refactor(autonomy): rename automation profile task flags to spec names

Renamed all 11 task-type confidence threshold fields in AutomationProfile
from phase-transition semantics to spec-defined task-type semantics.
Updated all 8 built-in profiles, CLI formatting, YAML schema, services,
and all Behave/Robot tests referencing the old field names.

Post-review fixes:
- Fixed 24 stale old field names in M6 fixture files
  (automation_profiles.json, autonomy_guardrails.json)
- Added model_validator(mode='before') to detect legacy field names
  and raise actionable ValueError with rename mapping
- Added semantic bridge comments in PlanLifecycleService mapping
  task-type thresholds to phase-transition gates
- Added threshold_field to structured log messages for observability
- Restored categorised CLI automation-profile show output to match
  spec (Phase Transitions / Decision Automation / Self-Repair /
  Execution Controls) instead of flat list
- Added missing access_network field to spec show output examples
  (Rich, Plain, JSON, YAML variants)
- Aligned ADR-017 profile fields table to all 11 fields with
  descriptions matching spec Automatable Tasks table
- Aligned automation_profiles.md threshold descriptions with spec
- Added spec section references in phase_reversion.md, error_recovery.md,
  and plan_execute.md for field naming context
- Extended repository roundtrip test to assert all 11 threshold fields
- Fixed benchmark _make_profile() passing safety fields as top-level
  kwargs instead of via SafetyProfile sub-model (incompatible with
  extra="forbid")
- Aligned CLI JSON/YAML output structure for automation-profile show
  with the specification grouped format (phase_transitions,
  decision_automation, self_repair, execution_controls)
- Moved safety boolean fields into the Execution Controls section
  of Rich output per spec examples
- Reverted auto profile description to "Fully automatic except apply"
  per specification (line 16703, line 28406)
- Improved bridge comments in test steps with semantic context for
  threshold-to-gate mappings

ISSUES CLOSED: #902

benchmarks/automation_profile_bench.py

@@ -23,6 +23,7 @@ try:
         AutomationProfile,
         get_builtin_profile,
     )
+    from cleveragents.domain.models.core.safety_profile import SafetyProfile
 except ModuleNotFoundError:
     sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
     from cleveragents.domain.models.core.automation_guard import (
@@ -33,6 +34,7 @@ except ModuleNotFoundError:
         AutomationProfile,
         get_builtin_profile,
     )
+    from cleveragents.domain.models.core.safety_profile import SafetyProfile
 
 
 def _make_profile() -> AutomationProfile:
@@ -40,20 +42,22 @@ def _make_profile() -> AutomationProfile:
     return AutomationProfile(
         name="bench/test-profile",
         description="Benchmark profile",
-        auto_strategize=0.7,
-        auto_execute=0.5,
-        auto_apply=1.0,
-        auto_decisions_strategize=0.6,
-        auto_decisions_execute=0.8,
-        auto_validation_fix=0.3,
-        auto_strategy_revision=0.9,
-        auto_reversion_from_apply=0.4,
-        auto_child_plans=0.7,
-        auto_retry_transient=0.1,
-        auto_checkpoint_restore=0.5,
-        require_sandbox=True,
-        require_checkpoints=True,
-        allow_unsafe_tools=False,
+        decompose_task=0.7,
+        create_tool=0.5,
+        select_tool=1.0,
+        edit_code=0.6,
+        execute_command=0.8,
+        create_file=0.3,
+        delete_content=0.9,
+        access_network=0.4,
+        install_dependency=0.7,
+        modify_config=0.1,
+        approve_plan=0.5,
+        safety=SafetyProfile(
+            require_sandbox=True,
+            require_checkpoints=True,
+            allow_unsafe_tools=False,
+        ),
     )
 
 
@@ -72,17 +76,17 @@ class ProfileValidationSuite:
         """Benchmark profile with all thresholds at 1.0."""
         AutomationProfile(
             name="bench/max",
-            auto_strategize=1.0,
-            auto_execute=1.0,
-            auto_apply=1.0,
-            auto_decisions_strategize=1.0,
-            auto_decisions_execute=1.0,
-            auto_validation_fix=1.0,
-            auto_strategy_revision=1.0,
-            auto_reversion_from_apply=1.0,
-            auto_child_plans=1.0,
-            auto_retry_transient=1.0,
-            auto_checkpoint_restore=1.0,
+            decompose_task=1.0,
+            create_tool=1.0,
+            select_tool=1.0,
+            edit_code=1.0,
+            execute_command=1.0,
+            create_file=1.0,
+            delete_content=1.0,
+            access_network=1.0,
+            install_dependency=1.0,
+            modify_config=1.0,
+            approve_plan=1.0,
         )
 
 
@@ -110,9 +114,9 @@ class ProfileFromConfigSuite:
         self.config = {
             "name": "bench/from-config",
             "description": "Config benchmark",
-            "auto_strategize": 0.7,
-            "auto_execute": 0.5,
-            "auto_apply": 1.0,
+            "decompose_task": 0.7,
+            "create_tool": 0.5,
+            "select_tool": 1.0,
         }
 
     def time_profile_from_config(self) -> None:

benchmarks/automation_profile_cli_bench.py

@@ -65,17 +65,17 @@ _VALID_YAML = """\
 name: bench/test-profile
 description: Benchmark test profile
 schema_version: "1.0"
-auto_strategize: 0.5
-auto_execute: 0.5
-auto_apply: 1.0
-auto_decisions_strategize: 0.5
-auto_decisions_execute: 0.5
-auto_validation_fix: 0.5
-auto_strategy_revision: 0.5
-auto_reversion_from_apply: 0.5
-auto_child_plans: 0.5
-auto_retry_transient: 0.0
-auto_checkpoint_restore: 0.5
+decompose_task: 0.5
+create_tool: 0.5
+select_tool: 1.0
+edit_code: 0.5
+execute_command: 0.5
+create_file: 0.5
+delete_content: 0.5
+access_network: 0.5
+install_dependency: 0.5
+modify_config: 0.0
+approve_plan: 0.5
 safety:
   require_sandbox: true
   require_checkpoints: true

benchmarks/semantic_escalation_bench.py

@@ -107,7 +107,7 @@ class EscalationDecisionSuite:
             risk_assessment=0.15,
             invariant_complexity=0.2,
         )
-        self.operation = OperationContext(operation_type="auto_execute")
+        self.operation = OperationContext(operation_type="create_tool")
         self.profile_cautious = BUILTIN_PROFILES["cautious"]
         self.profile_fullauto = BUILTIN_PROFILES["full-auto"]
         self.profile_manual = BUILTIN_PROFILES["manual"]
@@ -144,11 +144,11 @@ class HistoricalTrackingSuite:
         """Set up controller with pre-populated history."""
         self.controller = AutonomyController()
         self.outcome_success = HistoricalOutcome(
-            operation_type="auto_execute",
+            operation_type="create_tool",
             succeeded=True,
         )
         self.outcome_failure = HistoricalOutcome(
-            operation_type="auto_execute",
+            operation_type="create_tool",
             succeeded=False,
         )
         # Pre-populate history
@@ -161,8 +161,8 @@ class HistoricalTrackingSuite:
 
     def time_get_success_rate(self) -> None:
         """Benchmark retrieving historical success rate."""
-        self.controller.get_historical_success_rate("auto_execute")
+        self.controller.get_historical_success_rate("create_tool")
 
     def time_get_history_count(self) -> None:
         """Benchmark retrieving history count."""
-        self.controller.get_history_count("auto_execute")
+        self.controller.get_history_count("create_tool")