <DropdownMenuSubTrigger>edit</DropdownMenuSubTrigger>
-          <ModelEditSubmenu
-            effort="medium"
-            fastControl={opts.fastControl}
-            isActive
-            model="m1"
-            onSelectModel={vi.fn()}
-            provider="p1"
-            reasoning={opts.reasoning}
-            requestGateway={opts.requestGateway as never}
-          />
-        </DropdownMenuSub>
-      </DropdownMenuContent>
-    </DropdownMenu>
-  )
-}
-
-// Regression: editing the active row before a live session exists must stay
-// preset-only — the gateway's config.set falls back to global config when no
-// session matches, so it must not be called. (Caught in the second review.)
-describe('ModelEditSubmenu no-session guard', () => {
-  it('param fast: records the preset but skips the gateway without a session', () => {
-    const requestGateway = vi.fn().mockResolvedValue({})
-    renderSubmenu({ fastControl: { kind: 'param', on: false }, reasoning: false, requestGateway })
-
-    fireEvent.click(screen.getByRole('switch'))
-
-    expect(getModelPreset('p1', 'm1').fast).toBe(true)
-    expect(requestGateway).not.toHaveBeenCalled()
-  })
-
-  it('reasoning: records the preset but skips the gateway without a session', () => {
-    const requestGateway = vi.fn().mockResolvedValue({})
-    renderSubmenu({ fastControl: { kind: 'none' }, reasoning: true, requestGateway })
-
-    // Thinking starts on (medium); toggling it off routes through patchReasoning.
-    fireEvent.click(screen.getByRole('switch'))
-
-    expect(getModelPreset('p1', 'm1').effort).toBe('none')
-    expect(requestGateway).not.toHaveBeenCalled()
-  })
-
-  it('param fast: pushes to the gateway once a session is active', async () => {
-    const requestGateway = vi.fn().mockResolvedValue({})
-    $activeSessionId.set('sess1')
-    renderSubmenu({ fastControl: { kind: 'param', on: false }, reasoning: false, requestGateway })
-
-    fireEvent.click(screen.getByRole('switch'))
-
-    expect(requestGateway).toHaveBeenCalledWith('config.set', { key: 'fast', session_id: 'sess1', value: 'fast' })
-  })
-})

apps/desktop/src/app/shell/model-edit-submenu.tsx

@@ -12,9 +12,13 @@ import {
 } from '@/components/ui/dropdown-menu'
 import { Switch } from '@/components/ui/switch'
 import { useI18n } from '@/i18n'
-import { setModelPreset } from '@/store/model-presets'
 import { notifyError } from '@/store/notifications'
-import { $activeSessionId, setCurrentFastMode, setCurrentReasoningEffort } from '@/store/session'
+import {
+  $activeSessionId,
+  $currentReasoningEffort,
+  setCurrentFastMode,
+  setCurrentReasoningEffort
+} from '@/store/session'
 
 // Hermes' real reasoning levels (see VALID_REASONING_EFFORTS); `none` is owned
 // by the Thinking toggle, not the radio.
@@ -72,104 +76,96 @@ export function resolveFastControl(
 }
 
 interface ModelEditSubmenuProps {
-  /** This row's effective reasoning effort (live for the active model, else its
-   *  preset) — the submenu shows and edits from this, never the raw session. */
-  effort: string
   /** How fast mode is offered for this model (param toggle vs. variant swap). */
   fastControl: FastControl
   /** Whether this row's model is the active one. */
   isActive: boolean
-  /** This row's model id — edits persist as its global preset. */
-  model: string
+  /** Switch to this model (resolves false on failure). Awaited before applying
+   *  edits when not active so a failed switch doesn't write to the old model. */
+  onActivate: () => Promise<boolean> | void
   /** Switch to a specific model id (used to swap base ⇄ -fast variant). */
   onSelectModel: (model: string) => Promise<boolean> | void
-  /** This row's provider slug — edits persist as its global preset. */
-  provider: string
   /** Whether this model supports reasoning effort. */
   reasoning: boolean
   requestGateway: <T>(method: string, params?: Record<string, unknown>) => Promise<T>
 }
 
 export function ModelEditSubmenu({
-  effort,
   fastControl,
   isActive,
-  model,
+  onActivate,
   onSelectModel,
-  provider,
   reasoning,
   requestGateway
 }: ModelEditSubmenuProps) {
   const { t } = useI18n()
   const copy = t.shell.modelOptions
+  // Reactive session state comes straight from the stores rather than being
+  // drilled through the panel, so editing it re-renders only this submenu.
   const activeSessionId = useStore($activeSessionId)
+  const currentReasoningEffort = useStore($currentReasoningEffort)
 
-  const effortValue = normalizeEffort(effort)
-  const thinkingOn = isThinkingEnabled(effort)
+  const effort = normalizeEffort(currentReasoningEffort)
+  const thinkingOn = isThinkingEnabled(currentReasoningEffort)
 
-  // Editing always records the model's global preset; the active model also gets
-  // it pushed onto the live session. Non-active edits stay preset-only — they do
-  // not switch you to that model.
-  const patchReasoning = async (next: string) => {
-    setModelPreset(provider, model, { effort: next })
-
-    if (!isActive) {
-      return
+  // Reasoning/fast are session-scoped (they apply to the active model), so
+  // editing a non-active model first switches to it. Returns false if the
+  // switch failed, so callers skip applying to the wrong (previous) model.
+  const ensureActive = async (): Promise<boolean> => {
+    if (isActive) {
+      return true
     }
 
+    return (await onActivate()) !== false
+  }
+
+  const patchReasoning = async (next: string, rollback: string) => {
     setCurrentReasoningEffort(next)
 
-    // Preset-only without a session: `isActive` holds for the global/default
-    // row pre-session, and the gateway's `config.set` falls back to global
-    // config when none matches — so don't reach it (preset + optimistic store
-    // are the whole effect). Same guard in applyModelPreset / toggleFast.
-    if (!activeSessionId) {
-      return
-    }
-
     try {
-      await requestGateway('config.set', { key: 'reasoning', session_id: activeSessionId, value: next })
+      if (!(await ensureActive())) {
+        setCurrentReasoningEffort(rollback)
+
+        return
+      }
+
+      await requestGateway('config.set', {
+        key: 'reasoning',
+        session_id: activeSessionId ?? '',
+        value: next
+      })
     } catch (err) {
-      setCurrentReasoningEffort(effort)
-      setModelPreset(provider, model, { effort })
+      setCurrentReasoningEffort(rollback)
       notifyError(err, copy.updateFailed)
     }
   }
 
   const toggleFast = (enabled: boolean) => {
     if (fastControl.kind === 'variant') {
-      // Fast is a separate model id. Record the choice on the base model's
-      // preset (selectFamily picks the `-fast` sibling later when set), and
-      // only swap models now if this is the active row — inactive edits must
-      // stay preset-only, same as the param path below.
-      setModelPreset(provider, fastControl.baseId, { fast: enabled })
-
-      if (isActive) {
-        void onSelectModel(enabled ? fastControl.fastId : fastControl.baseId)
-      }
+      // Fast is a separate model id — swap to it (or back to the base).
+      void onSelectModel(enabled ? fastControl.fastId : fastControl.baseId)
 
       return
     }
 
     if (fastControl.kind === 'param') {
-      setModelPreset(provider, model, { fast: enabled })
-
-      if (!isActive) {
-        return
-      }
-
       setCurrentFastMode(enabled)
 
-      // Preset-only without a session (see patchReasoning).
-      if (!activeSessionId) {
-        return
-      }
       void (async () => {
         try {
-          await requestGateway('config.set', { key: 'fast', session_id: activeSessionId, value: enabled ? 'fast' : 'normal' })
+          if (!(await ensureActive())) {
+            setCurrentFastMode(!enabled)
+
+            return
+          }
+
+          await requestGateway('config.set', {
+            key: 'fast',
+            session_id: activeSessionId ?? '',
+            value: enabled ? 'fast' : 'normal'
+          })
         } catch (err) {
           setCurrentFastMode(!enabled)
-          setModelPreset(provider, model, { fast: !enabled })
           notifyError(err, copy.fastFailed)
         }
       })()
@@ -192,7 +188,9 @@ export function ModelEditSubmenu({
               <Switch
                 checked={thinkingOn}
                 className="ml-auto"
-                onCheckedChange={checked => void patchReasoning(checked ? effortValue || 'medium' : 'none')}
+                onCheckedChange={checked =>
+                  void patchReasoning(checked ? effort || 'medium' : 'none', currentReasoningEffort)
+                }
                 size="xs"
               />
             </DropdownMenuItem>
@@ -207,7 +205,10 @@ export function ModelEditSubmenu({
             <>
               <DropdownMenuSeparator className="mx-0" />
               <DropdownMenuLabel className={dropdownMenuSectionLabel}>{copy.effort}</DropdownMenuLabel>
-              <DropdownMenuRadioGroup onValueChange={value => void patchReasoning(value)} value={effortValue}>
+              <DropdownMenuRadioGroup
+                onValueChange={value => void patchReasoning(value, currentReasoningEffort)}
+                value={effort}
+              >
                 {EFFORT_OPTIONS.map(option => (
                   <DropdownMenuRadioItem
                     className={dropdownMenuRow}

apps/desktop/src/app/shell/model-menu-panel.tsx

@@ -1,6 +1,6 @@
 import { useStore } from '@nanostores/react'
 import { useQuery } from '@tanstack/react-query'
-import { createContext, useContext, useMemo, useState } from 'react'
+import { useMemo, useState } from 'react'
 
 import { Codicon } from '@/components/ui/codicon'
 import {
@@ -18,9 +18,8 @@ import { Skeleton } from '@/components/ui/skeleton'
 import type { HermesGateway } from '@/hermes'
 import { getGlobalModelOptions } from '@/hermes'
 import { useI18n } from '@/i18n'
-import { currentPickerSelection, displayModelName, modelDisplayParts, reasoningEffortLabel } from '@/lib/model-status-label'
+import { displayModelName, modelDisplayParts, reasoningEffortLabel } from '@/lib/model-status-label'
 import { cn } from '@/lib/utils'
-import { $modelPresets, applyModelPreset, modelPresetKey } from '@/store/model-presets'
 import {
   $visibleModels,
   collapseModelFamilies,
@@ -41,14 +40,9 @@ import type { ModelOptionProvider, ModelOptionsResponse } from '@/types/hermes'
 
 import { ModelEditSubmenu, resolveFastControl } from './model-edit-submenu'
 
-// Lets the host dropdown (model-pill) hand the panel a way to dismiss itself so
-// clicking a model row commits + closes, while the hover-revealed edit submenu
-// (reasoning/fast) stays open to play with (its items preventDefault on select).
-export const ModelMenuCloseContext = createContext<() => void>(() => {})
-
 interface ModelMenuPanelProps {
   gateway?: HermesGateway
-  onSelectModel: (selection: { model: string; provider: string }) => Promise<boolean> | void
+  onSelectModel: (selection: { model: string; persistGlobal: boolean; provider: string }) => Promise<boolean> | void
   requestGateway: <T>(method: string, params?: Record<string, unknown>) => Promise<T>
 }
 
@@ -60,7 +54,6 @@ interface ProviderGroup {
 export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: ModelMenuPanelProps) {
   const { t } = useI18n()
   const copy = t.shell.modelMenu
-  const closeMenu = useContext(ModelMenuCloseContext)
   const [search, setSearch] = useState('')
   // Reactive session state is read from the stores here (not drilled in), so
   // toggling effort/fast/model re-renders this panel in place without forcing
@@ -70,7 +63,6 @@ export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: Model
   const currentModel = useStore($currentModel)
   const currentProvider = useStore($currentProvider)
   const currentReasoningEffort = useStore($currentReasoningEffort)
-  const modelPresets = useStore($modelPresets)
   const visibleModels = useStore($visibleModels)
 
   const modelOptions = useQuery({
@@ -84,12 +76,8 @@ export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: Model
     }
   })
 
-  const { model: optionsModel, provider: optionsProvider } = currentPickerSelection(
-    !!activeSessionId,
-    { model: currentModel, provider: currentProvider },
-    modelOptions.data
-  )
-
+  const optionsModel = String(modelOptions.data?.model ?? currentModel ?? '')
+  const optionsProvider = String(modelOptions.data?.provider ?? currentProvider ?? '')
   const loading = modelOptions.isPending && !modelOptions.data
 
   const error = modelOptions.error
@@ -99,41 +87,13 @@ export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: Model
     : null
 
   const providers = modelOptions.data?.providers
-
   const effectiveVisibleModels = useMemo(
     () => effectiveVisibleKeys(visibleModels, providers ?? []),
     [visibleModels, providers]
   )
 
-  // The composer picker never persists the profile default. With a session it
-  // scopes the switch to that session; with none it's UI state shipped on the
-  // next session.create (see selectModel). The default lives in Settings → Model.
-  const switchTo = (model: string, provider: string) => onSelectModel({ model, provider })
-
-  // Selecting a model row restores that model's remembered preset onto the
-  // session (effort/fast), gated by capability. Unset → Hermes defaults.
-  const selectFamily = async (family: ModelFamily, provider: ModelOptionProvider) => {
-    const caps = provider.capabilities?.[family.id]
-    const preset = modelPresets[modelPresetKey(provider.slug, family.id)] ?? {}
-
-    // Variant-fast models (no speed param) express "fast" as a separate `-fast`
-    // id, so honor the saved preset by selecting that sibling. Param-fast is
-    // applied via applyModelPreset below instead.
-    const variantFast = !(caps?.fast ?? false) && !!family.fastId
-    const targetId = variantFast && preset.fast === true ? family.fastId! : family.id
-
-    if ((await switchTo(targetId, provider.slug)) === false) {
-      return
-    }
-
-    await applyModelPreset(
-      {
-        effort: (caps?.reasoning ?? true) ? (preset.effort ?? 'medium') : undefined,
-        fast: (caps?.fast ?? false) ? (preset.fast ?? false) : undefined
-      },
-      { failMessage: t.shell.modelOptions.updateFailed, request: requestGateway, sessionId: activeSessionId }
-    )
-  }
+  const switchTo = (model: string, provider: string) =>
+    onSelectModel({ model, persistGlobal: !activeSessionId, provider })
 
   const groups = useMemo(
     () => groupModels(providers ?? [], search, { model: optionsModel, provider: optionsProvider }, effectiveVisibleModels),
@@ -192,42 +152,37 @@ export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: Model
                 // -fast variant carries the same param support as its base.
                 const caps = group.provider.capabilities?.[family.id]
 
-                // Effective settings for this row: live session state when it's
-                // the active model, otherwise its remembered preset (Hermes
-                // defaults when unset). Row label AND submenu read from these so
-                // they never disagree.
-                const preset = modelPresets[modelPresetKey(group.provider.slug, family.id)] ?? {}
-                const effEffort = isCurrent ? currentReasoningEffort : preset.effort ?? ''
-                const effFast = isCurrent ? currentFastMode : preset.fast ?? false
-
+                // Single source of truth for the active row's fast state — keeps
+                // the row label in lock-step with the submenu's Fast toggle and
+                // handles the standalone `-fast` id case.
                 const fastControl = resolveFastControl(
                   activeId ?? family.id,
                   group.provider.models ?? [],
                   caps?.fast ?? false,
-                  effFast
+                  currentFastMode
                 )
 
-                const meta = [
-                  fastControl.kind !== 'none' && fastControl.on ? copy.fast : null,
-                  (caps?.reasoning ?? true) ? reasoningEffortLabel(effEffort) || copy.medium : null
-                ]
-                  .filter(Boolean)
-                  .join(' ')
+                // Grayed text is live session state only. Do not label inactive
+                // rows as "Fast" just because they have a fast-capable sibling:
+                // that makes an off Fast toggle look like it is already on.
+                const meta = isCurrent
+                  ? [
+                      fastControl.kind !== 'none' && fastControl.on ? copy.fast : null,
+                      reasoningEffortLabel(currentReasoningEffort) || copy.medium
+                    ]
+                      .filter(Boolean)
+                      .join(' ')
+                  : ''
 
                 // Every row is a hover-Edit submenu trigger. Activating it
-                // (pointer or keyboard) switches to the family's base model and
-                // restores its preset; the Fast toggle inside swaps to the -fast
-                // sibling (or flips the speed param). The sub-trigger has no
-                // `onSelect`, so wire both click and Enter/Space for keyboard parity.
-                // Clicking the row commits the model and closes the picker; the
-                // edit submenu (reasoning/fast) is reached by HOVER, so you can
-                // still tweak those without the click dismissing everything.
+                // (pointer or keyboard) switches to the family's base model;
+                // the Fast toggle inside swaps to the -fast sibling (or flips
+                // the speed param). The sub-trigger has no `onSelect`, so wire
+                // both click and Enter/Space for keyboard parity.
                 const activate = () => {
                   if (!isCurrent) {
-                    void selectFamily(family, group.provider)
+                    void switchTo(family.id, group.provider.slug)
                   }
-
-                  closeMenu()
                 }
 
                 return (
@@ -249,12 +204,10 @@ export function ModelMenuPanel({ gateway, onSelectModel, requestGateway }: Model
                       {isCurrent ? <Codicon className="ml-auto text-foreground" name="check" size="0.75rem" /> : null}
                     </DropdownMenuSubTrigger>
                     <ModelEditSubmenu
-                      effort={effEffort}
                       fastControl={fastControl}
                       isActive={isCurrent}
-                      model={family.id}
+                      onActivate={() => switchTo(family.id, group.provider.slug)}
                       onSelectModel={nextModel => switchTo(nextModel, group.provider.slug)}
-                      provider={group.provider.slug}
                       reasoning={caps?.reasoning ?? true}
                       requestGateway={requestGateway}
                     />

apps/desktop/src/app/types.ts

@@ -46,12 +46,6 @@ export interface SlashExecResponse {
   warning?: string
 }
 
-export interface BrowserManageResponse {
-  connected?: boolean
-  url?: string
-  messages?: string[]
-}
-
 export interface SessionSteerResponse {
   // 'queued' == accepted into the live turn's steer slot (injected at the next
   // tool-result boundary); 'rejected' == no live tool window, caller queues.

