ct-toolkit 0.3.1__tar.gz → 0.3.3__tar.gz

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ct-toolkit
-Version: 0.3.1
+Version: 0.3.3
 Summary: Computational Theseus Toolkit — Identity Continuity Guardrails for Agentic Systems
 Author: Hakan Damar
 License: Apache-2.0
@@ -51,6 +51,7 @@ CT Toolkit is an open-source security layer designed to preserve the **identity
 ---
 
 ## 📖 Official Documentation
+
 For full API reference, architecture details, examples, and integration guides, visit our documentation site:
 👉 [**https://hakandamar.github.io/ct-toolkit/**](https://hakandamar.github.io/ct-toolkit/)
 
@@ -63,6 +64,7 @@ For full API reference, architecture details, examples, and integration guides,
 In complex agentic workflows, LLMs tend to "drift" from their original instructions. CT Toolkit provides the mathematical and cryptographic guardrails to ensure your agents remain aligned with their core constitution, even across deep hierarchies.
 
 - **Constitutional Kernels**: Axiomatic identity anchors.
+- **Autonomous Self-Correction**: Active L2->L1 feedback loop that retries and corrects divergent responses before they reach the user.
 - **Divergence Engine**: Multi-tiered drift analysis (L1/L2/L3).
 - **Hierarchical Propagation**: Mother-to-child constraint inheritance.
 - **Provenance Log**: Immutable HMAC-signed interaction history.
@@ -92,15 +94,16 @@ print(f"Divergence Score: {response.divergence_score}")
 
 ## 🚦 Project Health & Status
 
-| Metric | Status |
-| :--- | :--- |
-| **Tests** | ✅ 218/218 passing (93% coverage) |
-| **Last Phase** | ✅ Phase 4: OS Support, Deep Agents & Alerts (Complete) |
-| **Current Goal** | 🔶 Phase 5: Vault and Security Infrastructure |
+| Metric           | Status                                                  |
+| :--------------- | :------------------------------------------------------ |
+| **Tests**        | ✅ 231/232 passing (90% coverage)                       |
+| **Last Phase**   | ✅ Phase 4: OS Support, Deep Agents & Alerts (Complete) |
+| **Current Goal** | 🔶 Phase 5: Vault & Security (In Progress)              |
 
 For a detailed breakdown of the 8-phase roadmap, see [**PROJECT_STATUS.md**](docs/PROJECT_STATUS.md).
 
 ### Framework & Model Support
+
 Seamlessly integrate with your favorite frameworks and local models:
 
 - **Local Models**: Support for LM Studio, Ollama, and local Qwen/Llama endpoints.
@@ -111,9 +114,11 @@ Seamlessly integrate with your favorite frameworks and local models:
 ---
 
 ## Theoretical Foundation
+
 Translating the framework proposed in [**The Computational Theseus (2025)**](https://hakandamar.com/the-computational-theseus-engineering-identity-continuity-as-a-guardrail-against-sequential-963918c1720d) into engineering practice.
 
 ---
 
 ## License
+
 Apache License 2.0.

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/README.md

@@ -12,6 +12,7 @@ CT Toolkit is an open-source security layer designed to preserve the **identity
 ---
 
 ## 📖 Official Documentation
+
 For full API reference, architecture details, examples, and integration guides, visit our documentation site:
 👉 [**https://hakandamar.github.io/ct-toolkit/**](https://hakandamar.github.io/ct-toolkit/)
 
@@ -24,6 +25,7 @@ For full API reference, architecture details, examples, and integration guides,
 In complex agentic workflows, LLMs tend to "drift" from their original instructions. CT Toolkit provides the mathematical and cryptographic guardrails to ensure your agents remain aligned with their core constitution, even across deep hierarchies.
 
