devagent-physical-engine 0.11.3__tar.gz → 0.11.5__tar.gz

{devagent_physical_engine-0.11.3/src/devagent_physical_engine.egg-info → devagent_physical_engine-0.11.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devagent-physical-engine
-Version: 0.11.3
+Version: 0.11.5
 Summary: Verification-first agentic planning runtime for robotic and industrial automation.
 Author: Tom Ha
 License: All Rights Reserved
@@ -49,11 +49,11 @@ DevAgent Smart Physical Engine adds AI-assisted engineering to existing automati
 
 ## Current version
 
-**v0.11.3 — Beta software / evidence-gated physical runtime**
+**v0.11.5 — Beta software / evidence-gated physical runtime**
 
 The Python software stack is regression-tested on Python 3.11, 3.12, and 3.13 with separate static/coverage, package-install, and runtime dependency security gates. The UR5e Gazebo/MoveIt path now contains production-candidate continuous-clearance, tool-collision, and workpiece-lifecycle capabilities, but those physical-simulation scopes remain **EXPERIMENTAL until the executable target-workstation v0.11 campaign passes**.
 
-v0.11.3 also normalizes provider-neutral agent schemas at the OpenAI transport boundary so strict Structured Outputs can represent DevAgent optional fields without changing Anthropic/Gemini or deterministic core semantics.
+v0.11.3 normalized provider-neutral agent schemas at the OpenAI transport boundary so strict Structured Outputs can represent DevAgent optional fields without changing Anthropic/Gemini or deterministic core semantics. v0.11.4 added live terminal progress tracing for AI request, engineering, and provider-qualification workflows. v0.11.5 adds explicit visualization modes: `--visualize` requests exact task-specific visualization and fails closed until an exact physical Twin plus compiled `PhysicalMotionPlan` exist; `--visual-demo` launches the UR5e Gazebo/MoveIt motion demo without misrepresenting that generic motion as the requested BOX/source/destination task.
 
 Real robot execution remains locked. Functional-safety certification and site qualification are not claimed.
 