apps/desktop/src/components/assistant-ui/thread-list.tsx

@@ -1,6 +1,5 @@
 import { ThreadPrimitive, useAuiEvent, useAuiState } from '@assistant-ui/react'
 import {
-  type CSSProperties,
   type ComponentProps,
   type FC,
   memo,
@@ -22,7 +21,6 @@ import {
   resetThreadScroll,
   setThreadAtBottom
 } from '@/store/thread-scroll'
-import { isSecondaryWindow } from '@/store/windows'
 
 import { MessageRenderBoundary } from './message-render-boundary'
 
@@ -134,20 +132,6 @@ const ThreadMessageListInner: FC<ThreadMessageListProps> = ({
   const hiddenCount = firstVisible
   const visibleGroups = hiddenCount > 0 ? groups.slice(hiddenCount) : groups
   const restoreFromBottomRef = useRef<number | null>(null)
-  // Secondary windows (new-session scratch, subagent watch, cmd-click pop-out)
-  // hide the titlebar tool cluster + session header, but the OS traffic lights
-  // still sit in the top-left, so reserve the titlebar gap above the transcript.
-  const secondaryWindow = isSecondaryWindow()
-  // NB: CSS calc() requires whitespace around the +/- operator. This string is
-  // assigned verbatim to the --sticky-human-top inline style below (it does not
-  // go through Tailwind, which would auto-space it), so the spaces are load-
-  // bearing — without them the declaration is invalid, gets dropped, and the
-  // sticky user bubble falls back to its ~4px default and slides under the OS
-  // traffic lights.
-  const secondaryTitlebarGap = 'calc(var(--titlebar-height) + 0.75rem)'
-  const threadContentTopPad = secondaryWindow
-    ? 'pt-[calc(var(--titlebar-height)+0.75rem)]'
-    : 'pt-[calc(var(--titlebar-height)-0.5rem)]'
 
   useEffect(() => setThreadAtBottom(isAtBottom), [isAtBottom])
   useEffect(() => () => resetThreadScroll(), [])
@@ -251,24 +235,8 @@ const ThreadMessageListInner: FC<ThreadMessageListProps> = ({
   return (
     <div
       className="relative min-h-0 max-w-full overflow-hidden contain-[layout_paint]"
-      style={
-        {
-          height: clampToComposer ? 'var(--thread-viewport-height)' : '100%',
-          ...(secondaryWindow ? { '--sticky-human-top': secondaryTitlebarGap } : {})
-        } as CSSProperties
-      }
+      style={{ height: clampToComposer ? 'var(--thread-viewport-height)' : '100%' }}
     >
-      {secondaryWindow && (
-        // Secondary windows hide the titlebar chrome, so the scroller runs to
-        // the window's top edge and streamed text slides up under the OS
-        // traffic lights. Content padding alone scrolls away with the text — a
-        // fixed opaque strip (the titlebar's drag region) masks anything behind
-        // it and keeps the window draggable, matching the main window's header.
-        <div
-          aria-hidden="true"
-          className="absolute inset-x-0 top-0 z-10 h-(--titlebar-height) bg-background [-webkit-app-region:drag]"
-        />
-      )}
       <div
         className="size-full overflow-x-hidden overflow-y-auto overscroll-contain"
         data-following={isAtBottom ? 'true' : 'false'}
@@ -284,7 +252,9 @@ const ThreadMessageListInner: FC<ThreadMessageListProps> = ({
           </div>
         ) : (
           <div
-            className={cn('mx-auto flex w-full max-w-(--composer-width) min-w-0 flex-col px-6', threadContentTopPad)}
+            className={cn(
+              'mx-auto flex w-full max-w-(--composer-width) min-w-0 flex-col px-6 pt-[calc(var(--titlebar-height)+1.5rem)]'
+            )}
             data-slot="aui_thread-content"
             ref={contentRef as React.RefCallback<HTMLDivElement>}
           >

apps/desktop/src/components/model-picker.tsx

@@ -2,7 +2,6 @@ import { useQuery } from '@tanstack/react-query'
 import { useState } from 'react'
 
 import { useI18n } from '@/i18n'
-import { currentPickerSelection } from '@/lib/model-status-label'
 import type { ModelOptionProvider, ModelOptionsResponse, ModelPricing } from '@/types/hermes'
 
 import type { HermesGateway } from '../hermes'
@@ -12,6 +11,7 @@ import { startManualOnboarding } from '../store/onboarding'
 
 import { InlineNotice } from './notifications'
 import { Button } from './ui/button'
+import { Checkbox } from './ui/checkbox'
 import { Command, CommandEmpty, CommandGroup, CommandInput, CommandItem, CommandList } from './ui/command'
 import { Dialog, DialogContent, DialogDescription, DialogFooter, DialogHeader, DialogTitle } from './ui/dialog'
 import { Skeleton } from './ui/skeleton'
@@ -23,7 +23,7 @@ interface ModelPickerDialogProps {
   sessionId?: string | null
   currentModel: string
   currentProvider: string
-  onSelect: (selection: { provider: string; model: string }) => void
+  onSelect: (selection: { provider: string; model: string; persistGlobal: boolean }) => void
   /**
    * Optional class to apply to DialogContent. Use to override z-index when
    * stacking the picker on top of another fixed overlay (e.g. the desktop
@@ -45,6 +45,7 @@ export function ModelPickerDialog({
 }: ModelPickerDialogProps) {
   const { t } = useI18n()
   const copy = t.modelPicker
+  const [persistGlobal, setPersistGlobal] = useState(!sessionId)
   // Own the search term so we can filter manually. cmdk's built-in
   // shouldFilter reorders items by its fuzzy-match score (≈alphabetical with
   // an empty query), which destroys the backend's curated order. We disable
@@ -67,13 +68,8 @@ export function ModelPickerDialog({
   })
 
   const providers = modelOptions.data?.providers ?? []
-
-  const { model: optionsModel, provider: optionsProvider } = currentPickerSelection(
-    !!sessionId,
-    { model: currentModel, provider: currentProvider },
-    modelOptions.data
-  )
-
+  const optionsModel = String(modelOptions.data?.model ?? currentModel ?? '')
+  const optionsProvider = String(modelOptions.data?.provider ?? currentProvider ?? '')
   const loading = modelOptions.isPending && !modelOptions.data
 
   const error = modelOptions.error
@@ -83,7 +79,11 @@ export function ModelPickerDialog({
     : null
 
   const selectModel = (provider: ModelOptionProvider, model: string) => {
-    onSelect({ provider: provider.slug, model })
+    onSelect({
+      provider: provider.slug,
+      model,
+      persistGlobal: persistGlobal || !sessionId
+    })
     onOpenChange(false)
   }
 
@@ -128,13 +128,24 @@ export function ModelPickerDialog({
           </CommandList>
         </Command>
 
-        <DialogFooter className="flex-row items-center justify-end gap-2 bg-card p-3">
-          <Button onClick={addProvider} variant="ghost">
-            {copy.addProvider}
-          </Button>
-          <Button onClick={() => onOpenChange(false)} variant="outline">
-            {t.common.cancel}
-          </Button>
+        <DialogFooter className="flex-row items-center justify-between gap-3 bg-card p-3 sm:justify-between">
+          <label className="flex cursor-pointer select-none items-center gap-2 text-xs text-muted-foreground">
+            <Checkbox
+              checked={persistGlobal || !sessionId}
+              disabled={!sessionId}
+              onCheckedChange={checked => setPersistGlobal(checked === true)}
+            />
+            {sessionId ? copy.persistGlobalSession : copy.persistGlobal}
+          </label>
+
+          <div className="flex items-center gap-2">
+            <Button onClick={addProvider} variant="ghost">
+              {copy.addProvider}
+            </Button>
+            <Button onClick={() => onOpenChange(false)} variant="outline">
+              {t.common.cancel}
+            </Button>
+          </div>
         </DialogFooter>
       </DialogContent>
     </Dialog>

apps/desktop/src/global.d.ts

@@ -24,8 +24,6 @@ declare global {
       // a spectator window (lazy resume — no agent build) for live-streaming
       // a running subagent's session.
       openSessionWindow: (sessionId: string, opts?: { watch?: boolean }) => Promise<{ ok: boolean; error?: string }>
-      // Open (or focus) a compact secondary window on the new-session draft.
-      openNewSessionWindow: () => Promise<{ ok: boolean; error?: string }>
       getBootProgress: () => Promise<DesktopBootProgress>
       getConnectionConfig: (profile?: null | string) => Promise<DesktopConnectionConfig>
       saveConnectionConfig: (payload: DesktopConnectionConfigInput) => Promise<DesktopConnectionConfig>

apps/desktop/src/i18n/en.ts

@@ -189,7 +189,6 @@ export const en: Translations = {
       'nav.cron': 'Open scheduled jobs',
       'nav.agents': 'Open agents',
       'session.new': 'New session',
-      'session.newWindow': 'New session in window',
       'session.next': 'Next session',
       'session.prev': 'Previous session',
       'session.slot.1': 'Switch to recent session 1',
@@ -538,10 +537,6 @@ export const en: Translations = {
       provider: 'Provider',
       model: 'Model',
       applying: 'Applying...',
-      defaultsLabel: 'Defaults',
-      reasoning: 'Reasoning',
-      reasoningOff: 'Off',
-      defaultsFailed: 'Failed to save model defaults',
       auxiliaryTitle: 'Auxiliary models',
       resetAllToMain: 'Reset all to main',
       auxiliaryDesc: 'Helper tasks run on the main model by default. Assign a dedicated model to any task to override.',
@@ -569,14 +564,9 @@ export const en: Translations = {
       collapse: 'Collapse',
       connectAnother: 'Connect another provider',
       otherProviders: 'Other providers',
-      disconnect: 'Disconnect',
-      disconnectInTerminal: 'Disconnect (runs the removal command in the terminal)',
       removeConfirm: provider => `Remove ${provider}?`,
-      removeExternalGeneric: provider => `${provider} is managed by its own CLI — remove it there.`,
+      removeExternal: (provider, command) => `${provider} is managed outside Hermes. Remove it with ${command}.`,
       removeKeyManaged: provider => `${provider} is configured from an API key. Remove it from API Keys.`,
-      removeTerminalConfirm: (provider, command) =>
-        `Disconnect ${provider}? This runs "${command}" in the terminal to clear the credential.`,
-      removeTerminalRunning: provider => `Running ${provider} disconnect in the terminal…`,
       removedTitle: 'Account removed',
       removedMessage: provider => `${provider} was removed.`,
       failedRemove: provider => `Could not remove ${provider}`,
@@ -1507,6 +1497,8 @@ export const en: Translations = {
     unknown: '(unknown)',
     search: 'Filter providers and models...',
     noModels: 'No models found.',
+    persistGlobalSession: 'Persist globally (otherwise this session only)',
+    persistGlobal: 'Persist globally',
     addProvider: 'Add provider',
     loadFailed: 'Could not load models',
     noAuthenticatedProviders: 'No authenticated providers.',

apps/desktop/src/i18n/ja.ts

@@ -695,6 +695,7 @@ export const ja = defineLocale({
       connectAnother: '別のプロバイダーを接続',
       otherProviders: 'その他のプロバイダー',
       removeConfirm: provider => `${provider} を削除しますか？`,
+      removeExternal: (provider, command) => `${provider} は Hermes の外部で管理されています。${command} で削除してください。`,
       removeKeyManaged: provider => `${provider} は API キーで設定されています。API Keys から削除してください。`,
       removedTitle: 'アカウントを削除しました',
       removedMessage: provider => `${provider} を削除しました。`,
@@ -1637,6 +1638,8 @@ export const ja = defineLocale({
     unknown: '(不明)',
     search: 'プロバイダーとモデルをフィルター...',
     noModels: 'モデルが見つかりません。',
+    persistGlobalSession: 'グローバルに保持（それ以外はこのセッションのみ）',
+    persistGlobal: 'グローバルに保持',
     addProvider: 'プロバイダーを追加',
     loadFailed: 'モデルを読み込めませんでした',
     noAuthenticatedProviders: '認証済みプロバイダーがありません。',

apps/desktop/src/i18n/types.ts

@@ -430,10 +430,6 @@ export interface Translations {
       provider: string
       model: string
       applying: string
-      defaultsLabel: string
-      reasoning: string
-      reasoningOff: string
-      defaultsFailed: string
       auxiliaryTitle: string
       resetAllToMain: string
       auxiliaryDesc: string
@@ -451,13 +447,9 @@ export interface Translations {
       collapse: string
       connectAnother: string
       otherProviders: string
-      disconnect: string
-      disconnectInTerminal: string
       removeConfirm: (provider: string) => string
-      removeExternalGeneric: (provider: string) => string
+      removeExternal: (provider: string, command: string) => string
       removeKeyManaged: (provider: string) => string
-      removeTerminalConfirm: (provider: string, command: string) => string
-      removeTerminalRunning: (provider: string) => string
       removedTitle: string
       removedMessage: (provider: string) => string
       failedRemove: (provider: string) => string
@@ -1149,6 +1141,8 @@ export interface Translations {
     unknown: string
     search: string
     noModels: string
+    persistGlobalSession: string
+    persistGlobal: string
     addProvider: string
     loadFailed: string
     noAuthenticatedProviders: string

apps/desktop/src/i18n/zh-hant.ts

@@ -672,6 +672,7 @@ export const zhHant = defineLocale({
       connectAnother: '連結其他提供方',
       otherProviders: '其他提供方',
       removeConfirm: provider => `移除 ${provider}？`,
+      removeExternal: (provider, command) => `${provider} 由 Hermes 外部管理。請使用 ${command} 移除。`,
       removeKeyManaged: provider => `${provider} 由 API 金鑰設定。請從 API Keys 中移除。`,
       removedTitle: '帳號已移除',
       removedMessage: provider => `${provider} 已移除。`,
@@ -1581,6 +1582,8 @@ export const zhHant = defineLocale({
     unknown: '（未知）',
     search: '篩選提供方和模型...',
     noModels: '找不到模型。',
+    persistGlobalSession: '全域儲存（否則僅限此工作階段）',
+    persistGlobal: '全域儲存',
     addProvider: '新增提供方',
     loadFailed: '無法載入模型',
     noAuthenticatedProviders: '沒有已驗證的提供方。',

apps/desktop/src/i18n/zh.ts

@@ -185,7 +185,6 @@ export const zh: Translations = {
       'nav.cron': '打开定时任务',
       'nav.agents': '打开智能体',
       'session.new': '新建会话',
-      'session.newWindow': '在新窗口中新建会话',
       'session.next': '下一个会话',
       'session.prev': '上一个会话',
       'session.slot.1': '切换到最近会话 1',
@@ -733,10 +732,6 @@ export const zh: Translations = {
       provider: '提供方',
       model: '模型',
       applying: '应用中...',
-      defaultsLabel: '默认值',
-      reasoning: '推理',
-      reasoningOff: '关闭',
-      defaultsFailed: '保存模型默认值失败',
       auxiliaryTitle: '辅助模型',
       resetAllToMain: '全部重置为主模型',
       auxiliaryDesc: '辅助任务默认使用主模型。你可以为任意任务指定专用模型。',
@@ -763,13 +758,9 @@ export const zh: Translations = {
       collapse: '收起',
       connectAnother: '连接其他提供方',
       otherProviders: '其他提供方',
-      disconnect: '断开连接',
-      disconnectInTerminal: '断开连接（在终端中运行移除命令）',
       removeConfirm: provider => `移除 ${provider}？`,
-      removeExternalGeneric: provider => `${provider} 由其自身的 CLI 管理 — 请在那里移除。`,
+      removeExternal: (provider, command) => `${provider} 由 Hermes 外部管理。请使用 ${command} 移除。`,
       removeKeyManaged: provider => `${provider} 由 API 密钥配置。请从 API Keys 中移除。`,
-      removeTerminalConfirm: (provider, command) => `断开 ${provider}？这将在终端中运行 "${command}" 以清除凭据。`,
-      removeTerminalRunning: provider => `正在终端中断开 ${provider}…`,
       removedTitle: '账号已移除',
       removedMessage: provider => `${provider} 已移除。`,
       failedRemove: provider => `无法移除 ${provider}`,
@@ -1687,6 +1678,8 @@ export const zh: Translations = {
     unknown: '(未知)',
     search: '筛选提供方和模型...',
     noModels: '未找到模型。',
+    persistGlobalSession: '全局保存 (否则仅当前会话)',
+    persistGlobal: '全局保存',
     addProvider: '添加提供方',
     loadFailed: '无法加载模型',
     noAuthenticatedProviders: '没有已认证的提供方。',

apps/desktop/src/lib/chat-messages.test.ts

@@ -3,7 +3,6 @@ import { describe, expect, it } from 'vitest'
 import type { ChatMessage, ChatMessagePart } from './chat-messages'
 import {
   appendAssistantTextPart,
-  appendReasoningPart,
   chatMessageText,
   preserveLocalAssistantErrors,
   renderMediaTags,
@@ -176,52 +175,6 @@ describe('renderMediaTags', () => {
   })
 })
 
