atmem 2.2.0__tar.gz → 2.2.3__tar.gz

{atmem-2.2.0/atmem.egg-info → atmem-2.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: atmem
-Version: 2.2.0
+Version: 2.2.3
 Summary: Host-neutral Agent Black Box and reversible memory control plane.
 Author-email: aetna000 <aetna000@gmail.com>
 Maintainer-email: aetna000 <aetna000@gmail.com>
@@ -24,7 +24,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: atmem-atbot==0.1.0a1
+Requires-Dist: atmem-atbot==0.1.0a2
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
 Requires-Dist: tomli>=2.0; python_version < "3.11" and extra == "dev"
@@ -44,14 +44,128 @@ Dynamic: license-file
 
 # AtMem
 
-[![Version 2.2.0](https://img.shields.io/badge/version-2.2.0-blue)](./docs/releases/v2.2.0.md)
+[![Version 2.2.3](https://img.shields.io/badge/version-2.2.3-blue)](./docs/releases/v2.2.3.md)
 [![CI](https://github.com/aetna000/atmem/actions/workflows/ci.yml/badge.svg)](https://github.com/aetna000/atmem/actions/workflows/ci.yml)
 
 **AtMem is a host-neutral Agent Black Box and reversible memory control plane.**
 
-> **Release status:** this repository describes **AtMem 2.2.0**. AtBot is a
-> separately packaged, headless intelligence companion installed and managed
-> by AtMem; AtMem remains the memory authority.
+Install AtMem once and give OpenClaw, Pydantic AI, LangChain/LangGraph, or a
+custom agent governed long-term memory. **AtBot is installed automatically** as
+AtMem's private intelligence companion: AtBot proposes and ranks; AtMem alone
+authorizes, stores, scopes, injects, corrects, and deletes memory.
+
+## Start here
+
+### 1. Install AtMem and choose memory intelligence
+
+```bash
+python -m pip install --upgrade atmem==2.2.3
+atmem atbot setup
+atmem atbot doctor
+atmem dashboard
+```
+
+That one Python installation includes the pinned `atmem-atbot` package and an
+always-present local vector index. Do **not** install AtBot separately. During
+`atmem atbot setup`, choose local Ollama, a local OpenAI-compatible model, a
+hosted provider, or the safe deterministic fallback. API keys stay in
+environment variables; AtMem does not save them.
+
+### 2. Connect your agent
+
+#### OpenClaw — fully managed
+
+```bash
+atmem openclaw install
+atmem control verify
+```
+
+AtMem installs the matching npm bridge, discovers OpenClaw agents and
+workspaces, starts in safe shadow mode, restarts the gateway, and verifies the
+connection. Do not install the npm package yourself.
+
+Already using AtMem 2.1 with OpenClaw? Upgrade in place:
+
+```bash
+python -m pip install --upgrade atmem==2.2.3
+atmem openclaw upgrade
+atmem control verify
+```
+
+#### Pydantic AI — native capability
+
+```bash
+python -m pip install 'atmem[pydantic-ai]==2.2.3'
+atmem control shadow --host generic --memory-db ~/.atmem/memories.db
+```
+
+```python
+from pydantic_ai import Agent
+from atmem.adapters import AtMemAdapterIdentity
+from atmem.adapters.pydantic_ai import PydanticAIAtMemAdapter
+from atmem.control import ControlPlaneManager
+
+manager = ControlPlaneManager()
+scope = manager.agent_topology()["agents"][0]
+identity = AtMemAdapterIdentity(
+    agent_id=scope["agent_id"],
+    workspace_id=scope["workspace_id"],
+    subject_id=scope["subject_id"],
+)
+memory = PydanticAIAtMemAdapter(manager, identity).capability()
+agent = Agent("openai:gpt-5-mini", capabilities=[memory])
+```
+
+#### LangChain/LangGraph — native middleware
+
+```bash
+python -m pip install 'atmem[langgraph]==2.2.3'
+atmem control shadow --host generic --memory-db ~/.atmem/memories.db
+```
+
+```python
+from langchain.agents import create_agent
+from atmem.adapters import AtMemAdapterIdentity
+from atmem.adapters.langgraph import create_langgraph_middleware
+from atmem.control import ControlPlaneManager
+
+manager = ControlPlaneManager()
+scope = manager.agent_topology()["agents"][0]
+identity = AtMemAdapterIdentity(
+    agent_id=scope["agent_id"],
+    workspace_id=scope["workspace_id"],
+    subject_id=scope["subject_id"],
+)
+memory = create_langgraph_middleware(manager, identity)
+agent = create_agent(model="openai:gpt-5-mini", tools=[], middleware=[memory])
+```
+
+The framework hooks automate authenticated capture, governed retrieval,
+context injection, exposure proof, and turn/tool evidence. They do not replace
+your agent's model, tools, conversation history, or LangGraph checkpoints. See
+the [complete framework adapter guide](docs/framework-adapters.md) for async,
+multi-agent, and low-level `StateGraph` integration.
+
+### 3. Review, then activate
+
+Every integration starts in **shadow mode**: AtMem learns and shows what it
+would retrieve, but cannot change model context. Review it in the dashboard,
+then explicitly enable governed injection:
+
+```bash
+atmem dashboard
+atmem control status
+atmem control activate
+atmem control verify
+```
+
+If AtBot or its selected model is unavailable, AtMem continues with safe local
+capture and hybrid ranking. Memory authority and agent operation do not depend
+on a hosted model.
+
+> **Release status:** this repository describes **AtMem 2.2.3**. AtBot is a
+> separately packaged, headless component installed and managed by AtMem; it is
+> not an independent agent or a second memory authority.
 