@@ -65,6 +65,9 @@ Real robot execution remains locked. Functional-safety certification and site qu
 | OpenAI / Anthropic / Gemini structured adapters | Implemented |
 | Planner / Critic / Recovery | Implemented |
 | Natural-language engineering request front door | Implemented |
+| Live terminal stage tracing (`stderr`) | Implemented; `--quiet` supported |
+| Explicit AI visual demo (`--visual-demo`) | Implemented for UR5e workstation visual motion; not task-specific |
+| Exact task visualization (`--visualize`) | Evidence-gated; blocked until exact Twin + compiled physical motion are available |
 | Deterministic compiler / semantic / verification gates | Implemented |
 | Multi-vendor robot profile registry | Implemented |
 | UR5e / FANUC CRX / KUKA KR / ABB IRB abstraction | Implemented; physical qualification is vendor-specific |
@@ -210,6 +213,49 @@ devagent-physical-ai engineer \
   --provider openai --model <model-id>
 ```
 
+Live commands show stage-by-stage progress while they are running, for example:
+
+```text
+[DevAgent +   0.00s] START        provider=openai model=<model-id>
+[DevAgent +   0.00s] INTERPRETER  understanding engineering request
+[DevAgent +   6.84s] INTERPRETER  validated request_id=REQ-...
+[DevAgent +   6.84s] REASONING    risk_score=1 max_revisions=1 critic_threshold=0.70
+[DevAgent +   6.84s] PLANNER      revision=0 generating high-level task graph
+[DevAgent +  12.21s] PLANNER      revision=0 proposal compiled and deterministically verified
+[DevAgent +  12.21s] CRITIC       revision=0 reviewing verified plan
+[DevAgent +  15.77s] CRITIC       revision=0 decision=accept score=0.91
+[DevAgent +  15.77s] PLANNING     verified plan accepted after revision=0
+[DevAgent +  15.77s] SIMULATION   running deterministic model execution
+[DevAgent +  15.78s] SIMULATION   deterministic model execution completed
+[DevAgent +  15.78s] COMPLETE     ready_for_twin_simulation=true
+```
+
+Progress logs are emitted to `stderr`, so piping `stdout` still produces clean JSON. For CI or scripts that do not want terminal progress, add `--quiet`.
+
+### Visualization semantics
+
+`--visualize` means **visualize the exact engineering task**, not merely make a robot move. Therefore it fails closed until the request has enough physical evidence to build the exact scene and a compiled physical trajectory:
+
+```bash
+devagent-physical-ai engineer \
+  "Use a UR5e to load BOX_101 from conveyor_a to cnc_04. Simulate and verify the plan." \
+  --provider openai --model <model-id> \
+  --visualize
+```
+
+Until the task-specific physical bridge is complete, the result reports `task_visualization_requires_physical_twin_motion_plan` and lists required evidence such as robot/source/destination poses, collision geometry, workpiece/tool geometry, and a compiled `PhysicalMotionPlan`. DevAgent intentionally does not substitute a canned motion and claim it is the requested BOX task.
+
+To verify that the workstation can actually launch Gazebo/MoveIt and visibly move a UR5e now, use the explicit demo mode:
+
+```bash
+devagent-physical-ai engineer \
+  "Use a UR5e to load BOX_101 from conveyor_a to cnc_04. Simulate and verify the plan." \
+  --provider openai --model <model-id> \
+  --visual-demo
+```
+
+The visual demo uses the packaged UR simulation motion smoke, records an acceptance report under `~/.devagent/ai-visual`, and leaves Gazebo/MoveIt open after success unless `--close-after` is supplied. Its JSON explicitly reports `task_specific=false` and `motion_source=ur_robot_driver/example_move.py`.
+
 Equivalent routing supports Anthropic and Gemini. Live AI qualification does not unlock real robot execution.
 
 ## Software production gates

{devagent_physical_engine-0.11.3 → devagent_physical_engine-0.11.5}/README.md

@@ -8,11 +8,11 @@ DevAgent Smart Physical Engine adds AI-assisted engineering to existing automati
 
 ## Current version
 
-**v0.11.3 — Beta software / evidence-gated physical runtime**
+**v0.11.5 — Beta software / evidence-gated physical runtime**
 
 The Python software stack is regression-tested on Python 3.11, 3.12, and 3.13 with separate static/coverage, package-install, and runtime dependency security gates. The UR5e Gazebo/MoveIt path now contains production-candidate continuous-clearance, tool-collision, and workpiece-lifecycle capabilities, but those physical-simulation scopes remain **EXPERIMENTAL until the executable target-workstation v0.11 campaign passes**.
 
-v0.11.3 also normalizes provider-neutral agent schemas at the OpenAI transport boundary so strict Structured Outputs can represent DevAgent optional fields without changing Anthropic/Gemini or deterministic core semantics.
+v0.11.3 normalized provider-neutral agent schemas at the OpenAI transport boundary so strict Structured Outputs can represent DevAgent optional fields without changing Anthropic/Gemini or deterministic core semantics. v0.11.4 added live terminal progress tracing for AI request, engineering, and provider-qualification workflows. v0.11.5 adds explicit visualization modes: `--visualize` requests exact task-specific visualization and fails closed until an exact physical Twin plus compiled `PhysicalMotionPlan` exist; `--visual-demo` launches the UR5e Gazebo/MoveIt motion demo without misrepresenting that generic motion as the requested BOX/source/destination task.
 
 Real robot execution remains locked. Functional-safety certification and site qualification are not claimed.
 
@@ -24,6 +24,9 @@ Real robot execution remains locked. Functional-safety certification and site qu
 | OpenAI / Anthropic / Gemini structured adapters | Implemented |
 | Planner / Critic / Recovery | Implemented |
 | Natural-language engineering request front door | Implemented |
+| Live terminal stage tracing (`stderr`) | Implemented; `--quiet` supported |
+| Explicit AI visual demo (`--visual-demo`) | Implemented for UR5e workstation visual motion; not task-specific |
+| Exact task visualization (`--visualize`) | Evidence-gated; blocked until exact Twin + compiled physical motion are available |
 | Deterministic compiler / semantic / verification gates | Implemented |
 | Multi-vendor robot profile registry | Implemented |
 | UR5e / FANUC CRX / KUKA KR / ABB IRB abstraction | Implemented; physical qualification is vendor-specific |
@@ -169,6 +172,49 @@ devagent-physical-ai engineer \
   --provider openai --model <model-id>
 ```
 