-describe('interleaved reasoning/text coalescing', () => {
-  it('keeps narration contiguous when reasoning interrupts mid-sentence', () => {
-    // Models that interleave reasoning_content + content deltas emit
-    // text → reasoning → text within one tool-bounded segment. The two text
-    // fragments are really one sentence and must not be split by the
-    // "Thinking" block between them.
-    let parts: ChatMessagePart[] = appendAssistantTextPart([], 'Let me ')
-    parts = appendReasoningPart(parts, 'checking the file...')
-    parts = appendAssistantTextPart(parts, 'verify the full file is correct:')
-
-    expect(parts.map(p => p.type)).toEqual(['text', 'reasoning'])
-    expect((parts[0] as { text: string }).text).toBe('Let me verify the full file is correct:')
-    expect((parts[1] as { text: string }).text).toBe('checking the file...')
-  })
-
-  it('merges reasoning bursts that straddle a narration fragment', () => {
-    let parts: ChatMessagePart[] = appendReasoningPart([], 'first thought ')
-    parts = appendAssistantTextPart(parts, 'Working on it.')
-    parts = appendReasoningPart(parts, 'second thought')
-
-    expect(parts.map(p => p.type)).toEqual(['reasoning', 'text'])
-    expect((parts[0] as { text: string }).text).toBe('first thought second thought')
-    expect((parts[1] as { text: string }).text).toBe('Working on it.')
-  })
-
-  it('starts a fresh text part after a tool call (segment boundary)', () => {
-    let parts: ChatMessagePart[] = appendAssistantTextPart([], 'Let me check.')
-    parts = upsertToolPart(parts, { name: 'read_file', tool_id: 'tc-1' }, 'running')
-    parts = appendAssistantTextPart(parts, 'Now editing.')
-
-    expect(parts.map(p => p.type)).toEqual(['text', 'tool-call', 'text'])
-    expect((parts[0] as { text: string }).text).toBe('Let me check.')
-    expect((parts[2] as { text: string }).text).toBe('Now editing.')
-  })
-
-  it('does not merge reasoning across a tool call', () => {
-    let parts: ChatMessagePart[] = appendReasoningPart([], 'before tool')
-    parts = upsertToolPart(parts, { name: 'read_file', tool_id: 'tc-1' }, 'running')
-    parts = appendReasoningPart(parts, 'after tool')
-
-    expect(parts.map(p => p.type)).toEqual(['reasoning', 'tool-call', 'reasoning'])
-    expect((parts[0] as { text: string }).text).toBe('before tool')
-    expect((parts[2] as { text: string }).text).toBe('after tool')
-  })
-})
-
 describe('preserveLocalAssistantErrors', () => {
   it('preserves a local user+error pair when hydration omits the failed turn', () => {
     const nextMessages: ChatMessage[] = [

apps/desktop/src/lib/chat-messages.ts

@@ -178,74 +178,54 @@ function displayContentForMessage(role: SessionMessage['role'], content: unknown
   return [refs.join('\n'), visibleText].filter(Boolean).join('\n\n') || visibleText
 }
 
-const STREAM_PART: Record<'reasoning' | 'text', (text: string) => ChatMessagePart> = {
-  reasoning: reasoningPart,
-  text: textPart
-}
-
-// Coalesce a streaming delta into the most recent same-type part within the
-// current segment, where a segment is bounded by any non-streaming part (a
-// tool call, image, …). The opposite streaming channel (text <-> reasoning) is
-// transparent, so a reasoning burst between two content deltas can't shred one
-// sentence into text / Thinking / text — the fragmentation models that
-// interleave reasoning_content + content otherwise produce. Tool calls still
-// open a fresh part, preserving narration order across steps.
-function appendStreamPart(
-  parts: ChatMessagePart[],
-  type: 'reasoning' | 'text',
-  delta: string
-): { index: number; parts: ChatMessagePart[] } {
-  const next = [...parts]
-
-  for (let i = next.length - 1; i >= 0; i--) {
-    const part = next[i]
-
-    if (part.type === type) {
-      next[i] = { ...part, text: `${(part as { text: string }).text}${delta}` } as ChatMessagePart
-
-      return { index: i, parts: next }
-    }
-
-    if (part.type !== 'text' && part.type !== 'reasoning') {
-      break
-    }
-  }
-
-  next.push(STREAM_PART[type](delta))
-
-  return { index: next.length - 1, parts: next }
-}
-
 export function appendTextPart(parts: ChatMessagePart[], delta: string): ChatMessagePart[] {
-  return appendStreamPart(parts, 'text', delta).parts
-}
+  const next = [...parts]
+  const last = next.at(-1)
 
-export function appendReasoningPart(parts: ChatMessagePart[], delta: string): ChatMessagePart[] {
-  return appendStreamPart(parts, 'reasoning', delta).parts
-}
+  if (last?.type === 'text') {
+    next[next.length - 1] = { ...last, text: `${last.text}${delta}` }
 
-export function appendAssistantTextPart(parts: ChatMessagePart[], delta: string): ChatMessagePart[] {
-  const { index, parts: next } = appendStreamPart(parts, 'text', delta)
-  const part = next[index]
-
-  if (part?.type !== 'text') {
     return next
   }
 
-  const mayContainMedia =
-    delta.includes('MEDIA:') || delta.includes('DIA:') || delta.includes('EDIA:') || delta.includes('IA:')
+  next.push(textPart(delta))
 
-  if (mayContainMedia || part.text.includes('MEDIA:')) {
-    const rendered = renderMediaTags(part.text)
+  return next
+}
 
-    if (rendered !== part.text) {
-      next[index] = { ...part, text: rendered }
-    }
+export function appendAssistantTextPart(parts: ChatMessagePart[], delta: string): ChatMessagePart[] {
+  const next = appendTextPart(parts, delta)
+  const last = next.at(-1)
+
+  if (last?.type === 'text') {
+    const current = last.text
+
+    const deltaMayContainMedia =
+      delta.includes('MEDIA:') || delta.includes('DIA:') || delta.includes('EDIA:') || delta.includes('IA:')
+
+    const needsMediaPass = deltaMayContainMedia || current.includes('MEDIA:')
+    const nextText = needsMediaPass ? renderMediaTags(current) : current
+    next[next.length - 1] = nextText === current ? last : { ...last, text: nextText }
   }
 
   return next
 }
 
+export function appendReasoningPart(parts: ChatMessagePart[], delta: string): ChatMessagePart[] {
+  const next = [...parts]
+  const last = next.at(-1)
+
+  if (last?.type === 'reasoning') {
+    next[next.length - 1] = { ...last, text: `${last.text}${delta}` }
+
+    return next
+  }
+
+  next.push(reasoningPart(delta))
+
+  return next
+}
+
 export function hasToolPart(message: ChatMessage): boolean {
   return message.parts.some(part => part.type === 'tool-call')
 }

apps/desktop/src/lib/desktop-slash-commands.test.ts

@@ -52,17 +52,6 @@ describe('desktop slash command curation', () => {
     expect(desktopSlashUnavailableMessage('/personality')).toBeNull()
   })
 
-  it('treats /browser as an executable action command (local-gateway connect)', () => {
-    // /browser used to be terminal-only; it now resolves to a desktop action
-    // handler that routes browser.manage RPC when the gateway is local.
-    expect(isDesktopSlashCommand('/browser')).toBe(true)
-    expect(isDesktopSlashSuggestion('/browser')).toBe(true)
-    expect(desktopSlashUnavailableMessage('/browser')).toBeNull()
-    expect(resolveDesktopCommand('/browser')?.surface).toEqual({ kind: 'action', action: 'browser' })
-    // Bare /browser expands to its sub-action options in the popover.
-    expect(resolveDesktopCommand('/browser')?.args).toBe(true)
-  })
-
   it('allows aliases to execute without cluttering the popover', () => {
     expect(isDesktopSlashSuggestion('/reset')).toBe(false)
     expect(isDesktopSlashCommand('/reset')).toBe(true)

apps/desktop/src/lib/desktop-slash-commands.ts

@@ -30,7 +30,6 @@ export interface DesktopThemeCommandOption {
  */
 export type DesktopActionId =
   | 'branch'
-  | 'browser'
   | 'handoff'
   | 'help'
   | 'new'
@@ -104,12 +103,6 @@ const DESKTOP_COMMAND_SPECS: readonly DesktopCommandSpec[] = [
   { name: '/skin', description: 'Switch desktop theme or cycle to the next one', surface: action('skin'), args: true },
   { name: '/title', description: 'Rename the current session', surface: action('title') },
   { name: '/help', description: 'Show desktop slash commands', aliases: ['/commands'], surface: action('help') },
-  {
-    name: '/browser',
-    description: 'Manage browser CDP connection [connect|disconnect|status] (local gateway only)',
-    surface: action('browser'),
-    args: true
-  },
 
   // Overlay pickers
   { name: '/model', description: 'Switch the model for this session', surface: picker('model'), hidden: true },
@@ -149,7 +142,7 @@ const DESKTOP_COMMAND_SPECS: readonly DesktopCommandSpec[] = [
 // per reason beats 40 identical object literals.
 const NO_DESKTOP_SURFACE: Record<DesktopUnavailableReason, readonly string[]> = {
   terminal: [
-    '/busy', '/clear', '/compact', '/config', '/copy', '/cron', '/details',
+    '/browser', '/busy', '/clear', '/compact', '/config', '/copy', '/cron', '/details',
     '/exit', '/footer', '/gateway', '/gquota', '/history', '/image', '/indicator', '/logs',
     '/mouse', '/paste', '/platforms', '/plugins', '/quit', '/redraw', '/reload', '/restart',
     '/sb', '/set-home', '/sethome', '/snap', '/snapshot', '/statusbar', '/toolsets', '/update', '/verbose'

apps/desktop/src/lib/keybinds/actions.ts

@@ -66,7 +66,6 @@ export const KEYBIND_ACTIONS: readonly KeybindActionMeta[] = [
 
   // ── Session ──────────────────────────────────────────────────────────────
   { id: 'session.new', category: 'session', defaults: ['mod+n', 'shift+n'] },
-  { id: 'session.newWindow', category: 'session', defaults: ['mod+shift+n'] },
   // ⌃Tab / ⌃⇧Tab — the universal tab-cycle chord. Literally Control, not Cmd
   // (macOS reserves Cmd+Tab for app switching); see `ctrl` in combo.ts.
   { id: 'session.next', category: 'session', defaults: ['ctrl+tab'] },

apps/desktop/src/lib/media.remote.test.ts

@@ -2,7 +2,7 @@ import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
 
 import { $connection } from '@/store/session'
 
-import { filePathFromMediaPath, gatewayMediaDataUrl, isRemoteGateway, mediaExternalUrl } from './media'
+import { filePathFromMediaPath, gatewayMediaDataUrl, isRemoteGateway } from './media'
 
 describe('isRemoteGateway', () => {
   afterEach(() => {
@@ -35,38 +35,6 @@ describe('filePathFromMediaPath', () => {
   })
 })
 
-describe('mediaExternalUrl', () => {
-  afterEach(() => {
-    $connection.set(null)
-  })
-
-  it('passes through http(s) URLs untouched', () => {
-    $connection.set({ mode: 'remote', baseUrl: 'https://gw', token: 't' } as never)
-    expect(mediaExternalUrl('https://example.com/a.png')).toBe('https://example.com/a.png')
-  })
-
-  it('keeps file:// form in local mode', () => {
-    $connection.set({ mode: 'local' } as never)
-    expect(mediaExternalUrl('/tmp/a.png')).toBe('file:///tmp/a.png')
-    expect(mediaExternalUrl('file:///tmp/a.png')).toBe('file:///tmp/a.png')
-  })
-
-  it('rewrites gateway-local paths to an authenticated download URL', () => {
-    $connection.set({ mode: 'remote', baseUrl: 'https://gw', token: 's e/cret' } as never)
-    expect(mediaExternalUrl('file:///tmp/a b.png')).toBe(
-      'https://gw/api/files/download?path=%2Ftmp%2Fa%20b.png&token=s%20e%2Fcret'
-    )
-    expect(mediaExternalUrl('/tmp/a b.png')).toBe(
-      'https://gw/api/files/download?path=%2Ftmp%2Fa%20b.png&token=s%20e%2Fcret'
-    )
-  })
-
-  it('falls back to file:// when remote connection lacks a token', () => {
-    $connection.set({ mode: 'remote', baseUrl: 'https://gw' } as never)
-    expect(mediaExternalUrl('/tmp/a.png')).toBe('file:///tmp/a.png')
-  })
-})
-
 describe('gatewayMediaDataUrl', () => {
   const api = vi.fn(async () => ({ data_url: 'data:image/png;base64,ZHVtbXk=' }))
 

apps/desktop/src/lib/media.ts

@@ -56,25 +56,8 @@ export function mediaMarkdownHref(path: string): string {
   return `#media:${encodeURIComponent(path)}`
 }
 
-// Resolve a media path to a URL the shell can open. Remote mode rewrites
-// gateway-local paths to an authenticated /api/files/download URL (the file
-// lives on the gateway, not this disk); local mode keeps the file:// form.
 export function mediaExternalUrl(path: string): string {
-  if (/^https?:/i.test(path)) {
-    return path
-  }
-
-  if (isRemoteGateway()) {
-    const conn = $connection.get()
-
-    if (conn?.baseUrl && conn.token) {
-      const file = encodeURIComponent(filePathFromMediaPath(path))
-
-      return `${conn.baseUrl}/api/files/download?path=${file}&token=${encodeURIComponent(conn.token)}`
-    }
-  }
-
-  return /^file:/i.test(path) ? path : `file://${path}`
+  return /^(?:https?|file):/i.test(path) ? path : `file://${path}`
 }
 
 // Custom Electron scheme (registered in electron/main.cjs) that streams a local

apps/desktop/src/lib/model-status-label.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect, it } from 'vitest'
 
-import { currentPickerSelection, displayModelName, formatModelStatusLabel, reasoningEffortLabel } from './model-status-label'
+import { displayModelName, formatModelStatusLabel, reasoningEffortLabel } from './model-status-label'
 
 describe('model-status-label', () => {
   it('formats display names consistently', () => {
@@ -10,11 +10,6 @@ describe('model-status-label', () => {
     expect(displayModelName('openai/gpt-5.5')).toBe('GPT-5.5')
   })
 
-  it('strips trailing date-pin snapshots from the display name', () => {
-    expect(displayModelName('claude-opus-4-5-20251101')).toBe('Opus 4 5')
-    expect(displayModelName('anthropic/claude-haiku-4-5-20251001')).toBe('Haiku 4 5')
-  })
-
   it('maps reasoning effort to compact labels', () => {
     expect(reasoningEffortLabel('high')).toBe('High')
     expect(reasoningEffortLabel('xhigh')).toBe('Max')
@@ -35,25 +30,4 @@ describe('model-status-label', () => {
   it('returns just the placeholder name when there is no model', () => {
     expect(formatModelStatusLabel('')).toBe('No model')
   })
-
-  describe('currentPickerSelection', () => {
-    const store = { model: 'opus', provider: 'anthropic' }
-    const options = { model: 'hermes-4', provider: 'nous' }
-
-    it('prefers the sticky composer pick over the profile default pre-session', () => {
-      expect(currentPickerSelection(false, store, options)).toEqual(store)
-    })
-
-    it('lets the live session model.options win when a session exists', () => {
-      expect(currentPickerSelection(true, store, options)).toEqual(options)
-    })
-
-    it('falls back to options when the store is empty', () => {
-      expect(currentPickerSelection(false, { model: '', provider: '' }, options)).toEqual(options)
-    })
-
-    it('falls back to the store while options are still loading', () => {
-      expect(currentPickerSelection(true, store, undefined)).toEqual(store)
-    })
-  })
 })

apps/desktop/src/lib/model-status-label.ts

@@ -17,22 +17,6 @@ export function reasoningEffortLabel(effort: string): string {
   return REASONING_LABELS[key] ?? effort
 }
 
-/** Which model/provider a picker should mark "current". With a live session the
- *  gateway's `model.options` is authoritative; pre-session there is no server
- *  "current", so the sticky composer pick wins over the profile default the
- *  global options query returns — else the checkmark snaps back to the default
- *  and the pick looks ignored. */
-export function currentPickerSelection(
-  hasSession: boolean,
-  store: { model: string; provider: string },
-  options?: { model?: string; provider?: string }
-): { model: string; provider: string } {
-  return {
-    model: String((hasSession && options?.model) || store.model || options?.model || ''),
-    provider: String((hasSession && options?.provider) || store.provider || options?.provider || '')
-  }
-}
-
 /** Strip provider prefix and normalize for display. */
 export function modelBaseId(model: string): string {
   const trimmed = model.trim()
@@ -84,9 +68,6 @@ export function modelDisplayParts(model: string): { name: string; tag: string }
     }
   }
 
