claude-smart 0.2.47 → 0.2.48

package/plugin/dashboard/package.json

@@ -9,6 +9,7 @@
     "lint": "eslint"
   },
   "dependencies": {
+    "@tailwindcss/postcss": "^4",
     "@base-ui/react": "^1.3.0",
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
@@ -17,17 +18,16 @@
     "next-themes": "^0.4.6",
     "react": "19.2.4",
     "react-dom": "19.2.4",
+    "shadcn": "^4.0.8",
     "tailwind-merge": "^3.5.0",
     "tw-animate-css": "^1.4.0"
   },
   "devDependencies": {
-    "@tailwindcss/postcss": "^4",
     "@types/node": "^20",
     "@types/react": "^19",
     "@types/react-dom": "^19",
     "eslint": "^9",
     "eslint-config-next": "16.2.6",
-    "shadcn": "^4.0.8",
     "tailwindcss": "^4",
     "typescript": "^5"
   },

package/plugin/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "claude-smart"
-version = "0.2.47"
+version = "0.2.48"
 description = "Self-improving Claude Code, Codex, and OpenCode plugin that turns corrections into Preferences, Project-specific skills, and Shared skills"
 keywords = [
     "claude",

package/plugin/uv.lock

@@ -476,7 +476,7 @@ wheels = [
 
 [[package]]
 name = "claude-smart"
-version = "0.2.47"
+version = "0.2.48"
 source = { editable = "." }
 dependencies = [
     { name = "chromadb" },

package/plugin/vendor/reflexio/.env.example

@@ -67,6 +67,13 @@ REFLEXIO_DEFAULT_ORG_ID=self-host-org
 # elided. (optional; default 512; set <= 0 to disable slicing and pass full
 # content)
 REFLEXIO_MAX_INTERACTION_CONTENT_TOKENS=512
+# Warn when queued post-persist async publish learning jobs reach this depth.
+# The queue is unbounded so acknowledged publishes do not drop learning due to
+# transient limiter pressure. (optional; default 1000)
+REFLEXIO_PUBLISH_LEARNING_QUEUE_WARN_SIZE=1000
+# Worker threads for post-persist async publish learning. (optional; default
+# matches the configured publish concurrency limit, currently 4)
+REFLEXIO_PUBLISH_LEARNING_WORKERS=
 # Inactivity delay in seconds before a quiet session is evaluated by agent-success
 # evaluation. (optional; default 600 = 10 minutes)
 GROUP_EVALUATION_DELAY_SECONDS=600

package/plugin/vendor/reflexio/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "reflexio-ai"
-version = "0.2.27"
+version = "0.2.28"
 description = "A Python library for the Reflexio"
 authors = [{name = "Reflexio Team"}]
 readme = "README.md"
@@ -218,6 +218,7 @@ ignore = [
 "reflexio/scripts/**" = ["S101", "G004", "ANN"]
 "reflexio/benchmarks/**" = ["S311"]
 "reflexio/server/api.py" = ["B008", "ARG001", "ARG002"]
+"reflexio/server/routes/**" = ["B008", "ARG001", "ARG002"]
 "reflexio/server/api_endpoints/**" = ["B008", "ARG001", "ARG002"]
 "reflexio/integrations/**" = ["ARG002"]
 # The openclaw plugin is a nested package; its tests/scripts/cli are not reached

package/plugin/vendor/reflexio/reflexio/README.md

@@ -101,9 +101,10 @@ Description: FastAPI backend server that processes user interactions to generate
 **Detailed Documentation**: See [`reflexio/server/README.md`](server/README.md) for component details, including the [Prompt Bank](server/prompt/prompt_bank/README.md), [Playbook Service](server/services/playbook/README.md), and [Site Variables](server/site_var/README.md)
 
 ### Main Entry Points
-- **API**: `api.py` - FastAPI routes
+- **API composer**: `api.py` - `create_app()` factory, middleware/capability wiring, and `core_router` aggregation
+- **Domain routes**: `server/routes/` - FastAPI route modules grouped by system, interactions, profiles, playbooks, search, provenance, evaluation, Braintrust, and config
 - **Extension Registry**: `extensions.py` - optional capability/service registration for OSS and enterprise integrations
-- **Endpoint Helpers**: `api_endpoints/` - Request handlers calling `Reflexio` (reflexio_lib)
+- **Endpoint Helpers**: `api_endpoints/` - Shared handler/helper functions and `RequestContext` used by route modules
 - **Core Service**: `services/generation_service.py` - Main orchestrator
 