 It gives agent runtimes one governed memory source and one tamper-evident record
 of what the host observed: memory considered and injected, model boundaries,
@@ -65,10 +179,10 @@ evidence, activate AtMem explicitly, and return to shadow at any time. The
 OpenClaw adapter additionally copies native memory, freezes it during takeover,
 and restores it exactly.
 
-## Install
+## Installation details
 
 ```bash
-python -m pip install atmem==2.2.0
+python -m pip install atmem==2.2.3
 atmem --version
 ```
 
@@ -76,11 +190,10 @@ AtMem requires Python 3.10 or newer. It always creates a dependency-free local
 vector sidecar; the semantic extra adds an optional local embedding upgrade:
 
 ```bash
-python -m pip install 'atmem[semantic]==2.2.0'
+python -m pip install 'atmem[semantic]==2.2.3'
 ```
 
-For repository development, install both packages so the exact companion
-version is satisfied locally:
+For repository development, install both workspace packages:
 
 ```bash
 python -m pip install -e './packages/atbot[dev]' -e '.[dev]'
@@ -92,7 +205,7 @@ AtMem distribution requires the separately packaged, exactly pinned AtBot
 companion. Consequently a complete 2.2 installation has AtBot's transitive
 dependencies even when the user selects AtMem's deterministic fallback.
 
-## Choose an integration
+## Integration boundaries
 
 | Runtime | Start command | What AtMem supplies | What the runtime supplies |
 | --- | --- | --- | --- |
@@ -257,7 +370,7 @@ atmem control restore
 Existing 2.1 installations upgrade without starting a new migration:
 
 ```bash
-python -m pip install --upgrade atmem==2.2.0
+python -m pip install --upgrade atmem==2.2.3
 atmem openclaw upgrade
 atmem control verify
 ```
@@ -403,7 +516,7 @@ npm test
 npm run smoke
 ```
 
-Current repository metadata is version **2.2.0**. Python and npm release
+Current repository metadata is version **2.2.3**. Python and npm release
 versions are intentionally kept equal because the OpenClaw installer pins the
 matching bridge.
 

{atmem-2.2.0 → atmem-2.2.3}/README.md

@@ -1,13 +1,127 @@
 # AtMem
 
-[![Version 2.2.0](https://img.shields.io/badge/version-2.2.0-blue)](./docs/releases/v2.2.0.md)
+[![Version 2.2.3](https://img.shields.io/badge/version-2.2.3-blue)](./docs/releases/v2.2.3.md)
 [![CI](https://github.com/aetna000/atmem/actions/workflows/ci.yml/badge.svg)](https://github.com/aetna000/atmem/actions/workflows/ci.yml)
 