-  // Drop a trailing date-pin (`…-20251101`) — snapshot noise, not a name.
-  base = base.replace(/-\d{8}$/, '')
-
   return { name: prettifyBase(base) || model.trim() || 'No model', tag }
 }
 

apps/desktop/src/store/model-presets.test.ts

@@ -1,51 +0,0 @@
-import { beforeEach, describe, expect, it } from 'vitest'
-
-import { $modelPresets, applyModelPreset, getModelPreset, modelPresetKey, setModelPreset } from './model-presets'
-
-describe('model presets', () => {
-  beforeEach(() => $modelPresets.set({}))
-
-  it('round-trips a preset and merges patches without dropping prior fields', () => {
-    setModelPreset('anthropic', 'claude-opus-4-8', { effort: 'high' })
-    setModelPreset('anthropic', 'claude-opus-4-8', { fast: true })
-
-    expect(getModelPreset('anthropic', 'claude-opus-4-8')).toEqual({ effort: 'high', fast: true })
-  })
-
-  it('returns an empty preset for unknown models', () => {
-    expect(getModelPreset('x', 'y')).toEqual({})
-  })
-
-  it('keys by provider::model', () => {
-    expect(modelPresetKey('openai', 'gpt-5.5')).toBe('openai::gpt-5.5')
-  })
-
-  it('pushes only the provided dimensions to the gateway', async () => {
-    const calls: { method: string; params?: Record<string, unknown> }[] = []
-
-    const request = async <T>(method: string, params?: Record<string, unknown>) => {
-      calls.push({ method, params })
-
-      return {} as T
-    }
-
-    await applyModelPreset({ effort: 'high' }, { failMessage: 'x', request, sessionId: 's1' })
-    await applyModelPreset({}, { failMessage: 'x', request, sessionId: 's1' })
-
-    expect(calls).toEqual([{ method: 'config.set', params: { key: 'reasoning', session_id: 's1', value: 'high' } }])
-  })
-
-  it('no-ops without a session so selecting a model cannot mutate global config', async () => {
-    const calls: { method: string; params?: Record<string, unknown> }[] = []
-
-    const request = async <T>(method: string, params?: Record<string, unknown>) => {
-      calls.push({ method, params })
-
-      return {} as T
-    }
-
-    await applyModelPreset({ effort: 'high', fast: true }, { failMessage: 'x', request, sessionId: null })
-
-    expect(calls).toEqual([])
-  })
-})

apps/desktop/src/store/model-presets.ts

@@ -1,86 +0,0 @@
-import { atom } from 'nanostores'
-
-import { persistString, storedString } from '@/lib/storage'
-
-import { notifyError } from './notifications'
-import { setCurrentFastMode, setCurrentReasoningEffort } from './session'
-
-const STORAGE_KEY = 'hermes.desktop.model-presets'
-
-/** Per-model reasoning/fast preset, remembered globally across sessions and
- *  re-applied to the session whenever that model is selected. Unset dimensions
- *  fall back to the Hermes default (medium effort, no fast). */
-export interface ModelPreset {
-  effort?: string
-  fast?: boolean
-}
-
-type RequestGateway = <T>(method: string, params?: Record<string, unknown>) => Promise<T>
-
-/** Stable `provider::model` key (matches the visibility-store format). */
-export const modelPresetKey = (provider: string, model: string): string => `${provider}::${model}`
-
-function load(): Record<string, ModelPreset> {
-  const raw = storedString(STORAGE_KEY)
-
-  if (!raw) {
-    return {}
-  }
-
-  try {
-    const parsed = JSON.parse(raw)
-
-    return parsed && typeof parsed === 'object' && !Array.isArray(parsed) ? (parsed as Record<string, ModelPreset>) : {}
-  } catch {
-    return {}
-  }
-}
-
-export const $modelPresets = atom<Record<string, ModelPreset>>(load())
-
-export function getModelPreset(provider: string, model: string): ModelPreset {
-  return $modelPresets.get()[modelPresetKey(provider, model)] ?? {}
-}
-
-/** Merge a partial preset for one model and persist. */
-export function setModelPreset(provider: string, model: string, patch: ModelPreset): void {
-  const key = modelPresetKey(provider, model)
-  const next = { ...$modelPresets.get(), [key]: { ...$modelPresets.get()[key], ...patch } }
-
-  $modelPresets.set(next)
-  persistString(STORAGE_KEY, JSON.stringify(next))
-}
-
-/** Push a model's preset onto the active session (optimistic + gateway).
- *  `undefined` skips that dimension; values are capability-gated upstream.
- *  No-ops without a session — the gateway's `config.set` reasoning/fast fall
- *  back to persistent (global/profile) config when none matches, so selecting
- *  a model must not reach it (else it rewrites `agent.*`, defaults included). */
-export async function applyModelPreset(
-  { effort, fast }: ModelPreset,
-  ctx: { failMessage: string; request: RequestGateway; sessionId: null | string }
-): Promise<void> {
-  if (!ctx.sessionId) {
-    return
-  }
-
-  if (effort !== undefined) {
-    setCurrentReasoningEffort(effort)
-  }
-
-  if (fast !== undefined) {
-    setCurrentFastMode(fast)
-  }
-
-  try {
-    if (effort !== undefined) {
-      await ctx.request('config.set', { key: 'reasoning', session_id: ctx.sessionId, value: effort })
-    }
-
-    if (fast !== undefined) {
-      await ctx.request('config.set', { key: 'fast', session_id: ctx.sessionId, value: fast ? 'fast' : 'normal' })
-    }
-  } catch (err) {
-    notifyError(err, ctx.failMessage)
-  }
-}

apps/desktop/src/store/model-visibility.test.ts

@@ -3,7 +3,6 @@ import { describe, expect, it } from 'vitest'
 import type { ModelOptionProvider } from '@/types/hermes'
 
 import {
-  collapseModelFamilies,
   effectiveVisibleKeys,
   emptyProviderSentinelKey,
   isProviderSentinel,
@@ -79,18 +78,6 @@ describe('model visibility', () => {
     expect(visible.has(modelVisibilityKey('nous', 'hermes-3-llama-3.1-8b'))).toBe(false)
   })
 
-  it('folds a date-pinned snapshot into its rolling alias when present', () => {
-    const families = collapseModelFamilies(['claude-opus-4-5', 'claude-opus-4-5-20251101'])
-
-    expect(families.map(f => f.id)).toEqual(['claude-opus-4-5'])
-  })
-
-  it('keeps a date-pinned snapshot standing alone when it has no alias', () => {
-    const families = collapseModelFamilies(['claude-opus-4-5-20251101', 'claude-haiku-4-5-20251001'])
-
-    expect(families.map(f => f.id)).toEqual(['claude-opus-4-5-20251101', 'claude-haiku-4-5-20251001'])
-  })
-
   it('sentinel key helper produces correct format', () => {
     expect(emptyProviderSentinelKey('openai')).toBe('openai::')
     expect(isProviderSentinel('openai::')).toBe(true)

apps/desktop/src/store/model-visibility.ts

@@ -51,11 +51,6 @@ export function collapseModelFamilies(models: readonly string[]): ModelFamily[]
       continue
     }
 
-    if (/-\d{8}$/.test(model) && present.has(model.replace(/-\d{8}$/, ''))) {
-      // A date-pinned snapshot superseded by its rolling alias — drop the dupe.
-      continue
-    }
-
     const fastId = `${model}-fast`
     const hasFast = present.has(fastId)
     families.push({ fastId: hasFast ? fastId : null, id: model })

apps/desktop/src/store/session-sync.ts

@@ -1,25 +0,0 @@
-// Cross-window session-list sync. Each desktop window is its own renderer
-// process with its own gateway socket and session store, so a mutation in one
-// (e.g. a new chat started in the compact pop-out) never reaches another
-// window. This bus pings every window to re-pull the shared session list; the
-// data already lives in the backend, the other window just doesn't know to look.
-const CHANNEL = 'hermes:sessions'
-
-const channel = typeof BroadcastChannel === 'undefined' ? null : new BroadcastChannel(CHANNEL)
-
-// A window that mutated the session list (created / titled a chat) tells the
-// others to refresh. A BroadcastChannel never delivers to its own poster, so the
-// caller refreshes locally as it already does.
-export function broadcastSessionsChanged(): void {
-  channel?.postMessage(1)
-}
-
-export function onSessionsChanged(handler: () => void): () => void {
-  if (!channel) {
-    return () => {}
-  }
-
-  channel.addEventListener('message', handler)
-
-  return () => channel.removeEventListener('message', handler)
-}

apps/desktop/src/store/session.ts

@@ -4,23 +4,13 @@ import { lastVisibleMessageIsUser } from '@/app/chat/thread-loading'
 import type { ContextSuggestion } from '@/app/types'
 import type { HermesConnection } from '@/global'
 import type { ChatMessage } from '@/lib/chat-messages'
-import { persistBoolean, persistString, storedBoolean, storedString } from '@/lib/storage'
+import { persistString, storedString } from '@/lib/storage'
 import type { SessionInfo, UsageStats } from '@/types/hermes'
 
 type Updater<T> = T | ((current: T) => T)
 
 const WORKSPACE_CWD_KEY = 'hermes.desktop.workspace-cwd'
 
-// The composer's model/effort/fast is sticky UI state, NOT the profile default
-// (that lives in Settings → Model). Persisting it in localStorage makes a pick
-// follow across Cmd+N and app restarts instead of snapping back to the default.
-// It's deliberately global (not per-profile): a profile switch force-reseeds to
-// that profile's default, while within a profile new chats keep your last pick.
-const COMPOSER_MODEL_KEY = 'hermes.desktop.composer.model'
-const COMPOSER_PROVIDER_KEY = 'hermes.desktop.composer.provider'
-const COMPOSER_EFFORT_KEY = 'hermes.desktop.composer.reasoning-effort'
-const COMPOSER_FAST_KEY = 'hermes.desktop.composer.fast'
-
 let configuredDefaultProjectDir = ''
 
 function workspaceCwdKey(connection: HermesConnection | null = $connection.get()): string {
@@ -218,11 +208,11 @@ export const $lastVisibleMessageIsUser = computed($messages, lastVisibleMessageI
 export const $freshDraftReady = atom(false)
 export const $busy = atom(false)
 export const $awaitingResponse = atom(false)
-export const $currentModel = atom(storedString(COMPOSER_MODEL_KEY) ?? '')
-export const $currentProvider = atom(storedString(COMPOSER_PROVIDER_KEY) ?? '')
-export const $currentReasoningEffort = atom(storedString(COMPOSER_EFFORT_KEY) ?? '')
+export const $currentModel = atom('')
+export const $currentProvider = atom('')
+export const $currentReasoningEffort = atom('')
 export const $currentServiceTier = atom('')
-export const $currentFastMode = atom(storedBoolean(COMPOSER_FAST_KEY, false))
+export const $currentFastMode = atom(false)
 // Effective approval-bypass state mirrored from the gateway (session.info).
 // Persistence lives in the backend config (approvals.mode), so this is a plain
 // reflection of the truth the gateway reports rather than its own store.
@@ -264,29 +254,11 @@ export const setMessages = (next: Updater<ChatMessage[]>) => updateAtom($message
 export const setFreshDraftReady = (next: Updater<boolean>) => updateAtom($freshDraftReady, next)
 export const setBusy = (next: Updater<boolean>) => updateAtom($busy, next)
 export const setAwaitingResponse = (next: Updater<boolean>) => updateAtom($awaitingResponse, next)
-
-export const setCurrentModel = (next: Updater<string>) => {
-  updateAtom($currentModel, next)
-  persistString(COMPOSER_MODEL_KEY, $currentModel.get() || null)
-}
-
-export const setCurrentProvider = (next: Updater<string>) => {
-  updateAtom($currentProvider, next)
-  persistString(COMPOSER_PROVIDER_KEY, $currentProvider.get() || null)
-}
-
-export const setCurrentReasoningEffort = (next: Updater<string>) => {
-  updateAtom($currentReasoningEffort, next)
-  persistString(COMPOSER_EFFORT_KEY, $currentReasoningEffort.get() || null)
-}
-
+export const setCurrentModel = (next: Updater<string>) => updateAtom($currentModel, next)
+export const setCurrentProvider = (next: Updater<string>) => updateAtom($currentProvider, next)
+export const setCurrentReasoningEffort = (next: Updater<string>) => updateAtom($currentReasoningEffort, next)
 export const setCurrentServiceTier = (next: Updater<string>) => updateAtom($currentServiceTier, next)
-
-export const setCurrentFastMode = (next: Updater<boolean>) => {
-  updateAtom($currentFastMode, next)
-  persistBoolean(COMPOSER_FAST_KEY, $currentFastMode.get())
-}
-
+export const setCurrentFastMode = (next: Updater<boolean>) => updateAtom($currentFastMode, next)
 export const setYoloActive = (next: Updater<boolean>) => updateAtom($yoloActive, next)
 
 export const setCurrentCwd = (next: Updater<string>) => {

apps/desktop/src/store/updates.test.ts

@@ -5,9 +5,6 @@ import type { DesktopUpdateStatus } from '@/global'
 const storage = new Map<string, string>()
 
 vi.mock('@/lib/storage', () => ({
-  persistBoolean: (key: string, value: boolean) => {
-    storage.set(key, String(value))
-  },
   persistString: (key: string, value: null | string) => {
     if (value === null) {
       storage.delete(key)
@@ -15,11 +12,6 @@ vi.mock('@/lib/storage', () => ({
       storage.set(key, value)
     }
   },
-  storedBoolean: (key: string, fallback: boolean) => {
-    const value = storage.get(key)
-
-    return value === undefined ? fallback : value === 'true'
-  },
   storedString: (key: string) => storage.get(key) ?? null
 }))
 

apps/desktop/src/store/windows.test.ts

@@ -1,6 +1,6 @@
 import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
 
-import { canOpenSessionWindow, openNewSessionInNewWindow, openSessionInNewWindow } from './windows'
+import { canOpenSessionWindow, openSessionInNewWindow } from './windows'
 
 const desktopWindow = window as unknown as { hermesDesktop?: Window['hermesDesktop'] }
 const initialHermesDesktop = desktopWindow.hermesDesktop
@@ -11,13 +11,9 @@ vi.mock('./notifications', () => ({
   notifyError: (...args: unknown[]) => notifyError(...args)
 }))
 
-function installBridge(
-  openSessionWindow?: Window['hermesDesktop']['openSessionWindow'],
-  openNewSessionWindow?: Window['hermesDesktop']['openNewSessionWindow']
-) {
+function installBridge(openSessionWindow?: Window['hermesDesktop']['openSessionWindow']) {
   desktopWindow.hermesDesktop = {
-    ...(openSessionWindow ? { openSessionWindow } : {}),
-    ...(openNewSessionWindow ? { openNewSessionWindow } : {})
+    ...(openSessionWindow ? { openSessionWindow } : {})
   } as unknown as Window['hermesDesktop']
 }
 
@@ -105,39 +101,3 @@ describe('openSessionInNewWindow', () => {
     expect(notifyError).toHaveBeenCalledTimes(1)
   })
 })
-
-describe('openNewSessionInNewWindow', () => {
-  it('no-ops gracefully when the bridge is absent (web fallback)', async () => {
-    delete desktopWindow.hermesDesktop
-
-    await openNewSessionInNewWindow()
-
-    expect(notifyError).not.toHaveBeenCalled()
-  })
-
-  it('no-ops when openNewSessionWindow is missing', async () => {
-    installBridge(vi.fn().mockResolvedValue({ ok: true }))
-
-    await openNewSessionInNewWindow()
-
-    expect(notifyError).not.toHaveBeenCalled()
-  })
-
-  it('invokes the bridge', async () => {
-    const openNew = vi.fn().mockResolvedValue({ ok: true })
-    installBridge(vi.fn().mockResolvedValue({ ok: true }), openNew)
-
-    await openNewSessionInNewWindow()
-
-    expect(openNew).toHaveBeenCalledTimes(1)
-    expect(notifyError).not.toHaveBeenCalled()
-  })
-
-  it('notifies on an ok:false result', async () => {
-    installBridge(vi.fn().mockResolvedValue({ ok: true }), vi.fn().mockResolvedValue({ ok: false, error: 'nope' }))
-
-    await openNewSessionInNewWindow()
-
-    expect(notifyError).toHaveBeenCalledTimes(1)
-  })
-})

apps/desktop/src/store/windows.ts

@@ -6,7 +6,6 @@ import { notifyError } from './notifications'
 // never from the router. A "secondary" window renders a single chat without the
 // global session sidebar or the install / onboarding overlays.
 const SECONDARY_WINDOW_FLAG = 'secondary'
-const NEW_SESSION_WINDOW_FLAG = '1'
 
 let secondaryWindowCache: boolean | null = null
 
@@ -28,26 +27,6 @@ export function isSecondaryWindow(): boolean {
   return result
 }
 
-let newSessionWindowCache: boolean | null = null
-
-export function isNewSessionWindow(): boolean {
-  if (newSessionWindowCache !== null) {
-    return newSessionWindowCache
-  }
-
-  let result = false
-
-  try {
-    result = new URLSearchParams(window.location.search).get('new') === NEW_SESSION_WINDOW_FLAG
-  } catch {
-    result = false
-  }
-
-  newSessionWindowCache = result
-
-  return result
-}
-
 let watchWindowCache: boolean | null = null
 
 // A "watch" window spectates a session that is being driven elsewhere (a
@@ -78,22 +57,6 @@ export function canOpenSessionWindow(): boolean {
   return typeof window !== 'undefined' && typeof window.hermesDesktop?.openSessionWindow === 'function'
 }
 
-type WindowOpenResult = { ok: boolean; error?: string } | undefined
-
-// Run a window-open bridge call, surfacing any failure as a toast. Shared by the
-// session pop-out and the new-session pop-out.
-async function openWindow(call: () => Promise<WindowOpenResult>, failMessage: string): Promise<void> {
-  try {
-    const result = await call()
-
-    if (!result?.ok) {
-      notifyError(new Error(result?.error || 'unknown error'), failMessage)
-    }
-  } catch (err) {
-    notifyError(err, failMessage)
-  }
-}
-
 // Open (or focus) a standalone OS window for a single chat session. No-ops
 // gracefully outside Electron so callers can wire it unconditionally.
 // `watch: true` opens a spectator window (lazy resume, live-mirror stream).
@@ -102,14 +65,13 @@ export async function openSessionInNewWindow(sessionId: string, opts?: { watch?:
     return
   }
 
-  await openWindow(() => window.hermesDesktop.openSessionWindow(sessionId, opts), 'Could not open chat in a new window')
-}
+  try {
+    const result = await window.hermesDesktop.openSessionWindow(sessionId, opts)
 
