devagent-ai 0.8.3__tar.gz → 0.8.5__tar.gz

{devagent_ai-0.8.3/devagent_ai.egg-info → devagent_ai-0.8.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devagent-ai
-Version: 0.8.3
+Version: 0.8.5
 Summary: Evidence-driven local autonomous software engineering agent
 Author: Tom Ha
 Maintainer: Tom Ha
@@ -9,6 +9,7 @@ Project-URL: Homepage, https://github.com/tomha85/devagent
 Project-URL: Repository, https://github.com/tomha85/devagent
 Project-URL: Issues, https://github.com/tomha85/devagent/issues
 Project-URL: Changelog, https://github.com/tomha85/devagent/blob/main/CHANGELOG.md
+Project-URL: Sponsor, https://github.com/sponsors/tomha85
 Keywords: ai,agent,developer-tools,software-engineering,verification,local-first
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
@@ -23,6 +24,7 @@ License-File: LICENSE
 License-File: NOTICE
 Requires-Dist: openai>=1.40.0
 Requires-Dist: anthropic>=0.34.0
+Requires-Dist: cryptography>=42.0.0
 Requires-Dist: tomli>=2.0.0; python_version < "3.11"
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0; extra == "dev"
@@ -152,6 +154,39 @@ reviewer     → independently review final diff
 
 The deterministic harness remains responsible for safety, tool execution, verification validity, acceptance adjudication, final status, reporting, and source-control publication regardless of which model handles a role.
 
+#### Example: use multiple AI models in one DevAgent run
+
+You do not have to use one AI model for every reasoning step. If you believe different models are better suited to different engineering roles, configure a default model plus any role-specific overrides. Roles that are not explicitly configured fall back to the default model.
+
+```bash
+# Keep credentials in environment variables; DevAgent does not store the keys.
+export OPENAI_API_KEY=...
+export GEMINI_API_KEY=...
+export ANTHROPIC_API_KEY=...
+export XAI_API_KEY=...
+
+# Default/fallback model.
+devagent setup --provider openai --model YOUR_OPENAI_MODEL
+
+# Optional per-role models.
+devagent setup --role investigator --provider gemini --model YOUR_GEMINI_MODEL
+devagent setup --role planner --provider anthropic --model YOUR_CLAUDE_MODEL
+devagent setup --role implementer --provider openai --model YOUR_OPENAI_MODEL
+devagent setup --role reviewer --provider xai --model YOUR_GROK_MODEL
+
+# Inspect routing and optionally probe every configured cloud model.
+devagent models
+devagent doctor --live
+
+# Run normally; saved role routing is applied automatically.
+cd my-repo
+devagent "Fix the checkout race condition and add regression coverage."
+```
+
+For example, a user may choose a fast or lower-cost model for repository investigation, a different model for planning, a preferred coding model for implementation, and another provider for independent review. This can be useful for cost, latency, provider diversity, or model-strength preferences, but it does not guarantee a better result. DevAgent still requires the same repository evidence, acceptance gates, deterministic verification, and publication rules.
+
+When using saved role routing, run the task without run-level `--provider`, `--model`, or `--base-url` overrides. Supplying those flags explicitly selects one provider/model for that run instead of the saved per-role routing.
+
 ## Run
 
 From the application repository:

{devagent_ai-0.8.3 → devagent_ai-0.8.5}/README.md

@@ -121,6 +121,39 @@ reviewer     → independently review final diff
 
 The deterministic harness remains responsible for safety, tool execution, verification validity, acceptance adjudication, final status, reporting, and source-control publication regardless of which model handles a role.
 
+#### Example: use multiple AI models in one DevAgent run
+
+You do not have to use one AI model for every reasoning step. If you believe different models are better suited to different engineering roles, configure a default model plus any role-specific overrides. Roles that are not explicitly configured fall back to the default model.
+
+```bash
+# Keep credentials in environment variables; DevAgent does not store the keys.
+export OPENAI_API_KEY=...
+export GEMINI_API_KEY=...
+export ANTHROPIC_API_KEY=...
+export XAI_API_KEY=...
+
+# Default/fallback model.
+devagent setup --provider openai --model YOUR_OPENAI_MODEL
+
+# Optional per-role models.
+devagent setup --role investigator --provider gemini --model YOUR_GEMINI_MODEL
+devagent setup --role planner --provider anthropic --model YOUR_CLAUDE_MODEL
+devagent setup --role implementer --provider openai --model YOUR_OPENAI_MODEL
+devagent setup --role reviewer --provider xai --model YOUR_GROK_MODEL
+
+# Inspect routing and optionally probe every configured cloud model.
+devagent models
+devagent doctor --live
+
+# Run normally; saved role routing is applied automatically.
+cd my-repo
+devagent "Fix the checkout race condition and add regression coverage."
+```
+
+For example, a user may choose a fast or lower-cost model for repository investigation, a different model for planning, a preferred coding model for implementation, and another provider for independent review. This can be useful for cost, latency, provider diversity, or model-strength preferences, but it does not guarantee a better result. DevAgent still requires the same repository evidence, acceptance gates, deterministic verification, and publication rules.
+
+When using saved role routing, run the task without run-level `--provider`, `--model`, or `--base-url` overrides. Supplying those flags explicitly selects one provider/model for that run instead of the saved per-role routing.
+
 ## Run
 
