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.

hermes_cli/config.py

@@ -863,6 +863,19 @@ DEFAULT_CONFIG = {
         # identity slot (SOUL.md). Empty by default. The HERMES_ENVIRONMENT_HINT
         # env var overrides this (build-time/container mechanism).
         "environment_hint": "",
+        # Coding posture — on interactive coding surfaces (CLI, TUI, desktop
+        # app, ACP) in a code workspace, Hermes adds a coding operating brief
+        # + a live git/workspace snapshot to the system prompt. See
+        # agent/coding_context.py.
+        #   "auto" (default) — prompt-only posture when the surface is
+        #                      interactive AND cwd is a code workspace.
+        #                      Toolsets are never touched; messaging platforms
+        #                      unaffected.
+        #   "focus"          — auto + collapse the toolset to the lean coding
+        #                      set (+ enabled MCP servers). Explicit opt-in.
+        #   "on"             — force the prompt posture everywhere.
+        #   "off"            — disable entirely.
+        "coding_context": "auto",
         # Staged inactivity warning: send a warning to the user at this
         # threshold before escalating to a full timeout.  The warning fires
         # once per run and does not interrupt the agent.  0 = disable warning.

hermes_cli/tools_config.py

@@ -1437,6 +1437,10 @@ def _get_platform_tools(
             continue
         if ts_def.get("includes"):
             continue
+        # Posture toolsets (e.g. ``coding``) are session-level selections made
+        # by agent/coding_context.py — not per-platform capabilities to recover.
+        if ts_def.get("posture"):
+            continue
         ts_tools = set(resolve_toolset(ts_key))
         if not ts_tools or not ts_tools.issubset(platform_tool_universe):
             continue