fix(vscode): persist compatible Claude modes and route Copilot CAPI (#2986)

## Description

Fixes #2492, #2028, and #2827.

Claude daemon workers consume project settings rather than reliably
inheriting wrapper environment state, while the Claude VS Code webview
cannot render deferred-tool response blocks. Separately, recent Copilot
Chat versions use the whole CAPI override for generation; the legacy
proxy override alone only sends model discovery through Headroom.

This PR carries both integrations through to the actual consumers
instead of only changing their launch-time surface configuration.

## Type of Change

- [x] Bug fix
- [ ] New feature
- [ ] Breaking change
- [ ] Documentation update
- [ ] Build / CI

## Changes Made

- Persist the resolved Claude ENABLE_TOOL_SEARCH value into project
settings for daemon workers and restore it transactionally after wrap
exits.
- Use compatibility-safe Foundry and Claude VS Code defaults while
preserving explicit user choices.
- Configure both Copilot overrideProxyUrl and overrideCapiUrl in the
reversible managed VS Code settings block.
- Route Copilot unprefixed POST /chat/completions and HTTP /responses
requests through the real compression handlers.
- Keep /responses out of the Codex WebSocket aliases because Copilot and
Codex use different WebSocket wire protocols.
- Extend wrap E2E assertions for both the Claude webview mode and
Copilot CAPI routing.

## Testing

- [x] 127 combined Claude, Copilot, route-integration, and MCP
dependency-contract tests pass.
- [x] Ruff check passes on all changed Python files.
- [x] Ruff format check passes.
- [x] Python compilation and git diff --check pass.

## Runtime Safety

Standalone Claude CLI defaults remain unchanged. Explicit Claude
tool-search values retain precedence, and project settings are restored
through the existing cleanup path. Copilot model/session helper
endpoints continue through generic passthrough, while only validated
HTTP generation paths receive explicit compression routes. Existing
Codex WebSocket behavior is unchanged.

## Review Readiness

- [x] Current main and MCP v1 compatibility retained
- [x] Worker-facing Claude persistence covered
- [x] Reversible Copilot and Claude settings behavior covered
- [x] Copilot generation routes covered at registration and proxy
integration layers
- [x] Ready for review

tests/test_cli/test_init_enable_tool_search.py

@@ -16,7 +16,8 @@ from headroom.cli import init as init_cli
 from headroom.providers.claude import install as claude_install
 
 
-def test_ensure_claude_hooks_sets_enable_tool_search(tmp_path: Path) -> None:
+def test_ensure_claude_hooks_sets_enable_tool_search(tmp_path: Path, monkeypatch) -> None:
+    monkeypatch.delenv("CLAUDE_CODE_USE_FOUNDRY", raising=False)
     settings = tmp_path / "settings.json"
     init_cli._ensure_claude_hooks(settings, profile="init-user", port=8787)
 
@@ -25,6 +26,16 @@ def test_ensure_claude_hooks_sets_enable_tool_search(tmp_path: Path) -> None:
     assert env["ENABLE_TOOL_SEARCH"] == "true"
 
 
+def test_ensure_claude_hooks_disables_tool_search_for_foundry(tmp_path: Path, monkeypatch) -> None:
+    monkeypatch.setenv("CLAUDE_CODE_USE_FOUNDRY", "1")
+    settings = tmp_path / "settings.json"
+
+    init_cli._ensure_claude_hooks(settings, profile="init-user", port=8787)
+
+    env = json.loads(settings.read_text(encoding="utf-8"))["env"]
+    assert env["ENABLE_TOOL_SEARCH"] == "false"
+
+
 def test_ensure_claude_hooks_respects_user_tool_search_value(tmp_path: Path) -> None:
     settings = tmp_path / "settings.json"
     settings.write_text(

tests/test_cli/test_wrap_claude_base_url.py

@@ -34,6 +34,29 @@ def test_write_preserves_other_env_keys(tmp_path: Path) -> None:
     assert payload["env"]["ANTHROPIC_BASE_URL"] == "http://127.0.0.1:8787"
 