 From the application repository:

{devagent_ai-0.8.3 → devagent_ai-0.8.5}/devagent/__init__.py

@@ -1,3 +1,3 @@
 """DevAgent: evidence-driven local software engineering automation."""
 
-__version__ = "0.8.3"
+__version__ = "0.8.5"

devagent_ai-0.8.5/devagent/__main__.py

@@ -0,0 +1,4 @@
+from devagent.entrypoint import main
+
+raise SystemExit(main())
+

{devagent_ai-0.8.3 → devagent_ai-0.8.5}/devagent/cli.py

@@ -4,10 +4,11 @@ import argparse
 import importlib.util
 import json
 import os
+import re
 import shutil
 import sys
 from pathlib import Path
-from typing import Sequence
+from typing import Callable, Sequence
 
 from devagent import __version__
 from devagent.config import (
@@ -37,6 +38,84 @@ _LIVE_PROBE_SCHEMA = {
     "additionalProperties": False,
 }
 
+_PROGRESS_STAGES: dict[str, tuple[int, str]] = {
+    "DISCOVER": (1, "DISCOVER / UNDERSTAND"),
+    "UNDERSTAND": (1, "DISCOVER / UNDERSTAND"),
+    "TASK_SPEC": (2, "REQUIREMENTS / PLAN"),
+    "BASELINE": (2, "REQUIREMENTS / PLAN"),
+    "PLAN": (2, "REQUIREMENTS / PLAN"),
+    "GATHER_CONTEXT": (2, "REQUIREMENTS / PLAN"),
+    "REPRODUCE": (2, "REQUIREMENTS / PLAN"),
+    "IMPLEMENT": (3, "IMPLEMENT"),
+    "VERIFY_TARGETED": (4, "VERIFY / REPAIR IF NEEDED"),
+    "VERIFY_BROAD": (4, "VERIFY / REPAIR IF NEEDED"),
+    "REVIEW": (5, "INDEPENDENT REVIEW"),
+    "QUALITY_CHECK": (6, "FINAL VERIFICATION"),
+    "FINAL_VERIFY": (6, "FINAL VERIFICATION"),
+}
+_STATE_LINE = re.compile(r"^\[([A-Z_]+)\]$")
+
+
+class _ProgressStatus:
+    """Render stable user-facing milestones while keeping full diagnostics opt-in."""
+
+    def __init__(
+        self,
+        sink: Callable[[str], None] = print,
+        *,
+        verbose: bool = False,
+    ) -> None:
+        self.sink = sink
+        self.verbose = verbose
+        self._last_stage = 0
+        self._plan_seen = False
+        self._implement_seen = False
+        self._review_seen = False
+
+    def __call__(self, message: str) -> None:
+        if self.verbose:
+            self.sink(message)
+            return
+
+        match = _STATE_LINE.fullmatch(message)
+        if match is None:
+            return
+        state = match.group(1)
+
+        if state == "DIAGNOSE":
+            self.sink("      ↳ DIAGNOSE")
+            return
+        if state == "PLAN":
+            if self._plan_seen:
+                self.sink("      ↳ REPLAN")
+                return
+            self._plan_seen = True
+        if state == "IMPLEMENT":
+            if self._implement_seen:
+                label = "APPLY REVIEW FIXES" if self._review_seen else "APPLY CORRECTION"
+                self.sink(f"      ↳ {label}")
+                return
+            self._implement_seen = True
+        if state == "REVIEW":
+            self._review_seen = True
+
+        stage = _PROGRESS_STAGES.get(state)
+        if stage is None:
+            return
+        number, label = stage
+        if number <= self._last_stage:
+            return
+        self._last_stage = number
+        self.sink(f"[{number}/7] {label}")
+
+    def report(self) -> None:
+        if self.verbose:
+            self.sink("[ENGINEERING_REPORT]")
+            return
+        if self._last_stage < 7:
+            self._last_stage = 7
+            self.sink("[7/7] ENGINEERING REPORT")
+
 