 ### Purpose
@@ -115,8 +116,9 @@ Receives user interactions from clients and processes them to:
 ### Component Relationships
 ```
 client (Python SDK)
-  -> api.py (FastAPI routes)
-    -> api_endpoints/ (request handlers)
+  -> api.py (create_app + core_router)
+    -> routes/ (domain FastAPI routers)
+    -> api_endpoints/ (shared handlers + RequestContext)
       -> reflexio_lib.Reflexio (main entry)
         -> services/generation_service.py (orchestrator)
           ├─> services/profile/ -> storage (BaseStorage)
@@ -126,12 +128,13 @@ client (Python SDK)
 
 ### Key Components
 - **`api_endpoints/`**: Request handling, `RequestContext` (bundles storage/config/prompts), auth
+- **`routes/`**: Domain route modules (`system.py`, `interactions.py`, `profiles.py`, `playbooks.py`, `search.py`, `provenance.py`, `evaluation.py`, `braintrust.py`, `config.py`) included into `api.py`'s `core_router`
 - **`db/`**: Auth & config storage only (SQLite) - NOT for profiles/interactions
 - **`llm/`**: Unified LLM client (auto-detects OpenAI/Claude from model name)
 - **`prompt/`**: Versioned prompt templates in `prompt_bank/`
 - **`services/`**: Core business logic
   - `generation_service.py` - Orchestrator (runs profile/playbook/success services)
-  - `base_generation_service.py` - Abstract base for parallel actor execution
+  - `base_generation_service.py` + `base_generation/` - Abstract base plus mixins for parallel actor execution, batch progress, should-run prechecks, status transitions, and usage billing
   - `profile/` - Profile extraction & updates
   - `playbook/` - Playbook extraction, consolidation, and aggregation
   - `agent_success_evaluation/` - Success evaluation

package/plugin/vendor/reflexio/reflexio/lib/_config.py

@@ -29,32 +29,37 @@ class ConfigMixin(ReflexioBase):
             # security). Without this, the marker reaches the readiness check as
             # an unfillable StorageConfigManagedSupabase and fails with
             # "Storage configuration is incomplete".
+            current_storage_config = configurator.get_current_storage_configuration()
             storage_config = config.storage_config
             if storage_config is None or isinstance(
                 storage_config, StorageConfigManagedSupabase
             ):
-                storage_config = configurator.get_current_storage_configuration()
+                storage_config = current_storage_config
                 config.storage_config = storage_config
 
-            # Check if storage config is ready to test
-            if not configurator.is_storage_config_ready_to_test(
-                storage_config=storage_config
-            ):
-                return SetConfigResponse(
-                    success=False, msg="Storage configuration is incomplete"
+            storage_config_changed = storage_config != current_storage_config
+            if storage_config_changed or current_storage_config is None:
+                # Storage validation initializes the backend and may run
+                # migrations, so only do it when the storage target changes.
+                if not configurator.is_storage_config_ready_to_test(
+                    storage_config=storage_config
+                ):
+                    return SetConfigResponse(
+                        success=False, msg="Storage configuration is incomplete"
+                    )
+
+                (
+                    success,
+                    error_msg,
+                ) = configurator.test_and_init_storage_config(
+                    storage_config=storage_config
                 )
 
-            # Test and initialize storage connection
-            (
-                success,
-                error_msg,
-            ) = configurator.test_and_init_storage_config(storage_config=storage_config)
-
-            if not success:
-                return SetConfigResponse(
-                    success=False,
-                    msg=f"Failed to validate storage connection: {error_msg}",
-                )
+                if not success:
+                    return SetConfigResponse(
+                        success=False,
+                        msg=f"Failed to validate storage connection: {error_msg}",
+                    )
 
             # Only set config if validation passed
             configurator.set_config(config)

package/plugin/vendor/reflexio/reflexio/lib/_interactions.py

@@ -53,11 +53,21 @@ class InteractionsMixin(ReflexioBase):
     def publish_interaction(
         self,
         request: PublishUserInteractionRequest | dict,
+        *,
