ct-toolkit 0.3.0__tar.gz → 0.3.2__tar.gz

{ct_toolkit-0.3.0 → ct_toolkit-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ct-toolkit
-Version: 0.3.0
+Version: 0.3.2
 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-0.3.0 → ct_toolkit-0.3.2}/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-0.3.0 → ct_toolkit-0.3.2}/ct_toolkit/core/wrapper.py

@@ -59,6 +59,10 @@ 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)
@@ -385,34 +389,52 @@ 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 +604,10 @@ 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
@@ -635,6 +657,21 @@ class TheseusWrapper:
             commitment_new_value=commitment_new_value,
         )
 
+    def export_provenance_log(self) -> list[dict[str, Any]]:
+        """
+        Exports the entire verified provenance log.
+
+        Verifies the integrity of the log before returning the data.
+        This is intended for external auditing and analysis.
+
+        Returns:
+            A list of all log entries as dictionaries.
+
+        Raises:
+            ChainIntegrityError: If the log's hash chain is broken.
+        """
+        return self._provenance_log.export_log()
+
     @property
     def kernel(self) -> ConstitutionalKernel:
         return self._kernel

{ct_toolkit-0.3.0 → ct_toolkit-0.3.2}/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-0.3.0 → ct_toolkit-0.3.2}/ct_toolkit/endorsement/reflective.py

@@ -210,6 +210,7 @@ class ReflectiveEndorsement:
         self._log = provenance_log
         self._approval_channel = approval_channel or cli_approval_channel
         self._pending_records: list[EndorsementRecord] = []
+        self._pre_update_snapshot: dict[str, Any] | None = None
 
     # ── Main Flow ───────────────────────────────────────────────────────────────
 

{ct_toolkit-0.3.0 → ct_toolkit-0.3.2}/ct_toolkit/provenance/log.py

@@ -43,6 +43,7 @@ class ProvenanceEntry:
     divergence_score: float | None
     metadata: dict[str, Any]
     prev_entry_hash: str          # Content hash of the previous entry
+    status: str = field(default="active") # "active" or "rolled_back"
     hmac_signature: str = field(default="", repr=False)
 
     def content_hash(self) -> str:
@@ -56,6 +57,7 @@ class ProvenanceEntry:
                 "divergence_score": self.divergence_score,
                 "metadata": self.metadata,
                 "prev_entry_hash": self.prev_entry_hash,
+                "status": self.status,
             },
             sort_keys=True,
         )
@@ -111,6 +113,7 @@ class ProvenanceLog:
                 divergence_score=divergence_score,
                 metadata=metadata or {},
                 prev_entry_hash=prev_hash,
+                status="active",
             )
 
             content_hash = entry.content_hash()
@@ -124,13 +127,14 @@ class ProvenanceLog:
 
     def verify_chain(self) -> bool:
         """
-        Verifies the entire chain from start to finish.
+        Verifies the active chain from start to finish.
         - Is each entry's HMAC valid?
         - Does each entry correctly reference the previous one?
+        - Ignores 'rolled_back' entries.
 
         Returns: True (valid) | raises ChainIntegrityError
         """
-        entries = self._load_all_entries()
+        entries = self._load_all_entries(include_rolled_back=False)
         if not entries:
             return True
 
@@ -148,12 +152,12 @@ class ProvenanceLog:
 
             expected_prev = entry.content_hash()
 
-        logger.info(f"Chain verified: {len(entries)} entries valid.")
+        logger.info(f"Chain verified: {len(entries)} active entries valid.")
         return True
 
-    def get_entries(self, limit: int = 100) -> list[ProvenanceEntry]:
+    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)
+        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(
@@ -166,15 +170,15 @@ class ProvenanceLog:
         self, template: str, kernel_name: str, model: str
     ) -> int:
         """
-        Calculates the number of interactions matching the current context.
+        Calculates the number of active interactions matching the current context.
         This provides the experience metric for Stability-Plasticity Scheduling.
         """
-        # We parse the JSON metadata column. SQLite JSON1 extension is standard.
         query = """
             SELECT COUNT(*) FROM provenance 
             WHERE json_extract(metadata, '$.template') = ?
               AND json_extract(metadata, '$.kernel') = ?
               AND json_extract(metadata, '$.model') = ?
+              AND status = 'active'
         """
         try:
             row = self._conn.execute(query, (template, kernel_name, model)).fetchone()
@@ -184,21 +188,81 @@ class ProvenanceLog:
                 f"Could not count interactions (JSON query failed): {e}. "
                 "Returning 0 to avoid inflating ElasticityScheduler thresholds."
             )
-            # Return 0 (conservative) — do NOT return total count without filters
-            # as it would incorrectly inflate the interaction_count for the scheduler.
             return 0
 