 def _top_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(prog="devagent", description="Evidence-driven local software engineering agent")
@@ -53,7 +132,11 @@ def _top_parser() -> argparse.ArgumentParser:
     parser.add_argument("--provider", choices=_PROVIDER_CHOICES)
     parser.add_argument("--model")
     parser.add_argument("--base-url")
-    parser.add_argument("--verbose", action="store_true", help="Show state transitions")
+    parser.add_argument(
+        "--verbose",
+        action="store_true",
+        help="Show internal state transitions and diagnostics instead of concise progress stages",
+    )
     parser.add_argument("--no-isolation", action="store_true", help="Work in place instead of creating a local detached worktree")
     parser.add_argument(
         "--publish",
@@ -337,11 +420,14 @@ def _run(argv: Sequence[str]) -> int:
         from devagent.orchestrator import DevAgent
         from devagent.report import recommendations_for, render_report
 
+        progress = _ProgressStatus(print, verbose=args.verbose)
         result = DevAgent(
             model_provider,
             isolate=not args.no_isolation,
-            verbose=args.verbose,
-            status=print,
+            # Internal status events are always emitted. The progress reporter keeps normal
+            # CLI output concise and passes the full state/diagnostic stream only in --verbose.
+            verbose=True,
+            status=progress,
             base_commit=publication_plan.base_commit if publication_plan else None,
         ).run(args.repo, requirement)
 
@@ -361,6 +447,7 @@ def _run(argv: Sequence[str]) -> int:
 
         # The full engineering report is intentionally emitted before any Git commit/push.
         result.recommendations = recommendations_for(result)
+        progress.report()
         print(render_report(result))
 
         if publish_requested:

devagent_ai-0.8.5/devagent/entrypoint.py

@@ -0,0 +1,22 @@
+from __future__ import annotations
+
+import sys
+from typing import Sequence
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    """Route domain subcommands without changing the existing software CLI."""
+
+    arguments = list(sys.argv[1:] if argv is None else argv)
+    if len(arguments) >= 2 and arguments[0] == "plc" and arguments[1] == "inspect":
+        from devagent.plc.inspect_cli import main as plc_inspect_main
+
+        return plc_inspect_main(arguments[2:])
+    if arguments and arguments[0] == "plc":
+        from devagent.plc.cli import main as plc_main
+
+        return plc_main(arguments[1:])
+
+    from devagent.cli import main as software_main
+
+    return software_main(arguments)