+Live commands show stage-by-stage progress while they are running, for example:
+
+```text
+[DevAgent +   0.00s] START        provider=openai model=<model-id>
+[DevAgent +   0.00s] INTERPRETER  understanding engineering request
+[DevAgent +   6.84s] INTERPRETER  validated request_id=REQ-...
+[DevAgent +   6.84s] REASONING    risk_score=1 max_revisions=1 critic_threshold=0.70
+[DevAgent +   6.84s] PLANNER      revision=0 generating high-level task graph
+[DevAgent +  12.21s] PLANNER      revision=0 proposal compiled and deterministically verified
+[DevAgent +  12.21s] CRITIC       revision=0 reviewing verified plan
+[DevAgent +  15.77s] CRITIC       revision=0 decision=accept score=0.91
+[DevAgent +  15.77s] PLANNING     verified plan accepted after revision=0
+[DevAgent +  15.77s] SIMULATION   running deterministic model execution
+[DevAgent +  15.78s] SIMULATION   deterministic model execution completed
+[DevAgent +  15.78s] COMPLETE     ready_for_twin_simulation=true
+```
+
+Progress logs are emitted to `stderr`, so piping `stdout` still produces clean JSON. For CI or scripts that do not want terminal progress, add `--quiet`.
+
+### Visualization semantics
+
+`--visualize` means **visualize the exact engineering task**, not merely make a robot move. Therefore it fails closed until the request has enough physical evidence to build the exact scene and a compiled physical trajectory:
+
+```bash
+devagent-physical-ai engineer \
+  "Use a UR5e to load BOX_101 from conveyor_a to cnc_04. Simulate and verify the plan." \
+  --provider openai --model <model-id> \
+  --visualize
+```
+
+Until the task-specific physical bridge is complete, the result reports `task_visualization_requires_physical_twin_motion_plan` and lists required evidence such as robot/source/destination poses, collision geometry, workpiece/tool geometry, and a compiled `PhysicalMotionPlan`. DevAgent intentionally does not substitute a canned motion and claim it is the requested BOX task.
+
+To verify that the workstation can actually launch Gazebo/MoveIt and visibly move a UR5e now, use the explicit demo mode:
+
+```bash
+devagent-physical-ai engineer \
+  "Use a UR5e to load BOX_101 from conveyor_a to cnc_04. Simulate and verify the plan." \
+  --provider openai --model <model-id> \
+  --visual-demo
+```
+
+The visual demo uses the packaged UR simulation motion smoke, records an acceptance report under `~/.devagent/ai-visual`, and leaves Gazebo/MoveIt open after success unless `--close-after` is supplied. Its JSON explicitly reports `task_specific=false` and `motion_source=ur_robot_driver/example_move.py`.
+
 Equivalent routing supports Anthropic and Gemini. Live AI qualification does not unlock real robot execution.
 
 ## Software production gates
@@ -294,4 +340,4 @@ DevAgent Smart Physical Engine
 Copyright © 2026 Tom Ha  
 Original creator: Tom Ha  
 Original project: https://github.com/tomha85/devagent-physical-engine  
-All rights reserved.
+All rights reserved.