 - **Constitutional Kernels**: Axiomatic identity anchors.
+- **Autonomous Self-Correction**: Active L2->L1 feedback loop that retries and corrects divergent responses before they reach the user.
 - **Divergence Engine**: Multi-tiered drift analysis (L1/L2/L3).
 - **Hierarchical Propagation**: Mother-to-child constraint inheritance.
 - **Provenance Log**: Immutable HMAC-signed interaction history.
@@ -53,15 +55,16 @@ print(f"Divergence Score: {response.divergence_score}")
 
 ## 🚦 Project Health & Status
 
-| Metric | Status |
-| :--- | :--- |
-| **Tests** | ✅ 218/218 passing (93% coverage) |
-| **Last Phase** | ✅ Phase 4: OS Support, Deep Agents & Alerts (Complete) |
-| **Current Goal** | 🔶 Phase 5: Vault and Security Infrastructure |
+| Metric           | Status                                                  |
+| :--------------- | :------------------------------------------------------ |
+| **Tests**        | ✅ 231/232 passing (90% coverage)                       |
+| **Last Phase**   | ✅ Phase 4: OS Support, Deep Agents & Alerts (Complete) |
+| **Current Goal** | 🔶 Phase 5: Vault & Security (In Progress)              |
 
 For a detailed breakdown of the 8-phase roadmap, see [**PROJECT_STATUS.md**](docs/PROJECT_STATUS.md).
 
 ### Framework & Model Support
+
 Seamlessly integrate with your favorite frameworks and local models:
 
 - **Local Models**: Support for LM Studio, Ollama, and local Qwen/Llama endpoints.
@@ -72,9 +75,11 @@ Seamlessly integrate with your favorite frameworks and local models:
 ---
 
 ## Theoretical Foundation
+
 Translating the framework proposed in [**The Computational Theseus (2025)**](https://hakandamar.com/the-computational-theseus-engineering-identity-continuity-as-a-guardrail-against-sequential-963918c1720d) into engineering practice.
 
 ---
 
 ## License
+
 Apache License 2.0.

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/ct_toolkit/__init__.py

@@ -23,7 +23,6 @@ from ct_toolkit.core.exceptions import (
     ChainIntegrityError,
 )
 
-__version__ = "0.2.5"
 __all__ = [
     "TheseusWrapper",
     "WrapperConfig",

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/ct_toolkit/core/wrapper.py

@@ -24,7 +24,7 @@ import hashlib
 import os
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Any, Iterator
+from typing import Any, Iterator, Optional, Callable, Dict
 import any_llm
 from any_llm import AnyLLM
 import glob
@@ -59,12 +59,18 @@ class WrapperConfig:
     embedding_model: str = "text-embedding-3-small"
     enterprise_mode: bool = False    # Run all tiers all the time
     parent_kernel: ConstitutionalKernel | None = None  # Propagated from mother agent
+    
+    # -- Auto-Correction Loop --
+    auto_correction: bool = False
+    max_correction_retries: int = 1
 
     # -- Dynamic Stability-Plasticity Scheduling --
     elasticity_max_thresholds: tuple[float, float, float] | None = None  # (max_l1, max_l2, max_l3)
     elasticity_growth_rate: float | None = None
     risk_profile: RiskProfile | None = None
 
+    strict_embedding: bool = False   # Raise error if embedding API fails
+
 
 @dataclass
 class CTResponse:
@@ -188,7 +194,7 @@ class TheseusWrapper:
                     if file_path.is_file():
                         self._integrity_monitor.register_file(file_path)
 
-        except (ImportError, ModuleNotFoundError):
+        except Exception:
             # Fallback for older Python or different environments
             package_root = Path(__file__).parent.parent
             # This is less ideal as it might find non-package files, but it's a
@@ -305,6 +311,7 @@ class TheseusWrapper:
             embedding_client=emb_client,
             embedding_model=self._config.embedding_model,
             project_root=self._project_root,
+            strict_embedding=self._config.strict_embedding,
         )
 
     def _init_divergence_engine(self) -> Any:
@@ -385,34 +392,52 @@ class TheseusWrapper:
                 f"Please provide a client or set the appropriate environment variables."
             )
 