+        use_publish_limiter: bool = True,
+        publish_limiter_wait_forever: bool = True,
+        defer_learning: bool = False,
     ) -> PublishUserInteractionResponse:
         """Publish user interactions.
 
         Args:
             request (Union[PublishUserInteractionRequest, dict]): The publish user interaction request
+            use_publish_limiter: Whether GenerationService should throttle the
+                post-write learning pipeline.
+            publish_limiter_wait_forever: Whether GenerationService should queue
+                indefinitely for that post-write learning limiter.
+            defer_learning: Whether to enqueue post-persist learning instead of
+                running it inline.
 
         Returns:
             PublishUserInteractionResponse: Response containing success status and message
@@ -87,7 +97,12 @@ class InteractionsMixin(ReflexioBase):
             # Convert dict to PublishUserInteractionRequest if needed
             if isinstance(request, dict):
                 request = PublishUserInteractionRequest(**request)
-            result = generation_service.run(request)
+            result = generation_service.run(
+                request,
+                use_publish_limiter=use_publish_limiter,
+                publish_limiter_wait_forever=publish_limiter_wait_forever,
+                defer_learning=defer_learning,
+            )
             after_profiles = _safe_count(storage.count_all_profiles)
             after_playbooks = _safe_count(storage.count_user_playbooks)
             # Don't concatenate warnings into the message field — they

package/plugin/vendor/reflexio/reflexio/lib/_search.py

@@ -42,17 +42,21 @@ class SearchMixin(ReflexioBase):
 
         try:
             if request.start_time or request.end_time:
-                results = self._get_storage().get_agent_success_evaluation_results_in_window(
-                    from_ts=(
-                        int(request.start_time.timestamp()) if request.start_time else 0
-                    ),
-                    to_ts=(
-                        int(request.end_time.timestamp())
-                        if request.end_time
-                        else 2**31 - 1
-                    ),
-                    limit=request.limit or 100,
-                    agent_version=request.agent_version,
+                results = (
+                    self._get_storage().get_agent_success_evaluation_results_in_window(
+                        from_ts=(
+                            int(request.start_time.timestamp())
+                            if request.start_time
+                            else 0
+                        ),
+                        to_ts=(
+                            int(request.end_time.timestamp())
+                            if request.end_time
+                            else 2**31 - 1
+                        ),
+                        limit=request.limit or 100,
+                        agent_version=request.agent_version,
+                    )
                 )
             else:
                 results = self._get_storage().get_agent_success_evaluation_results(

package/plugin/vendor/reflexio/reflexio/models/api_schema/domain/enums.py

@@ -46,6 +46,7 @@ class Status(str, Enum):  # noqa: UP042 - CURRENT=None is not compatible with St
     SUPERSEDED = (
         "superseded"  # tombstone: replaced by a new version (superseded_by set)
     )
+    EXPIRED = "expired"  # tombstone: TTL elapsed while active (see expiry reclamation)
 
 
 class OperationStatus(StrEnum):

package/plugin/vendor/reflexio/reflexio/models/config_schema.py

@@ -708,11 +708,27 @@ class LineageGCConfig(BaseModel):
     poll_interval_seconds: int = Field(default=86400, gt=0)
 
 
+class ExpiryReclamationConfig(BaseModel):
+    """Direct-delete reclamation of expired plain rows (non-audited).
+
+    Independent of ``lineage_gc``: these rows carry no PII/audit/grace obligation,
+    so they can be reclaimed whenever this is enabled even if tombstone GC is off.
+
+    Opt-in by default (``enabled=False``) so operators control a staged rollout
+    of the direct-delete Class B sweeps and are not surprised by deletions on
+    upgrade.  ``lineage_gc.enabled`` (which defaults to True) is unaffected and
+    continues to drive the Class A profile-expiry and tombstone-GC paths.
+    """
+
+    enabled: bool = False
+
+
 class GovernanceRetentionConfig(BaseModel):
     """Audit-event retention policy. **Enterprise-only:** reclamation is performed
-    by the reflexio_ext GovernanceRetentionCapability. In an OSS-only deployment