-// Open a fresh compact window on the new-session draft.
-export async function openNewSessionInNewWindow(): Promise<void> {
-  if (!canOpenSessionWindow() || typeof window.hermesDesktop.openNewSessionWindow !== 'function') {
-    return
+    if (!result?.ok) {
+      notifyError(new Error(result?.error || 'unknown error'), 'Could not open chat in a new window')
+    }
+  } catch (err) {
+    notifyError(err, 'Could not open chat in a new window')
   }
-
-  await openWindow(() => window.hermesDesktop.openNewSessionWindow(), 'Could not open new session window')
 }

apps/desktop/src/types/hermes.ts

@@ -47,9 +47,6 @@ export interface OAuthProviderStatus {
 
 export interface OAuthProvider {
   cli_command: string
-  /** Shell command that clears an external provider's credentials, run in the
-   *  embedded terminal. Null when Hermes doesn't know how to remove it. */
-  disconnect_command?: null | string
   disconnect_hint?: null | string
   disconnectable?: boolean
   docs_url: string

cli-config.yaml.example

@@ -724,7 +724,7 @@ platform_toolsets:
 #     # allowed_chats: ["-1001234567890"]
 #     extra:
 #       disable_link_previews: false  # Set true to suppress Telegram URL previews in bot messages
-#       rich_messages: false          # Bot API 10.1 rich messages (tables/task lists/details/math); default true, set false to force legacy MarkdownV2
+#       rich_messages: false          # Opt in to Bot API 10.1 rich messages; default uses legacy MarkdownV2
 #
 # Discord-specific settings (config.yaml top-level, not under platforms:):
 #

cli.py

@@ -977,11 +977,6 @@ def _run_cleanup(*, notify_session_finalize: bool = True):
         _cleanup_all_terminals()
     except Exception:
         pass
-    try:
-        from tools.async_delegation import interrupt_all as _interrupt_async_delegations
-        _interrupt_async_delegations(reason="CLI shutdown")
-    except Exception:
-        pass
     try:
         _cleanup_all_browsers()
     except Exception:

gateway/display_config.py

@@ -32,7 +32,6 @@ from typing import Any
 
 _GLOBAL_DEFAULTS: dict[str, Any] = {
     "tool_progress": "all",
-    "tool_progress_grouping": "accumulate",  # "accumulate" = edit one bubble; "separate" = one msg per tool
     "show_reasoning": False,
     "tool_preview_length": 0,
     "streaming": None,  # None = follow top-level streaming config
@@ -239,9 +238,6 @@ def _normalise(setting: str, value: Any) -> Any:
         if isinstance(value, str):
             return value.lower() in {"true", "1", "yes", "on"}
         return bool(value)
-    if setting == "tool_progress_grouping":
-        val = str(value).lower()
-        return val if val in ("accumulate", "separate") else "accumulate"
     if setting == "tool_preview_length":
         try:
             return int(value)

gateway/message_timestamps.py

@@ -1,166 +0,0 @@
-"""Helpers for rendering gateway message timestamps exactly once.
-
-Gateway messages need timestamps in the LLM context for temporal awareness, but
-persisted message content should stay clean so replay does not accumulate
-``[timestamp] [timestamp] ...`` prefixes across turns.
-"""
-
-from __future__ import annotations
-
-import re
-from datetime import datetime
-from typing import Any, Optional, Tuple
-
-
-# Current gateway format: [Tue 2026-04-28 13:40:53 CEST]
-_HUMAN_TIMESTAMP_RE = re.compile(
-    r"^\[(?P<dow>[A-Z][a-z]{2}) "
-    r"(?P<date>\d{4}-\d{2}-\d{2}) "
-    r"(?P<time>\d{2}:\d{2}:\d{2})"
-    r"(?: (?P<tz>[A-Za-z0-9_+\-/:]+))?\]\s*"
-)
-
-# Older gateway format: [2026-04-13T17:02:06+0200] or [+02:00]
-_ISO_TIMESTAMP_RE = re.compile(
-    r"^\[(?P<iso>\d{4}-\d{2}-\d{2}T[^\]]+)\]\s*"
-)
-
-
-def coerce_message_timestamp(ts_value: Any, tz=None) -> Optional[float]:
-    """Coerce a timestamp-like value to Unix epoch seconds.
-
-    Accepts Unix epoch numbers, datetime objects, ISO strings, and the gateway's
-    bracketed human-readable timestamp format. Returns ``None`` when the value
-    cannot be interpreted.
-    """
-    if ts_value is None:
-        return None
-
-    if isinstance(ts_value, (int, float)):
-        return float(ts_value)
-
-    if hasattr(ts_value, "timestamp"):
-        try:
-            return float(ts_value.timestamp())
-        except Exception:
-            return None
-
-    if isinstance(ts_value, str):
-        text = ts_value.strip()
-        if not text:
-            return None
-        parsed = _parse_timestamp_prefix(text, tz=tz)
-        if parsed is not None:
-            return parsed
-        try:
-            return float(text)
-        except (TypeError, ValueError):
-            pass
-        try:
-            dt = datetime.fromisoformat(text)
-        except (TypeError, ValueError):
-            try:
-                dt = datetime.strptime(text, "%Y-%m-%dT%H:%M:%S%z")
-            except (TypeError, ValueError):
-                return None
-        if dt.tzinfo is None:
-            if tz is not None:
-                dt = dt.replace(tzinfo=tz)
-            else:
-                dt = dt.astimezone()
-        return float(dt.timestamp())
-
-    return None
-
-
-def format_message_timestamp(ts_value: Any, tz=None) -> str:
-    """Format a timestamp value as ``[Tue 2026-04-28 13:40:53 CEST]``."""
-    epoch = coerce_message_timestamp(ts_value, tz=tz)
-    if epoch is None:
-        return ""
-    if tz is not None:
-        dt = datetime.fromtimestamp(epoch, tz=tz)
-    else:
-        dt = datetime.fromtimestamp(epoch).astimezone()
-    return "[" + dt.strftime("%a %Y-%m-%d %H:%M:%S %Z") + "]"
-
-
-def strip_leading_message_timestamps(content: str, tz=None) -> Tuple[str, Optional[float]]:
-    """Strip one or more leading gateway timestamp prefixes from ``content``.
-
-    Returns ``(clean_content, embedded_epoch)``.  If multiple timestamp prefixes
-    are present, the timestamp closest to the actual message text wins.  That
-    preserves the original platform-send time for legacy contaminated rows like
-    ``[processing time] [platform time] [sender] message``.
-    """
-    if not isinstance(content, str) or not content:
-        return content, None
-
-    text = content
-    embedded_epoch: Optional[float] = None
-
-    while True:
-        match = _HUMAN_TIMESTAMP_RE.match(text) or _ISO_TIMESTAMP_RE.match(text)
-        if not match:
-            break
-        parsed = _parse_timestamp_match(match, tz=tz)
-        if parsed is not None:
-            embedded_epoch = parsed
-        text = text[match.end():]
-
-    return text, embedded_epoch
-
-
-def render_user_content_with_timestamp(content: str, ts_value: Any = None, tz=None) -> str:
-    """Render a user message for LLM context with exactly one timestamp prefix.
-
-    Existing leading timestamp prefixes are removed first.  If such a prefix was
-    present, its parsed time wins over ``ts_value``; otherwise ``ts_value`` is
-    formatted and prepended.  If no timestamp is available, the cleaned content is
-    returned unchanged.
-    """
-    clean_content, embedded_epoch = strip_leading_message_timestamps(content, tz=tz)
-    effective_ts = embedded_epoch if embedded_epoch is not None else ts_value
-    prefix = format_message_timestamp(effective_ts, tz=tz)
-    if not prefix:
-        return clean_content
-    if clean_content:
-        return f"{prefix} {clean_content}"
-    return prefix
-
-
-def _parse_timestamp_prefix(text: str, tz=None) -> Optional[float]:
-    match = _HUMAN_TIMESTAMP_RE.match(text) or _ISO_TIMESTAMP_RE.match(text)
-    if not match:
-        return None
-    return _parse_timestamp_match(match, tz=tz)
-
-
-def _parse_timestamp_match(match: re.Match, tz=None) -> Optional[float]:
-    if "iso" in match.groupdict() and match.group("iso"):
-        iso_text = match.group("iso")
-        try:
-            dt = datetime.fromisoformat(iso_text)
-        except ValueError:
-            try:
-                dt = datetime.strptime(iso_text, "%Y-%m-%dT%H:%M:%S%z")
-            except ValueError:
-                return None
-        if dt.tzinfo is None:
-            if tz is not None:
-                dt = dt.replace(tzinfo=tz)
-            else:
-                dt = dt.astimezone()
-        return float(dt.timestamp())
-
-    date_part = match.group("date")
-    time_part = match.group("time")
-    try:
-        dt = datetime.strptime(f"{date_part} {time_part}", "%Y-%m-%d %H:%M:%S")
-    except ValueError:
-        return None
-    if tz is not None:
-        dt = dt.replace(tzinfo=tz)
-    else:
-        dt = dt.astimezone()
-    return float(dt.timestamp())

gateway/platforms/base.py

@@ -77,13 +77,6 @@ def _thread_metadata_for_source(source, reply_to_message_id: str | None = None)
     return metadata
 
 
-def _mark_notify_metadata(metadata: dict | None) -> dict:
-    """Clone metadata and mark a user-visible reply as notify-worthy."""
-    notify_metadata = dict(metadata) if metadata else {}
-    notify_metadata["notify"] = True
-    return notify_metadata
-
-
 def _reply_anchor_for_event(event) -> str | None:
     """Return reply_to id for platforms that need reply semantics.
 
@@ -3896,7 +3889,7 @@ class BasePlatformAdapter(ABC):
                     chat_id=event.source.chat_id,
                     content=_text,
                     reply_to=_reply_anchor_for_event(event),
-                    metadata=_mark_notify_metadata(thread_meta),
+                    metadata=thread_meta,
                 )
                 if _eph_ttl > 0 and _r.success and _r.message_id:
                     self._schedule_ephemeral_delete(
@@ -4002,7 +3995,7 @@ class BasePlatformAdapter(ABC):
                             chat_id=event.source.chat_id,
                             content=_text,
                             reply_to=_reply_anchor_for_event(event),
-                            metadata=_mark_notify_metadata(_thread_meta),
+                            metadata=_thread_meta,
                         )
                         if _eph_ttl > 0 and _r.success and _r.message_id:
                             self._schedule_ephemeral_delete(
@@ -4052,7 +4045,7 @@ class BasePlatformAdapter(ABC):
                                 chat_id=event.source.chat_id,
                                 content=_text,
                                 reply_to=_reply_anchor_for_event(event),
-                                metadata=_mark_notify_metadata(_thread_meta),
+                                metadata=_thread_meta,
                             )
                             if _eph_ttl > 0 and _r.success and _r.message_id:
                                 self._schedule_ephemeral_delete(
@@ -4275,12 +4268,6 @@ class BasePlatformAdapter(ABC):
                         )
                         text_content = _recovered
 
-                # Final user-visible content (text, TTS, media, files) gets
-                # the existing notify=True marker. Clone once so typing/status
-                # metadata stays unmarked and progress bubbles remain
-                # thread-strict.
-                _final_thread_metadata = _mark_notify_metadata(_thread_metadata)
-
                 # Auto-TTS: if voice message, generate audio FIRST (before sending text)
                 # Gated via ``_should_auto_tts_for_chat``: fires when the chat has
                 # an explicit ``/voice on|tts`` opt-in OR when ``voice.auto_tts`` is
@@ -4320,7 +4307,7 @@ class BasePlatformAdapter(ABC):
                             chat_id=event.source.chat_id,
                             audio_path=_tts_path,
                             caption=telegram_tts_caption,
-                            metadata=_final_thread_metadata,
+                            metadata=_thread_metadata,
                         )
                         _tts_caption_delivered = bool(
                             telegram_tts_caption and getattr(tts_result, "success", False)
@@ -4335,11 +4322,23 @@ class BasePlatformAdapter(ABC):
                 if text_content and not _tts_caption_delivered:
                     logger.info("[%s] Sending response (%d chars) to %s", self.name, len(text_content), event.source.chat_id)
                     _reply_anchor = _reply_anchor_for_event(event)
+                    # Mark final response messages for notification delivery.
+                    # Platform adapters that support per-message notification
+                    # control (e.g. Telegram's disable_notification) use this
+                    # flag to override silent-mode and ensure the final
+                    # response triggers a push notification.
+                    # Clone to avoid mutating the metadata shared with the
+                    # typing-indicator task (which must remain unmarked).
+                    if _thread_metadata is not None:
+                        _thread_metadata = dict(_thread_metadata)
+                        _thread_metadata["notify"] = True
+                    else:
+                        _thread_metadata = {"notify": True}
                     result = await self._send_with_retry(
                         chat_id=event.source.chat_id,
                         content=text_content,
                         reply_to=_reply_anchor,
-                        metadata=_final_thread_metadata,
+                        metadata=_thread_metadata,
                     )
                     _record_delivery(result)
 
@@ -4368,7 +4367,7 @@ class BasePlatformAdapter(ABC):
                         await self.send_multiple_images(
                             chat_id=event.source.chat_id,
                             images=images,
-                            metadata=_final_thread_metadata,
+                            metadata=_thread_metadata,
                             human_delay=human_delay,
                         )
                     except Exception as batch_err:
@@ -4410,7 +4409,7 @@ class BasePlatformAdapter(ABC):
                         await self.send_multiple_images(
                             chat_id=event.source.chat_id,
                             images=_batch,
-                            metadata=_final_thread_metadata,
+                            metadata=_thread_metadata,
                             human_delay=human_delay,
                         )
                     except Exception as batch_err:
@@ -4425,19 +4424,19 @@ class BasePlatformAdapter(ABC):
                             media_result = await self.send_voice(
                                 chat_id=event.source.chat_id,
                                 audio_path=media_path,
-                                metadata=_final_thread_metadata,
+                                metadata=_thread_metadata,
                             )
                         elif ext in _VIDEO_EXTS:
                             media_result = await self.send_video(
                                 chat_id=event.source.chat_id,
                                 video_path=media_path,
-                                metadata=_final_thread_metadata,
+                                metadata=_thread_metadata,
                             )
                         else:
                             media_result = await self.send_document(
                                 chat_id=event.source.chat_id,
                                 file_path=media_path,
-                                metadata=_final_thread_metadata,
+                                metadata=_thread_metadata,
                             )
 
                         if not media_result.success:
@@ -4455,13 +4454,13 @@ class BasePlatformAdapter(ABC):
                             await self.send_video(
                                 chat_id=event.source.chat_id,
                                 video_path=file_path,
-                                metadata=_final_thread_metadata,
+                                metadata=_thread_metadata,
                             )
                         else:
                             await self.send_document(
                                 chat_id=event.source.chat_id,
                                 file_path=file_path,
-                                metadata=_final_thread_metadata,
+                                metadata=_thread_metadata,
                             )
                     except Exception as file_err:
                         logger.error("[%s] Error sending local file %s: %s", self.name, file_path, file_err)

gateway/platforms/email.py

@@ -678,13 +678,8 @@ class EmailAdapter(BasePlatformAdapter):
         image_url: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        """Send an image URL as part of an email body.
-
-        ``metadata`` is accepted to honor the base-class contract; the
-        email body send doesn't use it.
-        """
+        """Send an image URL as part of an email body."""
         text = caption or ""
         text += f"\n\nImage: {image_url}"
         return await self.send(chat_id, text.strip(), reply_to)

gateway/platforms/telegram.py

@@ -419,13 +419,11 @@ class TelegramAdapter(BasePlatformAdapter):
         self._mention_patterns = self._compile_mention_patterns()
         self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'
         self._disable_link_previews: bool = self._coerce_bool_extra("disable_link_previews", False)
-        # Bot API 10.1 Rich Messages: render constructs the legacy MarkdownV2
-        # path degrades (tables → bullet lists, task lists, <details>, block
-        # math) via sendRichMessage / editMessageText's rich_message param using
-        # the raw agent markdown. Enabled by default; users can opt out for
-        # clients that accept but render rich messages poorly via
-        # platforms.telegram.extra.rich_messages: false.
-        self._rich_messages_enabled: bool = self._coerce_bool_extra("rich_messages", True)
+        # Bot API 10.1 Rich Messages: when explicitly enabled, send final
+        # replies via sendRichMessage with the raw agent markdown so
+        # tables/task lists/etc. render natively. Disabled by default because
+        # several Telegram clients accept but render rich messages poorly.
+        self._rich_messages_enabled: bool = self._coerce_bool_extra("rich_messages", False)
         # Latched off after a capability failure on sendRichMessage /
         # sendRichMessageDraft (e.g. older python-telegram-bot without the
         # endpoint) so later sends skip the doomed rich attempt entirely.
@@ -981,54 +979,18 @@ class TelegramAdapter(BasePlatformAdapter):
                 return True
         return False
 
-    def _needs_rich_rendering(self, content: str) -> bool:
-        """Return True for markdown constructs that the legacy path degrades.
-
-        Keep ordinary replies on the pre-rich MarkdownV2 path so Telegram
-        clients render a consistent font weight/spacing. The rich endpoint is
-        reserved for constructs where raw markdown materially improves output:
-        pipe tables (MarkdownV2 has no table syntax and rewrites them into
-        bullet lists), GFM task lists, collapsible ``<details>`` blocks, and
-        block math.  Adapted from #45995 (@YonganZhang).
-        """
-        if not content:
-            return False
-        if any(_TABLE_SEPARATOR_RE.match(line) for line in content.splitlines()):
-            return True
-        if re.search(r"(?m)^\s*[-*]\s+\[[ xX]\]\s+", content):
-            return True
-        if re.search(r"(?m)^<details\b|^</details>|^<summary\b|^</summary>", content):
-            return True
-        if "$$" in content:
-            return True
-        return False
-
-    def _rich_eligible(self, content: str) -> bool:
-        """Capability/content eligibility for rich, ignoring ``expect_edits``.
-
-        Shared core of :meth:`_should_attempt_rich` minus the per-call
-        ``expect_edits`` metadata gate.  The rich EDIT-finalize path
-        (:meth:`_try_edit_rich`) needs this: a streamed preview is sent with
-        ``expect_edits=True`` to stay on the editable path mid-stream, but the
-        FINAL edit should still upgrade to rich when the content warrants it.
-        """
-        return bool(
-            getattr(self, "_rich_messages_enabled", True)
-            and not getattr(self, "_rich_send_disabled", False)
-            and content
-            and content.strip()
-            and self._needs_rich_rendering(content)
-            and not self._has_telegram_desktop_details_math_crash_shape(content)
-            and self._content_fits_rich_limits(content)
-            and self._bot_supports_rich()
-        )
-
     def _should_attempt_rich(
         self, content: str, metadata: Optional[Dict[str, Any]] = None
     ) -> bool:
         return bool(
-            not (metadata or {}).get("expect_edits")
-            and self._rich_eligible(content)
+            getattr(self, "_rich_messages_enabled", False)
+            and not getattr(self, "_rich_send_disabled", False)
+            and not (metadata or {}).get("expect_edits")
+            and content
+            and content.strip()
+            and not self._has_telegram_desktop_details_math_crash_shape(content)
+            and self._content_fits_rich_limits(content)
+            and self._bot_supports_rich()
         )
 
     def prefers_fresh_final_streaming(
@@ -1036,13 +998,12 @@ class TelegramAdapter(BasePlatformAdapter):
     ) -> bool:
         """Whether to replace a streamed preview with a fresh rich final.
 