-        start_time = time.monotonic()
-
-        try:
-            raw_response = self._call_provider(messages, model=model, **kwargs)
-        except Exception as e:
-            logger.error(f"Provider API error: {e}")
-            raise
-
-        elapsed = time.monotonic() - start_time
-        content = self._extract_content(raw_response)
-        model_used = self._extract_model(raw_response, model)
-        self._last_model = model_used
-
-        # Compute current interaction experience
-        interaction_count = 0
-        if self._config.log_requests:
-            interaction_count = self._provenance_log.get_interaction_count(
-                template=self._config.template,
-                kernel_name=self._kernel.name,
-                model=model_used
+        retries = 0
+        max_retries = self._config.max_correction_retries if self._config.auto_correction else 0
+        
+        while retries <= max_retries:
+            start_time = time.monotonic()
+    
+            try:
+                raw_response = self._call_provider(messages, model=model, **kwargs)
+            except Exception as e:
+                logger.error(f"Provider API error: {e}")
+                raise
+    
+            elapsed = time.monotonic() - start_time
+            content = self._extract_content(raw_response)
+            model_used = self._extract_model(raw_response, model)
+            self._last_model = model_used
+    
+            # Compute current interaction experience
+            interaction_count = 0
+            if self._config.log_requests:
+                interaction_count = self._provenance_log.get_interaction_count(
+                    template=self._config.template,
+                    kernel_name=self._kernel.name,
+                    model=model_used
+                )
+    
+            # Divergence Engine (L1 -> L2 -> L3)
+            skip_l3 = self._config.auto_correction and retries < max_retries
+            div_result = self._run_divergence_engine(
+                message=message,
+                response=content,
+                interaction_count=interaction_count,
+                skip_l3=skip_l3,
             )
-
-        # Divergence Engine (L1 -> L2 -> L3)
-        div_result = self._run_divergence_engine(
-            message=message,
-            response=content,
-            interaction_count=interaction_count,
-        )
+            
+            from ct_toolkit.divergence.l2_judge import JudgeVerdict
+            if getattr(div_result, 'l2_verdict', None) == JudgeVerdict.MISALIGNED and retries < max_retries:
+                logger.warning(f"Auto-correction triggered. Reason: {div_result.l2_reason}")
+                messages.extend([
+                    {"role": "assistant", "content": content},
+                    {"role": "user", "content": f"Identity Drift Detected. Your previous response violated the core identity instructions. Reason: {div_result.l2_reason}. Please revise your response to strictly adhere to the system prompt."}
+                ])
+                retries += 1
+                continue
+                
+            break
 
         # Provenance Log record
         provenance_id = None
@@ -582,10 +607,10 @@ class TheseusWrapper:
             return raw.model
         return fallback or "unknown"
 
-    def _run_divergence_engine(self, message: str, response: str, interaction_count: int = 0) -> Any:
+    def _run_divergence_engine(self, message: str, response: str, interaction_count: int = 0, skip_l3: bool = False) -> Any:
         """Runs the staged divergence engine (L1 -> L2 -> L3)."""
         try:
-            return self._divergence_engine.analyze(message, response, interaction_count)
+            return self._divergence_engine.analyze(message, response, interaction_count, skip_l3=skip_l3)
         except Exception as e:
             logger.error(f"Divergence Engine execution failed: {e}")
             from ct_toolkit.divergence.engine import DivergenceResult, DivergenceTier

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/ct_toolkit/divergence/engine.py

@@ -154,6 +154,7 @@ class DivergenceEngine:
         request_text: str,
         response_text: str,
         interaction_count: int = 0,
+        skip_l3: bool = False,
     ) -> DivergenceResult:
         """
         Performs full divergence analysis.
@@ -166,8 +167,8 @@ class DivergenceEngine:
             )
 
         if self._enterprise:
-            return self._enterprise_analyze(request_text, response_text)
-        return self._standard_analyze(request_text, response_text)
+            return self._enterprise_analyze(request_text, response_text, skip_l3=skip_l3)
+        return self._standard_analyze(request_text, response_text, skip_l3=skip_l3)
 
     def get_drift_report(self, window_size: int = 50, model: str | None = None) -> DriftReport | None:
         """
@@ -189,6 +190,7 @@ class DivergenceEngine:
         self,
         request_text: str,
         response_text: str,
+        skip_l3: bool = False,
     ) -> DivergenceResult:
         """Progressive analysis: L1 → L2 if needed → L3 if needed."""
 
@@ -236,6 +238,18 @@ class DivergenceEngine:
             )
 
         # L3 — L2 problematic or L1 too high
+        if skip_l3:
+            return DivergenceResult(
+                tier=DivergenceTier.L2_JUDGE,
+                l1_score=l1_score,
+                l2_verdict=l2_result.verdict,
+                l2_confidence=l2_result.confidence,
+                l2_reason=l2_result.reason,
+                action_required=True,
+                cascade_blocked=True,
+                summary="L3 skipped due to auto-correction retry logic",
+            )
+
         if not self._l3_available:
             return DivergenceResult(
                 tier=DivergenceTier.L2_JUDGE,
@@ -269,6 +283,7 @@ class DivergenceEngine:
         self,
         request_text: str,
         response_text: str,
+        skip_l3: bool = False,
     ) -> DivergenceResult:
         """Enterprise mode: L1 + L2 + L3 all run, decision based on total score."""
         l1_score = self._run_l1(response_text)
@@ -278,7 +293,7 @@ class DivergenceEngine:
             l2_result = self._run_l2(request_text, response_text)
 
         l3_report = None
-        if self._l3_available:
+        if self._l3_available and not skip_l3:
             l3_report = self._run_l3(max_probes=5)  # Fast subset in Enterprise
 