{devagent_physical_engine-0.11.3 → devagent_physical_engine-0.11.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "devagent-physical-engine"
-version = "0.11.3"
+version = "0.11.5"
 description = "Verification-first agentic planning runtime for robotic and industrial automation."
 readme = "README.md"
 requires-python = ">=3.11"

{devagent_physical_engine-0.11.3 → devagent_physical_engine-0.11.5}/src/devagent_physical_engine/__init__.py

@@ -41,4 +41,4 @@ __all__ = [
     "TwinValidator",
 ]
 
-__version__ = "0.11.3"
+__version__ = "0.11.5"

{devagent_physical_engine-0.11.3 → devagent_physical_engine-0.11.5}/src/devagent_physical_engine/agent/coordinator.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
-from typing import Any, Mapping
+from typing import Any, Callable, Mapping
 
 from .contracts import AgentEvidence, CriticDecision, RoutingPolicy
 from .critic import CriticAgent
@@ -9,6 +9,8 @@ from .evidence import task_graph_hash
 from .planner import PlannerAgent
 from ..models import Goal, Resource, TaskGraph, WorldState
 
+ProgressCallback = Callable[[str, str], None]
+
 
 class PlanningCoordinationError(RuntimeError):
     pass
@@ -52,12 +54,18 @@ class PlanningCoordinator:
         critic_policy: RoutingPolicy,
         *,
         engineering_context: Mapping[str, Any] | None = None,
+        progress: ProgressCallback | None = None,
     ) -> VerifiedPlanArtifact:
         feedback: tuple[str, ...] = ()
         planner_evidence: list[AgentEvidence] = []
         critic_evidence: list[AgentEvidence] = []
 
         for revision in range(self.max_revision_rounds + 1):
+            if progress is not None:
+                progress(
+                    "PLANNER",
+                    f"revision={revision} generating high-level task graph",
+                )
             planned = self.planner.plan(
                 goal,
                 resources,
@@ -67,6 +75,15 @@ class PlanningCoordinator:
                 engineering_context=engineering_context,
             )
             planner_evidence.append(planned.evidence)
+            if progress is not None:
+                progress(
+                    "PLANNER",
+                    f"revision={revision} proposal compiled and deterministically verified",
+                )
+                progress(
+                    "CRITIC",
+                    f"revision={revision} reviewing verified plan",
+                )
 
             reviewed = self.critic.review(
                 goal,
@@ -77,11 +94,24 @@ class PlanningCoordinator:
                 engineering_context=engineering_context,
             )
             critic_evidence.append(reviewed.evidence)
+            if progress is not None:
+                progress(
+                    "CRITIC",
+                    (
+                        f"revision={revision} decision={reviewed.critique.decision.value} "
+                        f"score={reviewed.critique.score:.2f}"
+                    ),
+                )
 
             if (
                 reviewed.critique.decision is CriticDecision.ACCEPT
                 and reviewed.critique.score >= self.min_accept_score
             ):
+                if progress is not None:
+                    progress(
+                        "PLANNING",
+                        f"verified plan accepted after revision={revision}",
+                    )
                 return VerifiedPlanArtifact(
                     graph=planned.graph,
                     graph_hash=task_graph_hash(planned.graph),
@@ -91,6 +121,8 @@ class PlanningCoordinator:
                 )
 
             if reviewed.critique.decision is CriticDecision.REJECT:
+                if progress is not None:
+                    progress("PLANNING", f"critic rejected revision={revision}")
                 raise PlanningCoordinationError(
                     "critic_rejected_plan:"
                     + ";".join(reviewed.critique.issues)
@@ -104,5 +136,12 @@ class PlanningCoordinator:
                 feedback = reviewed.critique.issues or (
                     "critic_requested_revision",
                 )
+            if progress is not None:
+                progress(
+                    "PLANNING",
+                    f"revision={revision} requires another planning round",
+                )
 
+        if progress is not None:
+            progress("PLANNING", "revision budget exhausted")
         raise PlanningCoordinationError("revision_budget_exhausted")