+    def export_log(self, include_rolled_back: bool = False) -> list[dict[str, Any]]:
+        """
+        Exports the verified log as a list of dictionaries.
+        By default, only active entries are exported.
+
+        Args:
+            include_rolled_back: If True, include all entries.
+
+        Returns:
+            A list of all log entries, where each entry is a dictionary.
+
+        Raises:
+            ChainIntegrityError: If the active chain is invalid.
+        """
+        self.verify_chain()  # Ensure integrity before export
+        all_entries = self._load_all_entries(include_rolled_back=include_rolled_back)
+        return [asdict(entry) for entry in all_entries]
+
+    def get_read_only_connection(self) -> sqlite3.Connection:
+        """
+        Returns a read-only connection to the database.
+        """
+        try:
+            db_uri = self._vault_path.as_uri() + "?mode=ro"
+            return sqlite3.connect(db_uri, uri=True, check_same_thread=False)
+        except sqlite3.OperationalError as e:
+            raise VaultError(
+                "Could not open read-only connection. "
+                "Ensure the database file exists and has correct permissions."
+            ) from e
+
+    def rollback(self, agent_id: str, entry_id: str) -> None:
+        """
+        Rolls back the log to the specified entry ID for a given agent.
+        All subsequent entries for that agent will be marked as 'rolled_back'.
+        """
+        with self._lock:
+            entry = self.get_entry(entry_id)
+            if not entry:
+                raise ValueError(f"Entry with ID '{entry_id}' not found.")
+
+            # This is a simplification. In a real multi-agent system,
+            # we would need a more robust way to identify agent-specific entries.
+            # Here, we assume an 'agent_id' is stored in the metadata.
+            if entry.metadata.get("agent_id") != agent_id:
+                raise ValueError("Entry does not belong to the specified agent.")
+
+            try:
+                self._conn.execute(
+                    """
+                    UPDATE provenance
+                    SET status = 'rolled_back'
+                    WHERE timestamp > ? AND json_extract(metadata, '$.agent_id') = ?
+                    """,
+                    (entry.timestamp, agent_id),
+                )
+                self._conn.commit()
+                logger.info(f"Provenance log rolled back for agent '{agent_id}' to entry '{entry_id}'")
+            except sqlite3.Error as e:
+                raise VaultError(f"SQLite rollback error: {e}") from e
+
     # ── Database ──────────────────────────────────────────────────────────────
 
     def _init_db(self) -> sqlite3.Connection:
         import os
         self._vault_path.parent.mkdir(parents=True, exist_ok=True)
-        # Create file if not exist to set permissions before sqlite connection
         if not self._vault_path.exists():
             self._vault_path.touch()
             self._vault_path.chmod(0o600)
         
         conn = sqlite3.connect(str(self._vault_path), check_same_thread=False)
+
+        # Create table if it doesn't exist
         conn.execute("""
             CREATE TABLE IF NOT EXISTS provenance (
                 id TEXT PRIMARY KEY,
@@ -208,9 +272,18 @@ class ProvenanceLog:
                 divergence_score REAL,
                 metadata TEXT NOT NULL,
                 prev_entry_hash TEXT NOT NULL,
-                hmac_signature TEXT NOT NULL
+                hmac_signature TEXT NOT NULL,
+                status TEXT NOT NULL DEFAULT 'active'
             )
         """)
+
+        # Add status column for migration from older versions
+        try:
+            conn.execute("SELECT status FROM provenance LIMIT 1").fetchall()
+        except sqlite3.OperationalError:
+            conn.execute("ALTER TABLE provenance ADD COLUMN status TEXT DEFAULT 'active'")
+            logger.info("Migrated database: Added 'status' column to provenance table.")
+
         conn.commit()
         return conn
 
@@ -220,8 +293,8 @@ class ProvenanceLog:
                 """
                 INSERT INTO provenance
                 (id, timestamp, request_hash, response_hash,
-                 divergence_score, metadata, prev_entry_hash, hmac_signature)
-                VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+                 divergence_score, metadata, prev_entry_hash, hmac_signature, status)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
                 """,
                 (
                     entry.id,
@@ -232,22 +305,32 @@ class ProvenanceLog:
                     json.dumps(entry.metadata),
                     entry.prev_entry_hash,
                     entry.hmac_signature,
+                    entry.status,
                 ),
             )
             self._conn.commit()
         except sqlite3.Error as e:
             raise VaultError(f"SQLite write error: {e}") from e
 
-    def _load_all_entries(self, limit: int | None = None) -> list[ProvenanceEntry]:
-        query = "SELECT * FROM provenance ORDER BY timestamp ASC"
+    def _load_all_entries(self, limit: int | None = None, include_rolled_back: bool = False) -> list[ProvenanceEntry]:
+        query = "SELECT * FROM provenance"
+        conditions = []
+        if not include_rolled_back:
+            conditions.append("status = 'active'")
+        
+        if conditions:
+            query += " WHERE " + " AND ".join(conditions)
+
+        query += " ORDER BY timestamp ASC"
         if limit:
             query += f" LIMIT {limit}"
+        
         rows = self._conn.execute(query).fetchall()
         return [self._row_to_entry(r) for r in rows]
 
     def _get_last_entry_hash(self) -> str:
         row = self._conn.execute(
-            "SELECT * FROM provenance ORDER BY timestamp DESC LIMIT 1"
+            "SELECT * FROM provenance WHERE status = 'active' ORDER BY timestamp DESC LIMIT 1"
         ).fetchone()
         if not row:
             return self.GENESIS_HASH
@@ -264,6 +347,7 @@ class ProvenanceLog:
             metadata=json.loads(row[5]),
             prev_entry_hash=row[6],
             hmac_signature=row[7],
+            status=row[8],
         )
 
     # ── Cryptography ────────────────────────────────────────────────────────────

{ct_toolkit-0.3.0 → ct_toolkit-0.3.2}/ct_toolkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ct-toolkit
-Version: 0.3.0
+Version: 0.3.2
 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-0.3.0 → ct_toolkit-0.3.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ct-toolkit"
-version = "0.3.0"
+version = "0.3.2"
 description = "Computational Theseus Toolkit — Identity Continuity Guardrails for Agentic Systems"
 readme = "README.md"
 requires-python = ">=3.11"