         # Calculate total risk score

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/ct_toolkit/divergence/l3_icm.py

@@ -19,6 +19,8 @@ from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any
 
+import any_llm
+
 from ct_toolkit.utils.logger import get_logger
 
 logger = get_logger(__name__)
@@ -117,7 +119,7 @@ class BehaviorClassifier:
     ]
 
     COMPLY_SIGNALS = [
-        "sure", "of course", "here's",
+        "sure", "of course",
         "certainly", "happy to",
     ]
 
@@ -288,38 +290,47 @@ class ICMRunner:
     def _call_model(self, prompt: str) -> str:
         system = self._kernel.get_system_prompt_injection()
 
-        if self._provider == "openai":
-            resp = self._client.chat.completions.create(
-                model=self._model,
-                messages=[
-                    {"role": "system", "content": system},
-                    {"role": "user", "content": f"{prompt}\n\nPlease provide your reasoning step-by-step wrapped in <think></think> tags before your final response."},
-                ],
-                max_tokens=512,
-                temperature=0.0,
-            )
-            return resp.choices[0].message.content or ""
-
-        elif self._provider == "anthropic":
-            resp = self._client.messages.create(
-                model=self._model,
-                max_tokens=512,
-                system=system,
-                messages=[{"role": "user", "content": f"{prompt}\n\nPlease provide your reasoning step-by-step wrapped in <think></think> tags before your final response."}],
-            )
-            return resp.content[0].text if resp.content else ""
-
-        elif self._provider == "ollama":
-            resp = self._client.chat(
-                model=self._model,
-                messages=[
-                    {"role": "system", "content": system},
-                    {"role": "user", "content": f"{prompt}\n\nPlease provide your reasoning step-by-step wrapped in <think></think> tags before your final response."},
-                ],
-            )
-            return resp.message.content or ""
-
-        raise ValueError(f"Unsupported provider: {self._provider}")
+        full_model = self._model
+        if ":" not in self._model:
+            full_model = f"{self._provider}:{self._model}"
+
+        any_llm_kwargs = {
+            "model": full_model,
+            "messages": [
+                {"role": "system", "content": system},
+                {"role": "user", "content": f"{prompt}\n\nPlease provide your reasoning step-by-step wrapped in <think></think> tags before your final response."},
+            ],
+            "max_tokens": 512,
+            "temperature": 0.0,
+        }
+
+        # Extract connection info from client if possible
+        if hasattr(self._client, "base_url") and self._client.base_url:
+            any_llm_kwargs["api_base"] = str(self._client.base_url)
+        if hasattr(self._client, "api_key") and self._client.api_key:
+            any_llm_kwargs["api_key"] = self._client.api_key
+            
+        try:
+            resp = any_llm.completion(**any_llm_kwargs)
+            # any_llm SDK standardizes responses but fallback handling preserves robustness
+            if isinstance(resp, dict):
+                if "choices" in resp and resp["choices"]:
+                    return resp["choices"][0].get("message", {}).get("content", "")
+                if "message" in resp:
+                    return resp["message"].get("content", "")
+                return str(resp)
+
+            if hasattr(resp, "choices"):
+                return resp.choices[0].message.content or ""
+            if hasattr(resp, "content") and isinstance(resp.content, list):
+                return resp.content[0].text if resp.content else ""
+            if hasattr(resp, "message"):
+                return resp.message.content or ""
+            
+            return str(resp)
+        except Exception as e:
+            logger.error(f"ICM probe any_llm call failed: {e}")
+            raise
 
     # ── Probe Loading ──────────────────────────────────────────────────────────
 

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/ct_toolkit/endorsement/reflective.py

@@ -36,6 +36,7 @@ class EndorsementDecision(str, Enum):
     APPROVED = "approved"
     REJECTED = "rejected"
     PENDING  = "pending"
+    FAILED   = "failed"
 