devagent_ai-0.8.5/devagent/plc/__init__.py

@@ -0,0 +1,185 @@
+"""Vendor-neutral PLC engineering and production verification foundations for DevAgent."""
+
+from devagent.plc import analysis as _analysis
+from devagent.plc.rockwell_compare_hardening import install as _install_rockwell_compare_hardening
+from devagent.plc.rockwell_alias_hardening import install as _install_rockwell_alias_hardening
+from devagent.plc.rockwell_entrypoint_hardening import install as _install_rockwell_entrypoint_hardening
+from devagent.plc.rockwell_st_v10 import install as _install_rockwell_st_v10
+
+# Install fail-closed compare, alias, controller-entrypoint, and ST guards before
+# production verification is imported. Every downstream Rockwell proof must
+# share the same canonical writer identity and executable-entrypoint model.
+_install_rockwell_compare_hardening()
+_install_rockwell_alias_hardening()
+_install_rockwell_entrypoint_hardening()
+_install_rockwell_st_v10()
+
+from devagent.plc.rockwell_compare_reachability_hardening import (
+    install as _install_rockwell_compare_reachability_hardening,
+)
+
+# The typed-compare theorem/FAT path is independent from boolean output-logic
+# normalization, so explicitly bind it to the same executable routine closure.
+_install_rockwell_compare_reachability_hardening()
+
+from devagent.plc.rockwell_requirement_hardening import install as _install_rockwell_requirement_hardening
+from devagent.plc.rockwell_v10_semantics import install as _install_rockwell_v10_semantics
+from devagent.plc.rockwell_action_requirements import install as _install_rockwell_action_requirements
+from devagent.plc.rockwell_risk_hardening import install as _install_rockwell_risk_hardening
+from devagent.plc.rockwell_closeout_gate_hardening import install as _install_rockwell_closeout_gate_hardening
+
+_install_rockwell_requirement_hardening()
+# V10 extends the already-hardened V9 theorem. It proves bounded OTL/OTU action
+# effects and may prove final retained scan state only inside the deliberately
+# narrow same-active-Main-RLL-routine ordering theorem. Wider scheduling remains
+# fail-closed until explicitly modeled.
+_install_rockwell_v10_semantics()
+# Explicit natural-language requirements may bind to deterministic MOV/COPY/
+# CLR/RES local action effects, but never to final scan/process behavior.
+_install_rockwell_action_requirements()
+_install_rockwell_risk_hardening()
+# Install the V9 support-contract guard before importing regression/production
+# modules. Those modules import safe_analysis by value, so the patched support
+# check must already be visible when safe_analysis is first loaded.
+_install_rockwell_closeout_gate_hardening()
+
+from devagent.plc.rockwell_core_review_v12 import install as _install_rockwell_core_review_v12
+
+# V12 makes the commercial engineering-review contract explicit: cause/effect,
+# unreachable logic, contradictory linear paths, and sequence-branch risks are
+# deterministic review outputs. They remain evidence-backed findings, not AI
+# guesses and not runtime PASS claims.
+_install_rockwell_core_review_v12()
+
+from devagent.plc.fat_procedure_v12 import install as _install_fat_procedure_v12
+
+# Every FAT candidate, including tests created later by requirement mapping,
+# must be an engineer-ready manual procedure. DevAgent plans the FAT; it does not
+# connect to or execute the engineer's external simulator/HIL/controller.
+_install_fat_procedure_v12()
+
+from devagent.plc.rockwell_regression_evidence_hardening import (
+    install as _install_rockwell_regression_evidence_hardening,
+    install_domain_evidence as _install_rockwell_regression_domain_evidence,
+)
+
+_install_rockwell_regression_evidence_hardening()
+
+from devagent.plc.rockwell_regression_case_compat_v12 import (
+    install as _install_rockwell_regression_case_compat_v12,
+)
+
+# FAT-plan regression is semantic and case-insensitive. Studio 5000 identifier
+# spelling changes alone must not force a retest or create a false regression.
+_install_rockwell_regression_case_compat_v12()
+
+from devagent.plc.rockwell_branch_coverage_v16 import install as _install_rockwell_branch_coverage_v16
+
+# V16 reconciles branch coverage with the full deterministic theorem set. A
+# neutral-text branch proven by the bounded data/compute action theorem counts
+# as modeled even when it is not an OTE/OTL/OTU boolean-output branch. Mixed or
+# partially understood branch grammars remain fail-closed and withheld.
+_install_rockwell_branch_coverage_v16()
+
+from devagent.plc.rockwell_system_service_install_v17 import (
+    install as _install_rockwell_system_service_v17,
+)
+
+# V17 does not widen static proof. Reachable GSV/SSV system-service logic stays
+# PARTIAL, but every such runtime-dependent gap receives an evidence-linked,
+# engineer-executed FAT procedure and a specific commissioning risk. The install
+# happens before production imports capture analysis/risk functions by value.
+_install_rockwell_system_service_v17()
+
+from devagent.plc.semantic_coverage_report import install as _install_semantic_coverage_report
+
+# Ensure any later CLI import of render_production_report receives the
+# reachability-aware semantic coverage augmentation.
+_install_semantic_coverage_report()
+