-    these knobs are accepted but inert (the OSS lineage scheduler does not reclaim
-    audit events) and the server logs a startup warning when retention is enabled.
+    by an enterprise per-org reclamation sweep registered via
+    ``register_per_org_sweep``. In an OSS-only deployment these knobs are accepted
+    but inert (the OSS lineage scheduler does not reclaim audit events) and the
+    server logs a startup warning when retention is enabled.
     """
 
     audit_events_retention_enabled: bool = False
@@ -859,6 +875,10 @@ class Config(BaseModel):
     )
     # Tombstone GC job gate (opt-in, off by default — see LineageGCConfig)
     lineage_gc: LineageGCConfig = Field(default_factory=LineageGCConfig)
+    # Direct-delete reclamation of expired plain rows (share links, pending tool calls)
+    expiry_reclamation: ExpiryReclamationConfig = Field(
+        default_factory=ExpiryReclamationConfig
+    )
     governance_retention: GovernanceRetentionConfig = Field(
         default_factory=GovernanceRetentionConfig
     )
@@ -920,6 +940,7 @@ class Config(BaseModel):
                 "reflection_config",
                 "playbook_optimizer_config",
                 "lineage_gc",
+                "expiry_reclamation",
                 "governance_retention",
                 "pending_tool_call_config",
                 "retrieval_floor",

package/plugin/vendor/reflexio/reflexio/server/README.md

@@ -33,8 +33,9 @@ Description: FastAPI backend server that processes user interactions to generate
 
 ## Main Entry Points
 
-- **API**: `api.py` - FastAPI routes (only place to expose endpoints)
-- **Endpoint Helpers**: `api_endpoints/` - Bridge between routes and business logic
+- **API composer**: `api.py` - `create_app()` factory, middleware/capability wiring, OpenAPI auth decoration, and `core_router` aggregation
+- **Domain routes**: `routes/` - FastAPI route modules; add new public API surfaces here and include their routers in `api.py`
+- **Endpoint Helpers**: `api_endpoints/` - Shared handlers/helpers plus `RequestContext` used by route modules
 - **Extension Registry**: `extensions.py` - Capability and service registry for optional OSS/enterprise integrations
 - **Core Service**: `services/generation_service.py` - Main orchestrator
 
@@ -57,7 +58,19 @@ Description: FastAPI backend server that processes user interactions to generate
 
 **Directory**: `api_endpoints/`
 
-**Detailed Documentation**: See [`api_endpoints/README.md`](api_endpoints/README.md) for the `RequestContext` contract and per-file handler map.
+**Route modules** live in `routes/` and are grouped by domain. `api.py` remains the composition root: it creates `core_router`, includes each domain router, and mounts the aggregate router into the FastAPI app. **Detailed handler documentation**: See [`api_endpoints/README.md`](api_endpoints/README.md) for the `RequestContext` contract and helper map.
+
+| Route file | Purpose |
+|------|---------|
+| `routes/system.py` | Root/health/version and operation status/cancel surfaces. |
+| `routes/interactions.py` | Publish, request/session/interaction retrieval, direct interaction writes, and clear-data operations. |
+| `routes/profiles.py` | Profile retrieval, statistics, rerun/manual generation, upgrade/downgrade, update/delete lifecycle routes. |
+| `routes/playbooks.py` | User/agent playbook retrieval, aggregation, lifecycle, status/update/delete, and application stats routes. |
+| `routes/search.py` | Unified search and entity-specific search/rerank routes. |
+| `routes/provenance.py` | Learning provenance and approval routes. |
+| `routes/evaluation.py` | Evaluation overview, regenerate jobs, grade-on-demand, shadow comparisons, pending tool calls, and stall-state routes. |
+| `routes/braintrust.py` | Braintrust connection/project/status/sync routes. |
+| `routes/config.py` | Config read/write and account identity routes. |
 
 | File | Purpose |
 |------|---------|
@@ -97,10 +110,13 @@ Description: FastAPI backend server that processes user interactions to generate
 ## LLM Client
 
 **Directory**: `llm/`
-**Entry Point**: `litellm_client.py` - `LiteLLMClient`
+**Entry Point**: `litellm_client.py` - `LiteLLMClient` facade composed from focused mixins
 
 Key files:
-- `litellm_client.py`: Unified LiteLLMClient using LiteLLM for multi-provider support
+- `litellm_client.py`: Stable import surface, client config/credential resolution, and `LiteLLMClient` facade
+- `_litellm_text_generation.py`, `_litellm_embedding.py`, `_litellm_structured_output.py`: Completion/tool-call, embedding, and structured-output mixins