 
 @dataclass
@@ -273,20 +274,7 @@ class ReflectiveEndorsement:
         # Stage 2: Send to approval channel
         decision, actual_operator_id, rationale = self._approval_channel(conflict)
 
-        # Stage 3: Sign EndorsementRecord
-        record = EndorsementRecord(
-            id=str(uuid.uuid4()),
-            timestamp=time.time(),
-            conflict_id=conflict.id,
-            rule_text=rule_text,
-            commitment_id=conflict.conflicting_commitment_id,
-            decision=decision,
-            operator_id=actual_operator_id or operator_id,
-            rationale=rationale,
-            kernel_name=self._kernel.name,
-        )
-
-        # Stage 4: Apply decision
+        # Stage 3: Apply decision
         if decision == EndorsementDecision.APPROVED:
             applied = self._apply_override(
                 commitment_id=conflict.conflicting_commitment_id,
@@ -296,22 +284,37 @@ class ReflectiveEndorsement:
                 logger.info(
                     f"Override approved and applied | "
                     f"commitment={conflict.conflicting_commitment_id} | "
-                    f"operator={record.operator_id}"
+                    f"operator={actual_operator_id or operator_id}"
                 )
             else:
+                decision = EndorsementDecision.FAILED
+                rationale = "System failed to apply approved rule to kernel (commitment not found)"
                 logger.warning(
-                    f"Override APPROVED in log but NOT applied to kernel "
+                    f"Override APPROVED by operator but failed to apply to kernel "
                     f"(commitment not found) | "
                     f"commitment={conflict.conflicting_commitment_id} | "
-                    f"operator={record.operator_id}"
+                    f"operator={actual_operator_id or operator_id}"
                 )
         else:
             logger.info(
                 f"Override rejected | "
                 f"commitment={conflict.conflicting_commitment_id} | "
-                f"operator={record.operator_id}"
+                f"operator={actual_operator_id or operator_id}"
             )
 
+        # Stage 4: Sign EndorsementRecord
+        record = EndorsementRecord(
+            id=str(uuid.uuid4()),
+            timestamp=time.time(),
+            conflict_id=conflict.id,
+            rule_text=rule_text,
+            commitment_id=conflict.conflicting_commitment_id,
+            decision=decision,
+            operator_id=actual_operator_id or operator_id,
+            rationale=rationale,
+            kernel_name=self._kernel.name,
+        )
+
         # Write to log in either case
         self._write_to_log(record)
         self._pending_records.append(record)

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/ct_toolkit/identity/embedding.py

@@ -44,6 +44,7 @@ class IdentityEmbeddingLayer:
         embedding_client: Any = None,  # Provider client for real embeddings
         embedding_model: str = "text-embedding-3-small",
         project_root: Path | None = None,
+        strict_embedding: bool = False,
     ) -> None:
         self._template = template
         self._embedding_client = embedding_client
@@ -52,6 +53,7 @@ class IdentityEmbeddingLayer:
         self._template_keywords: list[str] = []
         self._reference_text: str = ""          # stored for lazy computation
         self._project_root = project_root
+        self._strict_embedding = strict_embedding
         self._embedding_method: str = "uninitialized"
         self._load_template()
 
@@ -165,6 +167,8 @@ class IdentityEmbeddingLayer:
                 else:
                     logger.debug("Embedding client does not support .embeddings API. Falling back.")
             except Exception as e:
+                if self._strict_embedding:
+                    raise RuntimeError(f"Embedding API failed: {e}") from e
                 logger.error(f"Embedding API failed: {e}. Falling back to local method.")
         if not self._template_keywords:
             # Fallback: character n-gram hash vector

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/ct_toolkit/provenance/log.py

@@ -85,7 +85,7 @@ class ProvenanceLog:
         self._vault_type = vault_type
         self._vault_path = Path(vault_path)
         self._hmac_key = hmac_key or self._load_or_generate_key()
-        self._lock = threading.Lock()
+        self._lock = threading.RLock()
         self._conn = self._init_db()
         logger.info(f"ProvenanceLog initialized | vault={vault_path}")
 
@@ -134,7 +134,8 @@ class ProvenanceLog:
 
         Returns: True (valid) | raises ChainIntegrityError
         """
-        entries = self._load_all_entries(include_rolled_back=False)
+        with self._lock:
+            entries = self._load_all_entries(include_rolled_back=False)
         if not entries:
             return True
 