 **AtMem is a host-neutral Agent Black Box and reversible memory control plane.**
 
-> **Release status:** this repository describes **AtMem 2.2.0**. AtBot is a
-> separately packaged, headless intelligence companion installed and managed
-> by AtMem; AtMem remains the memory authority.
+Install AtMem once and give OpenClaw, Pydantic AI, LangChain/LangGraph, or a
+custom agent governed long-term memory. **AtBot is installed automatically** as
+AtMem's private intelligence companion: AtBot proposes and ranks; AtMem alone
+authorizes, stores, scopes, injects, corrects, and deletes memory.
+
+## Start here
+
+### 1. Install AtMem and choose memory intelligence
+
+```bash
+python -m pip install --upgrade atmem==2.2.3
+atmem atbot setup
+atmem atbot doctor
+atmem dashboard
+```
+
+That one Python installation includes the pinned `atmem-atbot` package and an
+always-present local vector index. Do **not** install AtBot separately. During
+`atmem atbot setup`, choose local Ollama, a local OpenAI-compatible model, a
+hosted provider, or the safe deterministic fallback. API keys stay in
+environment variables; AtMem does not save them.
+
+### 2. Connect your agent
+
+#### OpenClaw — fully managed
+
+```bash
+atmem openclaw install
+atmem control verify
+```
+
+AtMem installs the matching npm bridge, discovers OpenClaw agents and
+workspaces, starts in safe shadow mode, restarts the gateway, and verifies the
+connection. Do not install the npm package yourself.
+
+Already using AtMem 2.1 with OpenClaw? Upgrade in place:
+
+```bash
+python -m pip install --upgrade atmem==2.2.3
+atmem openclaw upgrade
+atmem control verify
+```
+
+#### Pydantic AI — native capability
+
+```bash
+python -m pip install 'atmem[pydantic-ai]==2.2.3'
+atmem control shadow --host generic --memory-db ~/.atmem/memories.db
+```
+
+```python
+from pydantic_ai import Agent
+from atmem.adapters import AtMemAdapterIdentity
+from atmem.adapters.pydantic_ai import PydanticAIAtMemAdapter
+from atmem.control import ControlPlaneManager
+
+manager = ControlPlaneManager()
+scope = manager.agent_topology()["agents"][0]
+identity = AtMemAdapterIdentity(
+    agent_id=scope["agent_id"],
+    workspace_id=scope["workspace_id"],
+    subject_id=scope["subject_id"],
+)
+memory = PydanticAIAtMemAdapter(manager, identity).capability()
+agent = Agent("openai:gpt-5-mini", capabilities=[memory])
+```
+
+#### LangChain/LangGraph — native middleware
+
+```bash
+python -m pip install 'atmem[langgraph]==2.2.3'
+atmem control shadow --host generic --memory-db ~/.atmem/memories.db
+```
+
+```python
+from langchain.agents import create_agent
+from atmem.adapters import AtMemAdapterIdentity
+from atmem.adapters.langgraph import create_langgraph_middleware
+from atmem.control import ControlPlaneManager
+
+manager = ControlPlaneManager()
+scope = manager.agent_topology()["agents"][0]
+identity = AtMemAdapterIdentity(
+    agent_id=scope["agent_id"],
+    workspace_id=scope["workspace_id"],
+    subject_id=scope["subject_id"],
+)
+memory = create_langgraph_middleware(manager, identity)
+agent = create_agent(model="openai:gpt-5-mini", tools=[], middleware=[memory])
+```
+
+The framework hooks automate authenticated capture, governed retrieval,
+context injection, exposure proof, and turn/tool evidence. They do not replace
+your agent's model, tools, conversation history, or LangGraph checkpoints. See
+the [complete framework adapter guide](docs/framework-adapters.md) for async,
+multi-agent, and low-level `StateGraph` integration.
+
+### 3. Review, then activate
+
+Every integration starts in **shadow mode**: AtMem learns and shows what it
+would retrieve, but cannot change model context. Review it in the dashboard,
+then explicitly enable governed injection:
+
+```bash
+atmem dashboard
+atmem control status
+atmem control activate
+atmem control verify
+```
+
+If AtBot or its selected model is unavailable, AtMem continues with safe local
+capture and hybrid ranking. Memory authority and agent operation do not depend
+on a hosted model.
+
+> **Release status:** this repository describes **AtMem 2.2.3**. AtBot is a
+> separately packaged, headless component installed and managed by AtMem; it is
+> not an independent agent or a second memory authority.
 
 It gives agent runtimes one governed memory source and one tamper-evident record
 of what the host observed: memory considered and injected, model boundaries,
@@ -21,10 +135,10 @@ evidence, activate AtMem explicitly, and return to shadow at any time. The
 OpenClaw adapter additionally copies native memory, freezes it during takeover,
 and restores it exactly.
 
-## Install
+## Installation details
 
 ```bash
-python -m pip install atmem==2.2.0
+python -m pip install atmem==2.2.3
 atmem --version
 ```
 
@@ -32,11 +146,10 @@ AtMem requires Python 3.10 or newer. It always creates a dependency-free local
 vector sidecar; the semantic extra adds an optional local embedding upgrade:
 
 ```bash
-python -m pip install 'atmem[semantic]==2.2.0'
+python -m pip install 'atmem[semantic]==2.2.3'
 ```
 
-For repository development, install both packages so the exact companion
-version is satisfied locally:
+For repository development, install both workspace packages:
 
 ```bash
 python -m pip install -e './packages/atbot[dev]' -e '.[dev]'
@@ -48,7 +161,7 @@ AtMem distribution requires the separately packaged, exactly pinned AtBot
 companion. Consequently a complete 2.2 installation has AtBot's transitive
 dependencies even when the user selects AtMem's deterministic fallback.
 
-## Choose an integration
+## Integration boundaries
 
 | Runtime | Start command | What AtMem supplies | What the runtime supplies |
 | --- | --- | --- | --- |
@@ -213,7 +326,7 @@ atmem control restore
 Existing 2.1 installations upgrade without starting a new migration:
 