-        Disabled for Telegram. The fresh-final path briefly shows two copies of
-        the final answer, then deletes the streaming preview after the rich send
-        succeeds — it looks like duplicate delivery at the end of every streamed
-        turn (the reason #46206 reverted it).  Rich finalize is instead handled
-        by editing the existing preview in place via Bot API 10.1's
-        ``editMessageText`` ``rich_message`` parameter (see
-        :meth:`_try_edit_rich`), so no fresh re-send / delete is needed.
+        Keep this disabled for Telegram. The fresh-final path briefly shows two
+        copies of the final answer, then deletes the streaming preview after the
+        rich send succeeds. That is especially visible on clients that support
+        rich messages well, and it looks like duplicate delivery at the end of
+        every streamed turn. Until Telegram rich edits are wired directly, final
+        streamed replies should edit the existing preview in place.
         """
         return False
 
@@ -1058,7 +1019,7 @@ class TelegramAdapter(BasePlatformAdapter):
         streams split exactly as before.
         """
         if (
-            getattr(self, "_rich_messages_enabled", True)
+            getattr(self, "_rich_messages_enabled", False)
             and not getattr(self, "_rich_send_disabled", False)
             and self._bot_supports_rich()
         ):
@@ -1241,87 +1202,14 @@ class TelegramAdapter(BasePlatformAdapter):
                 message_id = (msg.get("result") or {}).get("message_id")
         else:
             message_id = getattr(msg, "message_id", None)
-        if message_id is not None:
-            # Telegram won't echo rich content in reply_to_message, so remember
-            # what we sent — replies to this message resolve via this index.
-            try:
-                from gateway import rich_sent_store
-                rich_sent_store.record(str(chat_id), str(message_id), content)
-            except Exception:
-                pass
         return SendResult(
             success=True,
             message_id=str(message_id) if message_id is not None else None,
         )
 
-    async def _try_edit_rich(
-        self,
-        chat_id: str,
-        message_id: str,
-        content: str,
-    ) -> Optional[SendResult]:
-        """Edit an existing message in place as a rich message (Bot API 10.1).
-
-        Uses ``editMessageText`` with the ``rich_message`` parameter so a
-        streamed preview can finalize as rich (tables/task lists/details/math)
-        WITHOUT a fresh send + delete — no duplicate preview.  Mirrors
-        :meth:`_try_send_rich`'s error contract:
-
-        - success → ``SendResult(success=True, message_id=...)``
-        - permanent / capability error → ``None`` (caller falls back to the
-          legacy MarkdownV2 edit; capability errors latch rich off)
-        - transient / unknown → ``SendResult(success=False)`` with retry
-          semantics (the message may already be edited; do NOT legacy-resend)
-        """
-        payload: Dict[str, Any] = {
-            "chat_id": int(chat_id),
-            "message_id": int(message_id),
-            "rich_message": self._rich_message_payload(content),
-        }
-        if getattr(self, "_disable_link_previews", False):
-            payload["link_preview_options"] = {"is_disabled": True}
-        try:
-            # Raw Bot API result; do not request return_type=Message (PTB does
-            # not fully model the 10.1 response shape yet — a post-edit parse
-            # error must not be mistaken for a failed edit).
-            await self._bot.do_api_request("editMessageText", api_kwargs=payload)
-        except Exception as exc:
-            if self._is_rich_fallback_error(exc):
-                if self._is_rich_capability_error(exc):
-                    self._rich_send_disabled = True
-                # "Message is not modified" — content identical to the current
-                # rich message; treat as a successful no-op so the caller does
-                # not fall through to a redundant legacy edit.
-                if "not modified" in str(exc).lower():
-                    return SendResult(success=True, message_id=message_id)
-                logger.debug(
-                    "[%s] rich editMessageText rejected (%s) — falling back to MarkdownV2 edit",
-                    self.name, exc,
-                )
-                return None
-            if "not modified" in str(exc).lower():
-                return SendResult(success=True, message_id=message_id)
-            err_str = str(exc).lower()
-            try:
-                from telegram.error import TimedOut as _TimedOut
-            except (ImportError, AttributeError):
-                _TimedOut = None
-            is_timeout = (_TimedOut and isinstance(exc, _TimedOut)) or "timed out" in err_str
-            is_connect_timeout = self._looks_like_connect_timeout(exc)
-            logger.warning(
-                "[%s] rich editMessageText transient failure (no legacy resend): %s",
-                self.name, exc,
-            )
-            return SendResult(
-                success=False,
-                error=str(exc),
-                retryable=(is_connect_timeout or not is_timeout),
-            )
-        return SendResult(success=True, message_id=message_id)
-
     def _should_attempt_rich_draft(self, content: str) -> bool:
         return bool(
-            getattr(self, "_rich_messages_enabled", True)
+            getattr(self, "_rich_messages_enabled", False)
             and not getattr(self, "_rich_send_disabled", False)
             and not getattr(self, "_rich_draft_disabled", False)
             and content
@@ -2667,21 +2555,6 @@ class TelegramAdapter(BasePlatformAdapter):
         if not self._bot:
             return SendResult(success=False, error="Not connected")
 
-        # Rich finalize (Bot API 10.1): when the completed content has
-        # constructs the legacy MarkdownV2 edit degrades (tables → bullet
-        # lists, task lists, <details>, block math) and rich is available,
-        # edit the preview IN PLACE via editMessageText's rich_message param.
-        # No fresh send + delete → no duplicate preview (the problem #46206
-        # reverted the fresh-final path for).  Attempted before the 4,096
-        # overflow pre-flight because the rich text cap is 32,768 — a rich
-        # table that exceeds the MarkdownV2 limit must not be split into legacy
-        # chunks.  Falls back to the legacy edit path (overflow split included)
-        # on capability/permanent rejection.
-        if finalize and self._rich_eligible(content):
-            rich_result = await self._try_edit_rich(chat_id, message_id, content)
-            if rich_result is not None:
-                return rich_result
-
         # Pre-flight: if content already exceeds the limit, split-and-deliver
         # without round-tripping a doomed edit.
         if utf16_len(content) > self.MAX_MESSAGE_LENGTH:
@@ -6708,19 +6581,6 @@ class TelegramAdapter(BasePlatformAdapter):
                     or message.reply_to_message.caption
                     or None
                 )
-                if not reply_to_text:
-                    # Rich messages (sendRichMessage — the launchd briefings and
-                    # the gateway's own rich finals) are NOT echoed with their
-                    # content in reply_to_message; Telegram sends no text,
-                    # caption, or api_kwargs for them. Recover the text we sent
-                    # from our local send-time index, keyed by message id.
-                    try:
-                        from gateway import rich_sent_store
-                        reply_to_text = rich_sent_store.lookup(
-                            str(chat.id), reply_to_id
-                        )
-                    except Exception:
-                        reply_to_text = None
 
         # Per-channel/topic ephemeral prompt
         from gateway.platforms.base import resolve_channel_prompt

gateway/platforms/whatsapp.py

@@ -846,20 +846,13 @@ class WhatsAppAdapter(WhatsAppBehaviorMixin, BasePlatformAdapter):
         image_url: str,
         caption: Optional[str] = None,
         reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        """Download image URL to cache, send natively via bridge.
-
-        ``metadata`` is accepted to honor the base-class contract — the
-        batch sender ``send_multiple_images`` passes it through to every
-        send path. The bridge media call doesn't use it, matching the
-        sibling overrides (send_video / send_voice / send_document).
-        """
+        """Download image URL to cache, send natively via bridge."""
         try:
             local_path = await cache_image_from_url(image_url)
             return await self._send_media_to_bridge(chat_id, local_path, "image", caption)
         except Exception:
-            return await super().send_image(chat_id, image_url, caption, reply_to, metadata)
+            return await super().send_image(chat_id, image_url, caption, reply_to)
 
     async def send_image_file(
         self,
@@ -1143,15 +1136,6 @@ class WhatsAppAdapter(WhatsAppBehaviorMixin, BasePlatformAdapter):
             body = data.get("body", "")
             if data.get("isGroup"):
                 body = self._clean_bot_mention_text(body, data)
-
-            # If this is a reply, include the quoted message text so the agent
-            # knows exactly what the user is responding to (fixes "approve" context issue)
-            quoted_text = str(data.get("quotedText") or "").strip()
-            if quoted_text and data.get("hasQuotedMessage"):
-                # Truncate long quoted text to keep prompts reasonable
-                if len(quoted_text) > 300:
-                    quoted_text = quoted_text[:297] + "..."
-                body = f"[Replying to: \"{quoted_text}\"]\n{body}"
             MAX_TEXT_INJECT_BYTES = 100 * 1024
             if msg_type == MessageType.DOCUMENT and cached_urls:
                 for doc_path in cached_urls:

gateway/rich_sent_store.py

@@ -1,80 +0,0 @@
-"""Local index of text we've sent via ``sendRichMessage`` (Bot API 10.1).
-
-Telegram does NOT echo a rich message's content back in ``reply_to_message``
-when a user replies to it (verified: ``.text``/``.caption`` empty,
-``.api_kwargs`` None). So replies to the launchd briefings / any rich send
-arrive with no quotable text and the agent is blind to what was referenced.
-
-Fix: remember ``message_id -> text`` at send time, look it up by
-``reply_to_id`` on inbound. This module is the single source of truth for that
-index.
-
-Best-effort and dependency-free: every operation swallows errors and degrades
-to a no-op / ``None`` so it can never break a send or an inbound message.
-"""
-
-from __future__ import annotations
-
-import json
-import os
-import time
-from typing import Optional
-
-_MAX_ENTRIES = 1000
-_MAX_TEXT_CHARS = 2000
-
-
-def _store_path() -> str:
-    home = os.environ.get("HERMES_HOME") or os.path.expanduser("~/.hermes")
-    return os.path.join(home, "state", "rich_sent_index.json")
-
-
-def _key(chat_id, message_id) -> str:
-    return f"{chat_id}:{message_id}"
-
-
-def record(chat_id, message_id, text: Optional[str]) -> None:
-    """Persist ``text`` for ``(chat_id, message_id)``. No-op on any failure."""
-    if not text or message_id is None or chat_id is None:
-        return
-    path = _store_path()
-    try:
-        os.makedirs(os.path.dirname(path), exist_ok=True)
-        try:
-            with open(path, "r", encoding="utf-8") as fh:
-                data = json.load(fh)
-            if not isinstance(data, dict):
-                data = {}
-        except (FileNotFoundError, ValueError):
-            data = {}
-        data[_key(chat_id, message_id)] = {
-            "t": text[:_MAX_TEXT_CHARS],
-            "ts": int(time.time()),
-        }
-        # Trim oldest by timestamp when over cap.
-        if len(data) > _MAX_ENTRIES:
-            for k, _ in sorted(
-                data.items(), key=lambda kv: kv[1].get("ts", 0)
-            )[: len(data) - _MAX_ENTRIES]:
-                data.pop(k, None)
-        tmp = f"{path}.tmp.{os.getpid()}"
-        with open(tmp, "w", encoding="utf-8") as fh:
-            json.dump(data, fh, ensure_ascii=False)
-        os.replace(tmp, path)  # atomic; tolerates concurrent writers racing
-    except Exception:
-        return
-
-
-def lookup(chat_id, message_id) -> Optional[str]:
-    """Return stored text for ``(chat_id, message_id)`` or ``None``."""
-    if message_id is None or chat_id is None:
-        return None
-    try:
-        with open(_store_path(), "r", encoding="utf-8") as fh:
-            data = json.load(fh)
-        entry = data.get(_key(chat_id, message_id))
-        if isinstance(entry, dict):
-            return entry.get("t") or None
-    except (FileNotFoundError, ValueError, AttributeError):
-        return None
-    return None

gateway/run.py

@@ -402,68 +402,6 @@ async def _send_or_update_status_coro(adapter, chat_id, status_key, content, met
     return await adapter.send(chat_id, content, metadata=metadata)
 
 
-def _resolve_progress_thread_id(platform: Any, source_thread_id: Any, event_message_id: Any) -> Optional[str]:
-    """Return thread/root ID that progress/status bubbles should target."""
-    platform_value = getattr(platform, "value", platform)
-    platform_key = str(platform_value or "").lower()
-    if source_thread_id:
-        return str(source_thread_id)
-    if platform_key in {"slack", "mattermost"} and event_message_id:
-        return str(event_message_id)
-    return None
-
-
-def _has_platform_display_override(user_config: dict, platform_key: str, setting: str) -> bool:
-    """Return True when display.platforms.<platform> explicitly sets setting."""
-    display = user_config.get("display") if isinstance(user_config, dict) else None
-    if not isinstance(display, dict):
-        return False
-    platforms = display.get("platforms")
-    if not isinstance(platforms, dict):
-        return False
-    platform_cfg = platforms.get(platform_key)
-    return isinstance(platform_cfg, dict) and setting in platform_cfg
-
-
-def _resolve_gateway_display_bool(
-    user_config: dict,
-    platform_key: str,
-    setting: str,
-    *,
-    default: bool = False,
-    platform: Any = None,
-    require_platform_override_for: set[Any] | None = None,
-) -> bool:
-    """Resolve a boolean display setting with optional platform-only opt-in.
-
-    Some display features expose assistant scratch text rather than deliberate
-    user-facing output.  For high-noise threaded chat surfaces such as
-    Mattermost, a global opt-in is too broad: they must be enabled with an
-    explicit display.platforms.<platform>.<setting> override.
-    """
-    current_platform = _gateway_platform_value(platform or platform_key)
-    platform_only = {
-        _gateway_platform_value(candidate)
-        for candidate in (require_platform_override_for or set())
-    }
-    if (
-        current_platform in platform_only
-        and not _has_platform_display_override(user_config, platform_key, setting)
-    ):
-        return False
-
-    from gateway.display_config import resolve_display_setting
-
-    value = resolve_display_setting(user_config, platform_key, setting, default)
-    if isinstance(value, bool):
-        return value
-    if isinstance(value, str):
-        return value.strip().lower() in {"true", "yes", "1", "on"}
-    if value is None:
-        return bool(default)
-    return bool(value)
-
-
 def _telegramize_command_mentions(text: str, platform: Any) -> str:
     """Rewrite slash-command mentions to Telegram-valid command names.
 
@@ -692,31 +630,10 @@ def _uses_telegram_observed_group_context(channel_prompt: Optional[str]) -> bool
     return bool(channel_prompt and _TELEGRAM_OBSERVED_CONTEXT_PROMPT_MARKER in channel_prompt)
 
 
-def _message_timestamps_enabled(user_config: Optional[dict]) -> bool:
-    """True when gateway.message_timestamps.enabled is opted in.
-
-    Default OFF: injecting a ``[Tue 2026-04-28 13:40:53 CEST]`` prefix onto
-    every user message changes what the model sees for all gateway users, so
-    it must be explicitly enabled in config.yaml under
-    ``gateway.message_timestamps.enabled``.
-    """
-    if not isinstance(user_config, dict):
-        return False
-    gw = user_config.get("gateway")
-    if not isinstance(gw, dict):
-        return False
-    mt = gw.get("message_timestamps")
-    if isinstance(mt, dict):
-        return bool(mt.get("enabled", False))
-    # Allow a bare ``message_timestamps: true`` shorthand.
-    return bool(mt)
-
-
 def _build_gateway_agent_history(
     history: List[Dict[str, Any]],
     *,
     channel_prompt: Optional[str] = None,
-    inject_timestamps: bool = False,
 ) -> tuple[List[Dict[str, Any]], Optional[str]]:
     """Convert stored gateway transcript rows into agent replay messages.
 