 
+def test_tool_search_write_and_restore_reaches_daemon_worker_settings(tmp_path: Path) -> None:
+    path = _settings(tmp_path)
+    path.parent.mkdir(parents=True)
+    path.write_text(
+        json.dumps({"env": {"ENABLE_TOOL_SEARCH": "true", "KEEP": "1"}}),
+        encoding="utf-8",
+    )
+
+    previous = wrap_cli._write_claude_wrap_tool_search("false", settings_path=path)
+
+    assert previous == "true"
+    assert json.loads(path.read_text(encoding="utf-8"))["env"] == {
+        "ENABLE_TOOL_SEARCH": "false",
+        "KEEP": "1",
+    }
+
+    wrap_cli._restore_claude_wrap_tool_search(previous, settings_path=path)
+    assert json.loads(path.read_text(encoding="utf-8"))["env"] == {
+        "ENABLE_TOOL_SEARCH": "true",
+        "KEEP": "1",
+    }
+
+
 def test_write_returns_none_when_key_absent(tmp_path: Path) -> None:
     path = _settings(tmp_path)
     prev = wrap_cli._write_claude_wrap_base_url("http://127.0.0.1:8787", settings_path=path)

tests/test_cli/test_wrap_claude_vertex_proxy_env.py

@@ -78,6 +78,13 @@ def _invoke_wrap_claude(
 
     monkeypatch.setattr(wrap_mod, "_write_claude_wrap_base_url", fake_write_base_url)
     monkeypatch.setattr(wrap_mod, "_restore_claude_wrap_base_url", lambda *_args, **_kwargs: None)
+
+    def fake_write_tool_search(value: str, **kwargs: object) -> None:
+        captured["write_tool_search_value"] = value
+        captured["write_tool_search_kwargs"] = kwargs
+
+    monkeypatch.setattr(wrap_mod, "_write_claude_wrap_tool_search", fake_write_tool_search)
+    monkeypatch.setattr(wrap_mod, "_restore_claude_wrap_tool_search", lambda *_a, **_k: None)
     monkeypatch.setattr(wrap_mod, "_print_telemetry_notice", lambda: None)
 
     def fake_ensure_proxy(*args: object, **kwargs: object) -> tuple[None, int]:
@@ -209,6 +216,24 @@ def test_wrap_claude_tool_search_banner_line_still_accurate_when_active(
     assert "on-demand tool loading kept on" in output
     assert "keeps it on for this session" in output
     assert "DISABLED per your setting" not in output
+    assert _captured["write_tool_search_value"] == "true"
+
+
+def test_wrap_claude_foundry_persists_disabled_tool_search_for_workers(
+    runner: CliRunner, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    captured, output = _invoke_wrap_claude(
+        runner,
+        monkeypatch,
+        env={
+            "CLAUDE_CODE_USE_FOUNDRY": "1",
+            "ANTHROPIC_FOUNDRY_BASE_URL": "https://tenant.services.ai.azure.com/anthropic",
+        },
+    )
+
+    assert captured["child_env"]["ENABLE_TOOL_SEARCH"] == "false"
+    assert captured["write_tool_search_value"] == "false"
+    assert "on-demand tool loading DISABLED" in output
 
 
 def test_wrap_claude_vertex_passes_custom_base_url_to_proxy_before_child_redirect(

tests/test_cli/test_wrap_vscode.py

@@ -66,6 +66,7 @@ def test_wrap_vscode_no_configure_prints_transparent_settings(tmp_path: Path) ->
     assert result.exit_code == 0, result.output
     assert not path.exists()
     assert "overrideProxyUrl" in result.output
+    assert "overrideCapiUrl" in result.output
     assert "overrideAuthType" in result.output
 
 

tests/test_cli/test_wrap_vscode_claude.py

@@ -25,7 +25,7 @@ def test_wrap_vscode_claude_configures_actual_port(tmp_path: Path) -> None:
     assert result.exit_code == 0, result.output
     env = json.loads(path.read_text(encoding="utf-8"))["env"]
     assert env["ANTHROPIC_BASE_URL"].startswith("http://127.0.0.1:9999/p/")
-    assert env["ENABLE_TOOL_SEARCH"] == "true"
+    assert env["ENABLE_TOOL_SEARCH"] == "false"
     assert "Reload VS Code" in result.output
     assert captured["agent_type"] == "claude"