@@ -157,14 +158,16 @@ class ProvenanceLog:
 
     def get_entries(self, limit: int = 100, include_rolled_back: bool = False) -> list[ProvenanceEntry]:
         """Returns the last N entries."""
-        return self._load_all_entries(limit=limit, include_rolled_back=include_rolled_back)
+        with self._lock:
+            return self._load_all_entries(limit=limit, include_rolled_back=include_rolled_back)
 
     def get_entry(self, entry_id: str) -> ProvenanceEntry | None:
-        cursor = self._conn.execute(
-            "SELECT * FROM provenance WHERE id = ?", (entry_id,)
-        )
-        row = cursor.fetchone()
-        return self._row_to_entry(row) if row else None
+        with self._lock:
+            cursor = self._conn.execute(
+                "SELECT * FROM provenance WHERE id = ?", (entry_id,)
+            )
+            row = cursor.fetchone()
+            return self._row_to_entry(row) if row else None
 
     def get_interaction_count(
         self, template: str, kernel_name: str, model: str

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/ct_toolkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ct-toolkit
-Version: 0.3.1
+Version: 0.3.3
 Summary: Computational Theseus Toolkit — Identity Continuity Guardrails for Agentic Systems
 Author: Hakan Damar
 License: Apache-2.0
@@ -51,6 +51,7 @@ CT Toolkit is an open-source security layer designed to preserve the **identity
 ---
 
 ## 📖 Official Documentation
+
 For full API reference, architecture details, examples, and integration guides, visit our documentation site:
 👉 [**https://hakandamar.github.io/ct-toolkit/**](https://hakandamar.github.io/ct-toolkit/)
 
@@ -63,6 +64,7 @@ For full API reference, architecture details, examples, and integration guides,
 In complex agentic workflows, LLMs tend to "drift" from their original instructions. CT Toolkit provides the mathematical and cryptographic guardrails to ensure your agents remain aligned with their core constitution, even across deep hierarchies.
 
 - **Constitutional Kernels**: Axiomatic identity anchors.
+- **Autonomous Self-Correction**: Active L2->L1 feedback loop that retries and corrects divergent responses before they reach the user.
 - **Divergence Engine**: Multi-tiered drift analysis (L1/L2/L3).
 - **Hierarchical Propagation**: Mother-to-child constraint inheritance.
 - **Provenance Log**: Immutable HMAC-signed interaction history.
@@ -92,15 +94,16 @@ print(f"Divergence Score: {response.divergence_score}")
 
 ## 🚦 Project Health & Status
 
-| Metric | Status |
-| :--- | :--- |
-| **Tests** | ✅ 218/218 passing (93% coverage) |
-| **Last Phase** | ✅ Phase 4: OS Support, Deep Agents & Alerts (Complete) |
-| **Current Goal** | 🔶 Phase 5: Vault and Security Infrastructure |
+| Metric           | Status                                                  |
+| :--------------- | :------------------------------------------------------ |
+| **Tests**        | ✅ 231/232 passing (90% coverage)                       |
+| **Last Phase**   | ✅ Phase 4: OS Support, Deep Agents & Alerts (Complete) |
+| **Current Goal** | 🔶 Phase 5: Vault & Security (In Progress)              |
 
 For a detailed breakdown of the 8-phase roadmap, see [**PROJECT_STATUS.md**](docs/PROJECT_STATUS.md).
 
 ### Framework & Model Support
+
 Seamlessly integrate with your favorite frameworks and local models:
 
 - **Local Models**: Support for LM Studio, Ollama, and local Qwen/Llama endpoints.
@@ -111,9 +114,11 @@ Seamlessly integrate with your favorite frameworks and local models:
 ---
 
 ## Theoretical Foundation
+
 Translating the framework proposed in [**The Computational Theseus (2025)**](https://hakandamar.com/the-computational-theseus-engineering-identity-continuity-as-a-guardrail-against-sequential-963918c1720d) into engineering practice.
 
 ---
 
 ## License
+
 Apache License 2.0.

{ct_toolkit-0.3.1 → ct_toolkit-0.3.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ct-toolkit"
-version = "0.3.1"
+version = "0.3.3"
 description = "Computational Theseus Toolkit — Identity Continuity Guardrails for Agentic Systems"
 readme = "README.md"
 requires-python = ">=3.11"