+from devagent.plc.rockwell_system_service_report_install_v17 import (
+    install as _install_rockwell_system_service_report_v17,
+)
+
+# Keep the public report renderer identity stable while adding an explicit V17
+# system-service runtime boundary inside the semantic coverage section.
+_install_rockwell_system_service_report_v17()
+
+from devagent.plc.four_contract_v13 import install as _install_four_contract_v13
+
+# V13 makes the commercial four-core contract explicit and testable:
+# engineering analysis, logic/risk review, five-area optimization recommendations,
+# and engineer-ready FAT planning. All optimization output is advisory only.
+_install_four_contract_v13()
+
+from devagent.plc.professional_report_install_v14 import install as _install_professional_report_v14
+
+# V14 adds a customer-facing executive layer while preserving every detailed
+# engineering/evidence section and the established public renderer identity.
+# This is presentation-only: it cannot change deterministic verdicts/readiness.
+_install_professional_report_v14()
+
+from devagent.plc.report_clarity_install_v16 import install as _install_report_clarity_v16
+
+# V16 clarifies project-only review and coverage terminology without changing
+# deterministic engineering, risk, FAT, or release-readiness decisions.
+_install_report_clarity_v16()
+
+from devagent.plc.agent_harness_install_v15 import install as _install_agent_harness_v15
+
+# V15 applies modern agent orchestration only to the probabilistic assistance
+# layer: bounded propose/critic/revise graphs, deterministic evidence guards, and
+# per-run trace capture. The PLC proof/risk/readiness core stays authoritative.
+_install_agent_harness_v15()
+
+from devagent.plc.siemens_integration_v1 import install as _install_siemens_integration_v1
+
+# Siemens V1 is a vendor branch over the already-qualified production contract.
+# It accepts offline TIA Portal Openness/XML and generated-source exports, proves
+# only bounded top-level SCL semantics, and leaves control-flow/LAD/FBD/GRAPH/STL
+# or protected behavior PARTIAL/OPAQUE. Qualified Rockwell dispatch still enters
+# the exact guarded Rockwell analyzer above.
+_install_siemens_integration_v1()
+
+from devagent.plc.siemens_scl_control_flow_v2 import install as _install_siemens_scl_control_flow_v2
+
+# Siemens V2 adds a deliberately bounded deterministic theorem for complete,
+# single-level IF/ELSIF/ELSE Boolean assignment chains. Missing/incomplete branch
+# assignments, nesting, CASE/loops, calls, cyclic/self-references, and unsupported
+# expressions stay fail-closed and require engineer-executed FAT evidence.
+_install_siemens_scl_control_flow_v2()
+
+from devagent.plc.siemens_scl_control_flow_hardening_v2 import (
+    install as _install_siemens_scl_control_flow_hardening_v2,
+)
+
+# A syntactically complete inner IF is still nested control flow. Do not allow an
+# inner chain to become independently FULL when its enclosing region is outside
+# the V2 single-level theorem.
+_install_siemens_scl_control_flow_hardening_v2()
+
+from devagent.plc.production_v5 import run_production_verification_v5
+from devagent.plc.siemens_v5_bindings_v1 import install as _install_siemens_v5_bindings_v1
+
+# Agent Harness V15 loads Production V5 before Siemens integration. Refresh only
+# V5's by-value shared production/evidence/review bindings after Siemens installs.
+# Siemens then reaches the vendor dispatcher while Rockwell remains behind the
+# exact qualified Rockwell functions selected by those vendor-aware wrappers.
+_install_siemens_v5_bindings_v1()
+
+# Production is now loaded; bind the stage-14 baseline evidence augmentation.
+_install_rockwell_regression_domain_evidence()
+from devagent.plc.safe_analysis import analyze_rockwell_l5x
+from devagent.plc.plc_dispatch import analyze_plc_project
+from devagent.plc.siemens_cli_install_v1 import install as _install_siemens_cli_v1
+
+# CLI parsing is loaded only after production_v5 exists, avoiding circular
+# imports while exposing both vendor input contracts through `devagent plc`.
+_install_siemens_cli_v1()
+
+# Keep existing imports from ``devagent.plc.analysis`` on the guarded Rockwell
+# public path. The base module remains reusable by ``safe_analysis`` without
+# recursive calls; vendor-neutral callers should use analyze_plc_project.
+_analysis.analyze_rockwell_l5x = analyze_rockwell_l5x
+
+__all__ = ["analyze_plc_project", "analyze_rockwell_l5x", "run_production_verification_v5"]

devagent_ai-0.8.5/devagent/plc/agent_harness_install_v15.py

@@ -0,0 +1,27 @@
+from __future__ import annotations
+
+from typing import Any, Callable
+
+from devagent.plc.agent_harness_v15 import begin_run_trace, end_run_trace
+from devagent.plc import production_v5
+
+_ORIGINAL: Callable[..., Any] = production_v5.run_production_verification_v5
+_INSTALLED = False
+
+
+def _run_with_harness_trace(*args: Any, **kwargs: Any):
+    trace, token = begin_run_trace()
+    try:
+        result = _ORIGINAL(*args, **kwargs)
+        result.ai_harness_trace = list(trace)
+        return result
+    finally:
+        end_run_trace(token)
+
+
+def install() -> None:
+    global _INSTALLED
+    if _INSTALLED:
+        return
+    production_v5.run_production_verification_v5 = _run_with_harness_trace
+    _INSTALLED = True