@@ -725,18 +642,8 @@ def _build_gateway_agent_history(
     turns.  Keeping that context out of ``conversation_history`` avoids
     consecutive-user repair merging it with the live user turn and then hiding
     the current message behind ``history_offset`` during persistence.
-
-    When ``inject_timestamps`` is True (gateway.message_timestamps.enabled),
-    each replayed user message is rendered with a single human-readable
-    timestamp prefix from its stored metadata.
     """
 
-    from hermes_time import get_timezone as _get_msg_tz
-    from gateway.message_timestamps import (
-        render_user_content_with_timestamp as _render_msg_ts,
-    )
-
-    _msg_tz = _get_msg_tz()
     agent_history: List[Dict[str, Any]] = []
     observed_group_context: List[str] = []
     separate_observed_context = _uses_telegram_observed_group_context(channel_prompt)
@@ -756,8 +663,6 @@ def _build_gateway_agent_history(
             continue
 
         content = msg.get("content")
-        if inject_timestamps and role == "user" and isinstance(content, str):
-            content = _render_msg_ts(content, msg.get("timestamp"), tz=_msg_tz)
         if separate_observed_context and msg.get("observed") and role == "user" and content:
             observed_group_context.append(str(content).strip())
             continue
@@ -2016,42 +1921,9 @@ def _format_gateway_process_notification(evt: dict) -> "str | None":
         text += "]"
         return text
 
-    if evt_type == "async_delegation":
-        # Reuse the shared rich formatter (self-contained task-source block).
-        from tools.process_registry import format_process_notification
-        return format_process_notification(evt)
-
     return None
 
 
-def _drain_gateway_watch_events(completion_queue) -> "list[dict]":
-    """Drain gateway-owned watch events without spinning on requeued events.
-
-    Watch events are handled by the post-turn gateway drain. Process
-    completions are owned by their per-process watcher task, and async
-    delegation completions are owned by ``_async_delegation_watcher``.
-    Requeueing async events inside ``while not queue.empty()`` would make the
-    loop non-terminating, so detach the current batch first, then requeue any
-    events this drain does not own after the queue is empty.
-    """
-    watch_events: list[dict] = []
-    requeue: list[dict] = []
-    while not completion_queue.empty():
-        try:
-            evt = completion_queue.get_nowait()
-        except Exception:
-            break
-        evt_type = evt.get("type", "completion")
-        if evt_type in {"watch_match", "watch_disabled"}:
-            watch_events.append(evt)
-        elif evt_type == "async_delegation":
-            requeue.append(evt)
-        # else: process completion events are handled by the watcher task
-    for evt in requeue:
-        completion_queue.put(evt)
-    return watch_events
-
-
 # Module-level weak reference to the active GatewayRunner instance.
 # Used by tools (e.g. send_message) that need to route through a live
 # adapter for plugin platforms.  Set in GatewayRunner.__init__().
@@ -5481,12 +5353,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         # turn so the agent kicks off the new chat.
         asyncio.create_task(self._handoff_watcher())
 
-        # Start background async-delegation watcher — drains completion events
-        # from delegate_task(background=true) subagents and injects each
-        # result back into its originating session as a new turn, covering the
-        # idle case where the subagent finishes with no agent turn running.
-        asyncio.create_task(self._async_delegation_watcher())
-
         logger.info("Press Ctrl+C to stop")
         
         return True
@@ -6123,16 +5989,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                         )
                 except Exception as _e:
                     logger.debug("process_registry.kill_all (%s) error: %s", phase, _e)
-                try:
-                    from tools.async_delegation import interrupt_all as _interrupt_async
-                    _async_n = _interrupt_async(reason=f"gateway shutdown ({phase})")
-                    if _async_n:
-                        logger.info(
-                            "Shutdown (%s): interrupted %d background delegation(s)",
-                            phase, _async_n,
-                        )
-                except Exception as _e:
-                    logger.debug("async interrupt_all (%s) error: %s", phase, _e)
                 try:
                     from tools.terminal_tool import cleanup_all_environments
                     cleanup_all_environments()
@@ -8292,12 +8148,10 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         _msg_start_time = time.time()
         _platform_name = source.platform.value if hasattr(source.platform, "value") else str(source.platform)
         _msg_preview = (event.text or "")[:80].replace("\n", " ")
-        _reply_id = getattr(event, "reply_to_message_id", None)
-        _reply_txt = (getattr(event, "reply_to_text", None) or "")[:80].replace("\n", " ")
         logger.info(
-            "inbound message: platform=%s user=%s chat=%s msg=%r reply_to_id=%s reply_to_text=%r",
+            "inbound message: platform=%s user=%s chat=%s msg=%r",
             _platform_name, source.user_name or source.user_id or "unknown",
-            source.chat_id or "unknown", _msg_preview, _reply_id, _reply_txt,
+            source.chat_id or "unknown", _msg_preview,
         )
 
         # Get or create session
@@ -8411,8 +8265,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         
         # Read privacy.redact_pii from config (re-read per message)
         _redact_pii = False
-        persist_user_message = None
-        persist_user_timestamp = None
         try:
             _pcfg = _load_gateway_config()
             _redact_pii = bool((_pcfg.get("privacy") or {}).get("redact_pii", False))
@@ -8937,42 +8789,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         if message_text is None:
             return
 
-        # Capture the platform event time as message metadata and keep the
-        # persisted transcript clean (strip any leading timestamp prefix).
-        # This runs regardless of the toggle so storage stays clean and the
-        # send-time is preserved. Only the in-context RENDER (prepending the
-        # human-readable prefix the model sees) is gated behind
-        # gateway.message_timestamps.enabled — default OFF.
-        try:
-            from hermes_time import get_timezone as _get_evt_tz
-            from gateway.message_timestamps import (
-                coerce_message_timestamp as _coerce_msg_ts,
-                render_user_content_with_timestamp as _render_msg_ts,
-                strip_leading_message_timestamps as _strip_msg_ts,
-            )
-            _evt_tz = _get_evt_tz()
-            _evt_ts = getattr(event, "timestamp", None)
-            if message_text and isinstance(message_text, str):
-                _clean_message_text, _embedded_ts = _strip_msg_ts(
-                    message_text, tz=_evt_tz)
-                persist_user_message = _clean_message_text
-                _event_epoch = _coerce_msg_ts(_evt_ts, tz=_evt_tz)
-                persist_user_timestamp = (
-                    _event_epoch if _event_epoch is not None else _embedded_ts
-                )
-                if _message_timestamps_enabled(_load_gateway_config()):
-                    message_text = _render_msg_ts(
-                        _clean_message_text,
-                        persist_user_timestamp,
-                        tz=_evt_tz,
-                    )
-                else:
-                    # Toggle off: model sees the clean message; the timestamp
-                    # is still stored as metadata for later opt-in.
-                    message_text = _clean_message_text
-        except Exception as _ts_err:
-            logger.debug("Message timestamp injection failed (non-fatal): %s", _ts_err)
-
         # Bind this gateway run generation to the adapter's active-session
         # event so deferred post-delivery callbacks can be released by the
         # same run that registered them.
@@ -9006,8 +8822,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                 run_generation=run_generation,
                 event_message_id=self._reply_anchor_for_event(event),
                 channel_prompt=event.channel_prompt,
-                persist_user_message=persist_user_message,
-                persist_user_timestamp=persist_user_timestamp,
             )
 
             # Stop persistent typing indicator now that the agent is done
@@ -9115,24 +8929,17 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     source, session_entry, reason="agent-result-compression",
                 )
 
-            # Prepend reasoning/thinking if display is enabled (per-platform).
-            # Mattermost requires explicit per-platform opt-in because this is
-            # scratch text, not ordinary final-answer content.
+            # Prepend reasoning/thinking if display is enabled (per-platform)
             try:
-                _show_reasoning_effective = _resolve_gateway_display_bool(
+                from gateway.display_config import resolve_display_setting as _rds
+                _show_reasoning_effective = _rds(
                     _load_gateway_config(),
                     _platform_config_key(source.platform),
                     "show_reasoning",
-                    default=bool(getattr(self, "_show_reasoning", False)),
-                    platform=source.platform,
-                    require_platform_override_for={Platform.MATTERMOST},
+                    getattr(self, "_show_reasoning", False),
                 )
             except Exception:
-                _show_reasoning_effective = (
-                    False
-                    if source.platform == Platform.MATTERMOST
-                    else getattr(self, "_show_reasoning", False)
-                )
+                _show_reasoning_effective = getattr(self, "_show_reasoning", False)
             if _show_reasoning_effective and response and not _intentional_silence:
                 last_reasoning = agent_result.get("last_reasoning")
                 if last_reasoning:
@@ -9188,17 +8995,18 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                 logger.error("Process watcher setup error: %s", e)
 
             # Drain watch pattern notifications that arrived during the agent run.
-            # Watch events and completions share the same queue; process
-            # completions are already handled by the per-process watcher task
-            # above, so we only inject watch-type events here.
-            #
-            # Async-delegation completions ALSO ride this shared queue but are
-            # owned by the dedicated _async_delegation_watcher (started at
-            # boot), which covers both the idle and post-turn cases with a
-            # single consumer — so we leave them on the queue here.
+            # Watch events and completions share the same queue; completions are
+            # already handled by the per-process watcher task above, so we only
+            # inject watch-type events here.
             try:
                 from tools.process_registry import process_registry as _pr
-                _watch_events = _drain_gateway_watch_events(_pr.completion_queue)
+                _watch_events = []
+                while not _pr.completion_queue.empty():
+                    evt = _pr.completion_queue.get_nowait()
+                    evt_type = evt.get("type", "completion")
+                    if evt_type in {"watch_match", "watch_disabled"}:
+                        _watch_events.append(evt)
+                    # else: completion events are handled by the watcher task
                 for evt in _watch_events:
                     synth_text = _format_gateway_process_notification(evt)
                     if synth_text:
@@ -9299,7 +9107,7 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     "Your next message will start a fresh session."
                 )
 
-            ts = time.time()  # Unix epoch float — consistent with DB storage
+            ts = datetime.now().isoformat()
             
             # If this is a fresh session (no history), write the full tool
             # definitions as the first entry so the transcript is self-describing
@@ -9335,19 +9143,7 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                 # message so the next message can load a transcript that
                 # reflects what was said.  Skip the assistant error text since
                 # it's a gateway-generated hint, not model output. (#7100)
-                _user_entry = {
-                    "role": "user",
-                    "content": (
-                        persist_user_message
-                        if persist_user_message is not None
-                        else message_text
-                    ),
-                    "timestamp": (
-                        persist_user_timestamp
-                        if persist_user_timestamp is not None
-                        else ts
-                    ),
-                }
+                _user_entry = {"role": "user", "content": message_text, "timestamp": ts}
                 if event.message_id:
                     _user_entry["message_id"] = str(event.message_id)
                 self.session_store.append_to_transcript(
@@ -9361,19 +9157,7 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
 
                 # If no new messages found (edge case), fall back to simple user/assistant
                 if not new_messages:
-                    _user_entry = {
-                        "role": "user",
-                        "content": (
-                            persist_user_message
-                            if persist_user_message is not None
-                            else message_text
-                        ),
-                        "timestamp": (
-                            persist_user_timestamp
-                            if persist_user_timestamp is not None
-                            else ts
-                        ),
-                    }
+                    _user_entry = {"role": "user", "content": message_text, "timestamp": ts}
                     if event.message_id:
                         _user_entry["message_id"] = str(event.message_id)
                     self.session_store.append_to_transcript(
@@ -9498,26 +9282,13 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                         _recent_transcript = []
                     for _msg in reversed(_recent_transcript[-10:]):
                         if _msg.get("role") == "user":
-                            _expected_user_content = (
-                                persist_user_message
-                                if persist_user_message is not None
-                                else message_text
-                            )
-                            _already_persisted = (_msg.get("content") == _expected_user_content)
+                            _already_persisted = (_msg.get("content") == message_text)
                             break
                     if not _already_persisted:
                         _user_entry = {
                             "role": "user",
-                            "content": (
-                                persist_user_message
-                                if persist_user_message is not None
-                                else message_text
-                            ),
-                            "timestamp": (
-                                persist_user_timestamp
-                                if persist_user_timestamp is not None
-                                else time.time()
-                            ),
+                            "content": message_text,
+                            "timestamp": datetime.now().isoformat(),
                         }
                         if getattr(event, "message_id", None):
                             _user_entry["message_id"] = str(event.message_id)
@@ -12494,74 +12265,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         except Exception as e:
             logger.error("Watch notification injection error: %s", e)
 
-    def _enrich_async_delegation_routing(self, evt: dict) -> None:
-        """Fill platform/chat_id/thread_id/chat_type on an async-delegation event.
-
-        Async-delegation completion events only carry ``session_key`` (the
-        daemon worker has no access to the per-message routing metadata the
-        terminal background watcher captures at spawn time). Parse the
-        session_key into the routing fields ``_build_process_event_source``
-        expects. Best-effort: a CLI-origin event (empty session_key) is left
-        as-is and simply won't route on the gateway.
-        """
-        if evt.get("platform"):
-            return  # already enriched
-        parsed = _parse_session_key(evt.get("session_key", "") or "")
-        if not parsed:
-            return
-        evt["platform"] = parsed.get("platform", "")
-        evt["chat_type"] = parsed.get("chat_type", "")
-        evt["chat_id"] = parsed.get("chat_id", "")
-        if parsed.get("thread_id"):
-            evt["thread_id"] = parsed["thread_id"]
-
-    async def _async_delegation_watcher(self, interval: float = 2.0) -> None:
-        """Drain async-delegation completions and inject them as new turns.
-
-        Background subagents (``delegate_task(background=true)``) run on the
-        async-delegation daemon executor — they have no per-process watcher
-        task, so their completion events would only be seen by the post-turn
-        queue drain. This watcher covers the IDLE case: when a background
-        subagent finishes while no agent turn is running, its result still
-        re-enters the originating session promptly.
-
-        Mirrors the CLI's idle ``process_loop`` drain. Stays silent when the
-        queue has nothing for us; ignores non-async event types (those are
-        handled by ``_run_process_watcher`` / the post-turn drain).
-        """
-        await asyncio.sleep(3)  # let platforms finish connecting
-        from tools.process_registry import process_registry as _pr
-        while self._running:
-            try:
-                # Peek the queue for async-delegation events. We must NOT
-                # consume watch/completion events here (other drains own them),
-                # so requeue anything that isn't ours.
-                requeue = []
-                async_events = []
-                while not _pr.completion_queue.empty():
-                    try:
-                        evt = _pr.completion_queue.get_nowait()
-                    except Exception:
-                        break
-                    if evt.get("type") == "async_delegation":
-                        async_events.append(evt)
-                    else:
-                        requeue.append(evt)
-                for evt in requeue:
-                    _pr.completion_queue.put(evt)
-                for evt in async_events:
-                    self._enrich_async_delegation_routing(evt)
-                    synth_text = _format_gateway_process_notification(evt)
-                    if not synth_text:
-                        continue
-                    try:
-                        await self._inject_watch_notification(synth_text, evt)
-                    except Exception as e:
-                        logger.error("Async delegation injection error: %s", e)
-            except Exception as e:
-                logger.debug("Async delegation watcher error: %s", e)
-            await asyncio.sleep(interval)
-
     async def _run_process_watcher(self, watcher: dict) -> None:
         """
         Periodically check a background process and push updates to the user.
@@ -13712,8 +13415,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         _interrupt_depth: int = 0,
         event_message_id: Optional[str] = None,
         channel_prompt: Optional[str] = None,
-        persist_user_message: Optional[str] = None,
-        persist_user_timestamp: Optional[float] = None,
     ) -> Dict[str, Any]:
         """
         Run the agent with the given message and context.
@@ -13796,8 +13497,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
             if _env_tp and not _tool_progress_configured
             else (_resolved_tp or _env_tp or "all")
         )
-        # Tool progress grouping: "accumulate" (edit one bubble) or "separate" (one msg per tool)
-        progress_grouping = resolve_display_setting(user_config, platform_key, "tool_progress_grouping") or "accumulate"
         # Disable tool progress for webhooks - they don't support message editing,
         # so each progress line would be sent as a separate message.
         from gateway.config import Platform
@@ -13807,32 +13506,18 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         # in chat platforms while opting into concise mid-turn updates.
         interim_assistant_messages_enabled = (
             source.platform != Platform.WEBHOOK
-            and _resolve_gateway_display_bool(
-                user_config,
-                platform_key,
-                "interim_assistant_messages",
-                default=True,
-                platform=source.platform,
-                require_platform_override_for={Platform.MATTERMOST},
+            and bool(
+                resolve_display_setting(
+                    user_config,
+                    platform_key,
+                    "interim_assistant_messages",
+                    True,
+                )
             )
         )
-        # thinking_progress is independent — if enabled, we need the progress
-        # queue even when tool_progress is off (thinking relay uses same infra).
-        # Mattermost requires a per-platform opt-in: global scratch-text display
-        # is too easy to leak into busy public threads.
-        _thinking_enabled = _resolve_gateway_display_bool(
-            user_config,
-            platform_key,
-            "thinking_progress",
-            default=False,
-            platform=source.platform,
-            require_platform_override_for={Platform.MATTERMOST},
-        )
-        needs_progress_queue = tool_progress_enabled or _thinking_enabled
-
-
+        
         # Queue for progress messages (thread-safe)
-        progress_queue = queue.Queue() if needs_progress_queue else None
+        progress_queue = queue.Queue() if tool_progress_enabled else None
         last_tool = [None]  # Mutable container for tracking in closure
         last_progress_msg = [None]  # Track last message for dedup
         repeat_count = [0]  # How many times the same message repeated
@@ -13938,24 +13623,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     logger.debug("tool-progress onboarding hint failed: %s", _hint_err)
                 return
 
