feat(agent): coding-context posture across CLI/TUI/desktop/ACP (#43316)

* feat(agent): coding-context posture with per-model edit-format tuning

Hermes detects when it's running in a coding context — an interactive
surface (CLI, TUI, ACP, desktop) sitting in a code workspace (git repo or
recognised project root) — and shifts into a coding posture. Outside that
(chat platforms, non-workspaces) nothing changes.

The posture is modelled as a frozen RuntimeMode selected from a small
ContextProfile registry (coding/general). A profile is data: the toolset to
collapse to, the operating brief to inject, and seams for model routing and
memory. Every domain reads the same resolved object instead of re-probing
git/config on its own:

- System prompt — RuntimeMode.system_blocks(): an operating brief (gather
  context before editing, edit through tools not chat, verify with terminal,
  cap retry loops) plus a live git/workspace snapshot, built once and baked
  into the stable prompt tier so per-conversation caching is preserved.
- Per-model edit-format tuning — the brief nudges each model family toward
  the patch mode it handles best: OpenAI/Codex toward mode='patch' (V4A
  multi-file diffs), Anthropic toward mode='replace' (string replacement).
  The model id rides on RuntimeMode; unknown families keep neutral wording.
- Skill index — non-coding skill categories are pruned from the prompt's
  skill index (discovery-only; skills_list/skill_view still reach the full
  catalog, with a disclosure note).
- Toolset — only under the opt-in 'focus' mode does the posture collapse to
  the coding toolset + enabled MCP servers; the default posture is
  prompt-only and never overrides configured toolsets.

Activation via agent.coding_context: auto (default), focus, on, off.
Subagents inherit the posture for free via toolset inheritance + the shared
prompt builder. Detection is not memoized so a long-lived gateway/TUI
process can't pin a stale posture across working directories.

* feat(agent): cover new-file authoring in the coding edit-format nudge

The per-model edit-format guidance only addressed editing existing code
(patch mode='patch' vs 'replace'), but authoring a brand-new file —
write_file, not patch — is a large fraction of real coding work and the
nudge was silent on it. Surfaced when building a single-file artifact where
the dominant operation was write_file and the steering offered no guidance.

Both family lines now lead with "author new files with write_file; for
edits to existing code prefer ...". Tests assert write_file appears in each
family's brief; unknown families still get neutral wording.

* docs(agent): correct memoization docstring + clarify TUI config-load asymmetry

* feat(agent): sharpen the coding posture — verify-loop facts, wider edit steering, $HOME guard

Tuning pass on the coding posture from dogfooding it as a harness:

- Workspace snapshot now hands the model its verify loop up front:
  detected manifests + package manager (lockfile sniff), the exact
  verify commands (package.json scripts, Makefile targets,
  scripts/run_tests.sh, pytest config), and which context files
  (AGENTS.md / CLAUDE.md / .cursorrules) exist at the root. Marker-only
  (non-git) projects get the snapshot too instead of nothing. The
  "verify before claiming done" brief line was the highest-value piece
  in evals — this turns it from advice into an executable loop instead
  of making the model rediscover the test command every session. Still
  stat-cheap, size-guarded reads, built once at prompt time.

- Edit-format steering covers the families Hermes actually serves:
  Gemini and open-weight coding models (DeepSeek, Qwen, Kimi, GLM,
  Grok, Hermes, Llama, Mistral, Devstral, MiniMax) steer to
  mode='replace' — their RL scaffolds use str_replace-style editors.
  Previously only GPT/Codex and Claude families got steering; the
  models Hermes users disproportionately run all fell to neutral.

- Operating brief gains four behaviors elite harnesses encode: batch
  independent reads/searches in one turn; fix root causes and the bug
  class (sibling call paths), not the reported site; no drive-by
  refactors/renames/reformatting; never read, print, or commit secrets.
  Plus a patch-failure escalation ladder: after the same region fails
  twice, rewrite the enclosing function/file with write_file instead of
  a third patch attempt.

- $HOME dotfiles guard: a git repo rooted exactly at the home directory
  (or a marker sitting in it, e.g. a global ~/AGENTS.md) is user config,
  not a code workspace — without the guard, every session anywhere under
  a dotfiles-managed home silently flipped to the coding posture. Real
  projects under such a home still detect via their own markers/repos;
  'on' mode bypasses the guard.

toolsets.py

@@ -339,6 +339,33 @@ TOOLSETS = {
         "tools": [],
         "includes": ["web", "vision", "image_gen"]
     },
+
+    # Coding posture (base Hermes — CLI/TUI/desktop/ACP). Auto-selected in a
+    # code workspace; see agent/coding_context.py. Keeps everything you reach
+    # for while pairing on code and drops the rest (messaging, tts, image_gen,
+    # spotify, home-assistant, cron, computer-use).
+    "coding": {
+        "description": "Coding-focused toolset: files, terminal, search, web docs, skills, todo, delegate, vision, browser",
+        "tools": [
+            "web_search", "web_extract",
+            "terminal", "process", "read_terminal",
+            "read_file", "write_file", "patch", "search_files",
+            "vision_analyze",
+            "skills_list", "skill_view", "skill_manage",
+            "browser_navigate", "browser_snapshot", "browser_click",
+            "browser_type", "browser_scroll", "browser_back",
+            "browser_press", "browser_get_images",
+            "browser_vision", "browser_console", "browser_cdp", "browser_dialog",
+            "todo", "memory",
+            "session_search", "clarify",
+            "execute_code", "delegate_task",
+        ],
+        "includes": [],
+        # Posture toolset: selected per-session by agent/coding_context.py,
+        # never auto-recovered into per-platform tool config (see the
+        # non-configurable-toolset recovery loop in hermes_cli/tools_config.py).
+        "posture": True,
+    },
     
     # ==========================================================================
     # Full Hermes toolsets (CLI + messaging platforms)