+- `_litellm_json_extraction.py`, `_litellm_subprocess.py`, `_litellm_types.py`: JSON parsing, hard-timeout subprocess snapshots/workers, and shared public types/errors
+- `providers/`: Optional local/provider adapters (`claude-code/`, OpenClaw, local embedding, Nomic embedding); registration is opt-in via environment/config
 - `openai_client.py`: OpenAI implementation (legacy, do not use directly)
 - `claude_client.py`: Claude implementation (legacy, do not use directly)
 - `llm_utils.py`: Helper functions for Pydantic model conversion
@@ -230,7 +246,8 @@ Called by API endpoints via `Reflexio`
 
 ### Base Infrastructure
 
-- `base_generation_service.py`: Abstract base for all services (parallel extractor execution via ThreadPoolExecutor, `EXTRACTOR_TIMEOUT_SECONDS = 300` per-extractor safety timeout)
+- `base_generation_service.py`: Stable `BaseGenerationService` import surface plus service-specific orchestration hooks (parallel extractor execution via ThreadPoolExecutor, `EXTRACTOR_TIMEOUT_SECONDS = 300` per-extractor safety timeout)
+- `base_generation/`: Mixins for batch progress, config filtering, extraction lifecycle, should-run prechecks, status transitions, and usage billing that keep `base_generation_service.py` navigable without changing caller imports
 - `extractor_config_utils.py`: Shared utility for filtering extractor configs by source, `allow_manual_trigger`, and extractor names
 - `extractor_interaction_utils.py`: Per-extractor utilities for stride_size checking and source filtering
 - `operation_state_utils.py`: Centralized `OperationStateManager` for all `_operation_state` table interactions (progress tracking, concurrency locks, extractor/aggregator bookmarks, simple locks)
@@ -488,8 +505,8 @@ Pre-computed embeddings passed to storage methods via `query_embedding` paramete
 
 | File | Purpose |
 |------|---------|
-| `storage_base/` | BaseStorage interface split by domain (`_profiles.py`, `_playbook.py`, `_requests.py`, `_operations.py`, `_agent_run.py`, `_lineage.py`, `_shadow_verdicts.py`, `_stall_state.py`, `_share_links.py`) |
-| `sqlite_storage/` | SQLite-backed implementation split across the same domains, including governance-aware retention/barrier handling and lineage/tombstone support in `_governance.py` / `_lineage.py` |
+| `storage_base/` | BaseStorage interface split by domain. Legacy facades (`_profiles.py`, `_playbook.py`, `_agent_run.py`, etc.) preserve imports while subpackages (`profiles/`, `playbook/`, `agent_run/`, `governance/`) hold focused abstract store contracts. |
+| `sqlite_storage/` | SQLite-backed implementation split across matching facades and subpackages (`profiles/`, `playbook/`, `agent_run/`, `governance/`, `base/`), including governance-aware retention/barrier handling and lineage/tombstone support. |
 | `governance_validation.py` | Shared validation helpers for subject references and governance contracts before storage writes. |
 | `retention.py`, `retention_mixin.py` | Data retention and cleanup helpers |
 | `constants.py`, `error.py` | Storage constants and shared errors |

package/plugin/vendor/reflexio/reflexio/server/__init__.py

@@ -230,5 +230,24 @@ if DEBUG_LOG_TO_CONSOLE:
         logging.ERROR
     )
 else:
-    # Default to WARNING level when DEBUG_LOG_TO_CONSOLE is not set or is false
-    root_logger.setLevel(logging.WARNING)
+    # Production (DEBUG_LOG_TO_CONSOLE off): emit INFO+ app logs to stdout so the
+    # container log driver (e.g. CloudWatch awslogs) captures business-logic audit
+    # lines — billing/webhook/enforcement, etc. Without an explicit handler the
+    # stdlib "handler of last resort" emits only WARNING+ to stderr, so INFO logs
+    # were silently dropped in production. Plain formatter (no colors/files/dedup)
+    # keeps this lean and log-driver friendly — none of the DEBUG-branch overhead.
+    root_logger.setLevel(logging.INFO)
+    if not any(isinstance(h, logging.StreamHandler) for h in root_logger.handlers):
+        prod_console_handler = logging.StreamHandler(sys.stdout)
+        prod_console_handler.setLevel(logging.INFO)
+        prod_console_handler.setFormatter(
+            logging.Formatter("%(asctime)s %(name)s %(levelname)s %(message)s")
+        )
+        root_logger.addHandler(prod_console_handler)
+
+    # Keep noisy loggers quiet even at INFO (mirror the debug branch's suppression).
+    for _noisy in ("litellm", "LiteLLM", "httpx", "httpcore", "openai", "urllib3"):
+        logging.getLogger(_noisy).setLevel(logging.WARNING)
+    logging.getLogger("reflexio.server.site_var.site_var_manager").setLevel(
+        logging.ERROR
+    )