-            # "_thinking" is assistant scratch text between tool calls.  It
-            # is never ordinary tool progress: only relay it when the platform
-            # explicitly opted into thinking_progress.  Handle both legacy
-            # callback shapes: ("_thinking", text) and
-            # ("reasoning.available", "_thinking", text, ...).
-            if event_type == "_thinking" or tool_name == "_thinking":
-                if not _thinking_enabled:
-                    return
-                thinking_text = preview if tool_name == "_thinking" else tool_name
-                msg = f"💬 {thinking_text}" if thinking_text else None
-                if msg:
-                    progress_queue.put(msg)
-                return
-
-            # If tool_progress is off, only _thinking passes through (above).
-            # Regular tool calls are suppressed.
-            if not tool_progress_enabled:
-                return
 
             # Only act on tool.started events (ignore tool.completed, reasoning.available, etc.)
             if event_type not in {"tool.started",}:
@@ -14101,9 +13768,10 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
         # - Feishu only honors reply_in_thread when sending a reply, so topic
         #   progress uses the triggering event message as the reply target
         # - Other platforms should use explicit source.thread_id only
-        _progress_thread_id = _resolve_progress_thread_id(
-            source.platform, source.thread_id, event_message_id,
-        )
+        if source.platform == Platform.SLACK:
+            _progress_thread_id = source.thread_id or event_message_id
+        else:
+            _progress_thread_id = source.thread_id
         _progress_metadata = (
             self._thread_metadata_for_source(source, event_message_id)
             if _progress_thread_id == source.thread_id
@@ -14136,7 +13804,7 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
 
             progress_lines = []      # Accumulated tool lines for the CURRENT editable bubble
             progress_msg_id = None   # ID of the current progress message to edit
-            can_edit = progress_grouping != "separate"  # "separate" = one message per tool (pre-v0.9 behavior)
+            can_edit = True          # False once an edit fails (platform doesn't support it)
             _last_edit_ts = 0.0      # Throttle edits to avoid Telegram flood control
             _PROGRESS_EDIT_INTERVAL = 1.5  # Minimum seconds between edits
 
@@ -14482,17 +14150,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                 log_message="agent:step hook scheduling error",
             )
 
-        # Bridge sync event_callback → async hooks.emit for lifecycle events
-        # (e.g. session:compress fires after context compression splits a session)
-        def _event_callback_sync(event_type: str, context: dict) -> None:
-            try:
-                asyncio.run_coroutine_threadsafe(
-                    _hooks_ref.emit(event_type, context),
-                    _loop_for_step,
-                )
-            except Exception as _e:
-                logger.debug("event_callback hook error: %s", _e)
-
         # Bridge sync status_callback → async adapter.send for context pressure
         _status_adapter = self.adapters.get(source.platform)
         _status_chat_id = source.chat_id
@@ -14827,14 +14484,15 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
             agent.stream_delta_callback = _stream_delta_cb
             agent.interim_assistant_callback = _interim_assistant_cb if _want_interim_messages else None
             agent.status_callback = _status_callback_sync
+
             # Credits / out-of-band notices (usage bands, depletion, restored).
             # Messaging has no persistent status bar, so each notice is a
             # standalone push: render to a single plaintext line and deliver via
             # the shared _deliver_platform_notice rail (honors private/public +
             # thread metadata). Fires from the agent's sync worker thread, so we
-            # hop onto the gateway loop with safe_schedule_threadsafe - same
+            # hop onto the gateway loop with safe_schedule_threadsafe — same
             # pattern as _status_callback_sync. The fired-once latch lives on the
-            # cached agent and persists across turns, so a band crosses -> one
+            # cached agent and persists across turns, so a band crosses → one
             # push (no per-turn re-nag). Recovery ("✓ Credit access restored")
             # rides the same show path (it's emitted as a success notice, not a
             # clear). The clear callback is a no-op: a sent platform message
@@ -14858,7 +14516,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
 
             agent.notice_callback = _notice_callback_sync
             agent.notice_clear_callback = None
-            agent.event_callback = _event_callback_sync
             agent.reasoning_config = reasoning_config
             agent.service_tier = self._service_tier
             agent.request_overrides = turn_route.get("request_overrides") or {}
@@ -14914,14 +14571,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     _pdc = getattr(_status_adapter, "_post_delivery_callbacks", None)
                     if _pdc is not None:
                         _pdc[session_key] = _release_bg_review_messages
-            # Memory update notifications in chat.  Config: display.memory_notifications
-            #   off     — no chat notification (still logged to stdout)
-            #   on      — generic "💾 Memory updated" (default)
-            #   verbose — content preview: "💾 Memory ➕ Hermes Repo..."
-            _mem_notif = user_config.get("display", {}).get("memory_notifications")
-            if isinstance(_mem_notif, bool):
-                _mem_notif = "on" if _mem_notif else "off"
-            agent.memory_notifications = str(_mem_notif).lower() if _mem_notif else "on"
 
             # ------------------------------------------------------------------
             # Clarify callback: present a clarify prompt and block on a response.
@@ -14998,10 +14647,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
 
             agent.clarify_callback = _clarify_callback_sync
 
-            # Show assistant thinking between tool calls — independent of
-            # tool_progress mode. Mattermost needs an explicit per-platform
-            # opt-in so global scratch-text display does not leak into threads.
-            agent.thinking_progress = _thinking_enabled
             # Store agent reference for interrupt support
             agent_holder[0] = agent
             # Capture the full tool definitions for transcript logging
@@ -15024,7 +14669,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
             agent_history, observed_group_context = _build_gateway_agent_history(
                 history,
                 channel_prompt=channel_prompt,
-                inject_timestamps=_message_timestamps_enabled(_load_gateway_config()),
             )
             
             # Collect MEDIA paths already in history so we can exclude them
@@ -15141,8 +14785,7 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
             # Keep real user text separate from API-only recovery guidance.  If
             # an auto-continue note is prepended below, persist the original
             # message so stale guidance never replays as user-authored text.
-            _persist_user_message_override: Optional[Any] = persist_user_message
-            _persist_user_timestamp_override: Optional[float] = persist_user_timestamp
+            _persist_user_message_override: Optional[Any] = None
 
             # Prepend pending model switch note so the model knows about the switch
             _pending_notes = getattr(self, '_pending_model_notes', {})
@@ -15282,8 +14925,6 @@ class GatewayRunner(GatewayAuthorizationMixin, GatewayKanbanWatchersMixin, Gatew
                     _conversation_kwargs["persist_user_message"] = _persist_user_message_override
                 elif observed_group_context:
                     _conversation_kwargs["persist_user_message"] = message
-                if _persist_user_timestamp_override is not None:
-                    _conversation_kwargs["persist_user_timestamp"] = _persist_user_timestamp_override
                 result = agent.run_conversation(_api_run_message, **_conversation_kwargs)
             finally:
                 unregister_gateway_notify(_approval_session_key)

gateway/session.py

@@ -1322,7 +1322,6 @@ class SessionStore:
                         message.get("platform_message_id") or message.get("message_id")
                     ),
                     observed=bool(message.get("observed")),
-                    timestamp=message.get("timestamp"),
                 )
             except Exception as e:
                 logger.debug("Session DB operation failed: %s", e)

gateway/stream_consumer.py

@@ -197,30 +197,6 @@ class GatewayStreamConsumer:
         # this response and route through edit-based for graceful degradation.
         self._draft_failures = 0
 
-    def _metadata_for_send(
-        self,
-        *,
-        final: bool = False,
-        expect_edits: bool = False,
-    ) -> dict | None:
-        """Return per-send metadata for stream-created messages.
-
-        Mattermost treats notify-worthy sends as user-visible final content
-        when deciding whether a broken thread root may fall back flat.  Preview
-        and progress sends keep their original metadata and remain thread-strict.
-
-        ``expect_edits`` preserves the upstream Telegram streaming contract:
-        preview messages that may be edited later must stay on the editable
-        legacy send path, while fresh/fallback final sends can still use richer
-        final-message delivery.
-        """
-        meta = dict(self.metadata) if self.metadata else {}
-        if expect_edits:
-            meta["expect_edits"] = True
-        if final:
-            meta["notify"] = True
-        return meta or None
-
     @property
     def already_sent(self) -> bool:
         """True if at least one message was sent or edited during the run."""
@@ -537,11 +513,7 @@ class GatewayStreamConsumer:
                         chunks_delivered = False
                         reply_to = self._message_id or self._initial_reply_to_id
                         for chunk in chunks:
-                            new_id = await self._send_new_chunk(
-                                chunk,
-                                reply_to,
-                                final=got_done,
-                            )
+                            new_id = await self._send_new_chunk(chunk, reply_to)
                             if new_id is not None and new_id != reply_to:
                                 chunks_delivered = True
                         self._accumulated = ""
@@ -777,13 +749,7 @@ class GatewayStreamConsumer:
         # Strip trailing whitespace/newlines but preserve leading content
         return cleaned.rstrip()
 
-    async def _send_new_chunk(
-        self,
-        text: str,
-        reply_to_id: Optional[str],
-        *,
-        final: bool = False,
-    ) -> Optional[str]:
+    async def _send_new_chunk(self, text: str, reply_to_id: Optional[str]) -> Optional[str]:
         """Send a new message chunk, optionally threaded to a previous message.
 
         Returns the message_id so callers can thread subsequent chunks.
@@ -792,11 +758,15 @@ class GatewayStreamConsumer:
         if not text.strip():
             return reply_to_id
         try:
+            meta = dict(self.metadata) if self.metadata else {}
+            # This chunk becomes the next edit target — adapters that support
+            # rich final sends (Telegram) must keep it on the editable path.
+            meta["expect_edits"] = True
             result = await self.adapter.send(
                 chat_id=self.chat_id,
                 content=text,
                 reply_to=reply_to_id,
-                metadata=self._metadata_for_send(final=final, expect_edits=True),
+                metadata=meta,
             )
             if result.success and result.message_id:
                 self._message_id = str(result.message_id)
@@ -915,7 +885,7 @@ class GatewayStreamConsumer:
                 result = await self.adapter.send(
                     chat_id=self.chat_id,
                     content=chunk,
-                    metadata=self._metadata_for_send(final=True),
+                    metadata=self.metadata,
                 )
                 if result.success:
                     break
@@ -1272,7 +1242,7 @@ class GatewayStreamConsumer:
             result = await self.adapter.send(
                 chat_id=self.chat_id,
                 content=text,
-                metadata=self._metadata_for_send(final=True),
+                metadata=self.metadata,
             )
         except Exception as e:
             logger.debug("Fresh-final send failed, falling back to edit: %s", e)
@@ -1562,10 +1532,7 @@ class GatewayStreamConsumer:
                     chat_id=self.chat_id,
                     content=text,
                     reply_to=self._initial_reply_to_id,
-                    metadata=self._metadata_for_send(
-                        final=finalize,
-                        expect_edits=True,
-                    ),
+                    metadata={**(self.metadata or {}), "expect_edits": True},
                 )
                 if result.success:
                     if result.message_id:

hermes_cli/auth.py

@@ -3806,26 +3806,6 @@ def resolve_codex_runtime_credentials(
                 "last_refresh": None,
                 "auth_mode": "chatgpt",
             }
-        pool_rate_limit = _codex_pool_rate_limit_status()
-        if pool_rate_limit:
-            reset_at = pool_rate_limit.get("reset_at")
-            if isinstance(reset_at, (int, float)) and reset_at > time.time():
-                remaining = int(reset_at - time.time())
-                message = (
-                    f"Codex provider quota exhausted (429); retry after {remaining}s. "
-                    "Credentials are still valid."
-                )
-            else:
-                message = (
-                    "Codex provider quota exhausted (429). Credentials are still valid; "
-                    "retry after the usage limit resets."
-                )
-            raise AuthError(
-                message,
-                provider="openai-codex",
-                code=CODEX_RATE_LIMITED_CODE,
-                relogin_required=False,
-            )
         if read_error is not None:
             raise read_error
         raise AuthError(
@@ -3872,79 +3852,6 @@ def resolve_codex_runtime_credentials(
     }
 
 
-def _codex_pool_rate_limit_status() -> Optional[Dict[str, Any]]:
-    """Return metadata for a pool-only Codex credential in quota cooldown."""
-    def _parse_reset_at(value: Any) -> Optional[float]:
-        if value is None or value == "":
-            return None
-        if isinstance(value, (int, float)):
-            numeric = float(value)
-            if numeric <= 0:
-                return None
-            return numeric / 1000.0 if numeric > 1_000_000_000_000 else numeric
-        if isinstance(value, str):
-            raw = value.strip()
-            if not raw:
-                return None
-            try:
-                numeric = float(raw)
-            except ValueError:
-                numeric = None
-            if numeric is not None:
-                return numeric / 1000.0 if numeric > 1_000_000_000_000 else numeric
-            try:
-                return datetime.fromisoformat(raw.replace("Z", "+00:00")).timestamp()
-            except ValueError:
-                return None
-        return None
-
-    try:
-        with _auth_store_lock():
-            auth_store = _load_auth_store()
-        pool = auth_store.get("credential_pool")
-        if not isinstance(pool, dict):
-            return None
-        entries = pool.get("openai-codex")
-        if not isinstance(entries, list):
-            return None
-        now = time.time()
-        for entry in entries:
-            if not isinstance(entry, dict):
-                continue
-            token = entry.get("access_token")
-            if not isinstance(token, str) or not token.strip():
-                continue
-            if entry.get("last_status") != "exhausted":
-                continue
-            code = entry.get("last_error_code")
-            reason = str(entry.get("last_error_reason") or "").lower()
-            message = str(entry.get("last_error_message") or "").lower()
-            is_rate_limited = (
-                code == 429
-                or "rate_limit" in reason
-                or "usage_limit" in reason
-                or "quota" in reason
-                or "rate limit" in message
-                or "usage limit" in message
-                or "quota" in message
-            )
-            if not is_rate_limited:
-                continue
-            reset_at = _parse_reset_at(entry.get("last_error_reset_at"))
-            if reset_at is not None and reset_at <= now:
-                continue
-            return {
-                "label": entry.get("label"),
-                "last_refresh": entry.get("last_refresh"),
-                "reset_at": reset_at,
-                "reason": entry.get("last_error_reason"),
-                "message": entry.get("last_error_message"),
-            }
-    except Exception:
-        logger.debug("Codex pool rate-limit lookup failed", exc_info=True)
-    return None
-
-
 def _pool_codex_access_token() -> str:
     """Return the most-recent usable access_token from the openai-codex pool.
 
@@ -5856,24 +5763,18 @@ def _snapshot_nous_pool_status() -> Dict[str, Any]:
 # subscription-feature checks) call it many times per render — `hermes tools` → "All Platforms"
 # was firing the refresh ~31× during one menu paint, racking up >13s of HTTP and burning
 # single-use refresh tokens. Cache the snapshot for a few seconds, keyed on the auth.json
-# path + mtime so that profile switches do not share a process memo and
-# `hermes auth login/logout/add/remove` invalidate naturally on the next call.
+# mtime so that `hermes auth login/logout/add/remove` invalidate naturally on the next call.
 _NOUS_AUTH_STATUS_CACHE_TTL = 15.0  # seconds
-_nous_auth_status_cache: Optional[Tuple[float, str, Optional[float], Dict[str, Any]]] = None
+_nous_auth_status_cache: Optional[Tuple[float, Optional[float], Dict[str, Any]]] = None
 
 
-def _auth_file_cache_key() -> Tuple[str, Optional[float]]:
-    auth_file = _auth_file_path()
+def _auth_file_mtime() -> Optional[float]:
     try:
-        auth_file_key = str(auth_file.resolve(strict=False))
-    except Exception:
-        auth_file_key = str(auth_file)
-    try:
-        return auth_file_key, auth_file.stat().st_mtime
+        return _auth_file_path().stat().st_mtime
     except FileNotFoundError:
-        return auth_file_key, None
+        return None
     except Exception:
-        return auth_file_key, None
+        return None
 
 
 def invalidate_nous_auth_status_cache() -> None:
@@ -5905,19 +5806,18 @@ def get_nous_auth_status() -> Dict[str, Any]:
     """
     global _nous_auth_status_cache
     now = time.monotonic()
-    auth_file_key, mtime = _auth_file_cache_key()
+    mtime = _auth_file_mtime()
     cached = _nous_auth_status_cache
     if cached is not None:
-        cached_at, cached_auth_file_key, cached_mtime, cached_status = cached
+        cached_at, cached_mtime, cached_status = cached
         if (
-            cached_auth_file_key == auth_file_key
-            and cached_mtime == mtime
+            cached_mtime == mtime
             and (now - cached_at) < _NOUS_AUTH_STATUS_CACHE_TTL
         ):
             return dict(cached_status)
 
     status = _compute_nous_auth_status()
-    _nous_auth_status_cache = (now, auth_file_key, mtime, dict(status))
+    _nous_auth_status_cache = (now, mtime, dict(status))
     return status
 
 
@@ -6000,22 +5900,6 @@ def get_codex_auth_status() -> Dict[str, Any]:
                         "source": f"pool:{getattr(entry, 'label', 'unknown')}",
                         "api_key": api_key,
                     }
-            rate_limit = _codex_pool_rate_limit_status()
-            if rate_limit:
-                return {
-                    "logged_in": True,
-                    "auth_store": str(_auth_file_path()),
-                    "last_refresh": rate_limit.get("last_refresh"),
-                    "auth_mode": "chatgpt",
-                    "source": f"pool:{rate_limit.get('label') or 'unknown'}",
-                    "rate_limited": True,
-                    "error_code": CODEX_RATE_LIMITED_CODE,
-                    "error": (
-                        rate_limit.get("message")
-                        or "Codex provider quota exhausted; retry after the usage limit resets."
-                    ),
-                    "reset_at": rate_limit.get("reset_at"),
-                }
     except Exception:
         pass