 ```bash
-python -m pip install --upgrade atmem==2.2.0
+python -m pip install --upgrade atmem==2.2.3
 atmem openclaw upgrade
 atmem control verify
 ```
@@ -359,7 +472,7 @@ npm test
 npm run smoke
 ```
 
-Current repository metadata is version **2.2.0**. Python and npm release
+Current repository metadata is version **2.2.3**. Python and npm release
 versions are intentionally kept equal because the OpenClaw installer pins the
 matching bridge.
 

{atmem-2.2.0 → atmem-2.2.3}/atmem/adapters/pydantic_ai.py

@@ -1,4 +1,4 @@
-"""Pydantic AI 2.x Hooks adapter for automatic governed memory."""
+"""Pydantic AI Hooks adapter for automatic governed memory."""
 
 from __future__ import annotations
 
@@ -54,7 +54,7 @@ class PydanticAIAtMemAdapter:
             if governed:
                 messages.append(ModelRequest(parts=[UserPromptPart(governed)]))
             model_name = str(
-                request_context.model_id
+                getattr(request_context, "model_id", None)
                 or getattr(request_context.model, "model_name", None)
                 or getattr(request_context.model, "model_id", None)
                 or "unknown"

{atmem-2.2.0 → atmem-2.2.3}/atmem/control/atbot_service.py

@@ -16,7 +16,7 @@ from typing import Any
 from urllib.parse import urlparse
 
 
-PINNED_ATBOT_VERSION = "0.1.0a1"
+PINNED_ATBOT_VERSION = "0.1.0a2"
 ATBOT_DISTRIBUTION = "atmem-atbot"
 ATBOT_PROTOCOL_VERSION = "1"
 DEFAULT_ROOT = Path.home() / ".atmem" / "atbot"

{atmem-2.2.0 → atmem-2.2.3}/atmem/mcp/server.py

@@ -26,7 +26,7 @@ try:
 
     SERVER_VERSION = _pkg_version("atmem")
 except Exception:  # not installed (e.g. run from a checkout)
-    SERVER_VERSION = "2.2.0"
+    SERVER_VERSION = "2.2.3"
 
 _SUBJECT_PROPERTY = {
     "subject_id": {

{atmem-2.2.0 → atmem-2.2.3}/atmem/openclaw_install.py

@@ -16,7 +16,7 @@ from atmem.control.manager import DEFAULT_STATE_PATH, DEFAULT_CONTROL_ROOT
 
 OPENCLAW_PLUGIN_ID = "memory-atmem"
 OPENCLAW_PLUGIN_PACKAGE = "openclaw-memory-atmem"
-OPENCLAW_PLUGIN_VERSION = "2.2.0"
+OPENCLAW_PLUGIN_VERSION = "2.2.3"
 _CONFIG_KEY = "plugins.entries.memory-atmem"
 
 

{atmem-2.2.0 → atmem-2.2.3/atmem.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: atmem
-Version: 2.2.0
+Version: 2.2.3
 Summary: Host-neutral Agent Black Box and reversible memory control plane.
 Author-email: aetna000 <aetna000@gmail.com>
 Maintainer-email: aetna000 <aetna000@gmail.com>
@@ -24,7 +24,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: atmem-atbot==0.1.0a1
+Requires-Dist: atmem-atbot==0.1.0a2
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
 Requires-Dist: tomli>=2.0; python_version < "3.11" and extra == "dev"
@@ -44,14 +44,128 @@ Dynamic: license-file
 
 # AtMem
 
-[![Version 2.2.0](https://img.shields.io/badge/version-2.2.0-blue)](./docs/releases/v2.2.0.md)
+[![Version 2.2.3](https://img.shields.io/badge/version-2.2.3-blue)](./docs/releases/v2.2.3.md)
 [![CI](https://github.com/aetna000/atmem/actions/workflows/ci.yml/badge.svg)](https://github.com/aetna000/atmem/actions/workflows/ci.yml)
 
 **AtMem is a host-neutral Agent Black Box and reversible memory control plane.**
 
-> **Release status:** this repository describes **AtMem 2.2.0**. AtBot is a
-> separately packaged, headless intelligence companion installed and managed
-> by AtMem; AtMem remains the memory authority.
+Install AtMem once and give OpenClaw, Pydantic AI, LangChain/LangGraph, or a
+custom agent governed long-term memory. **AtBot is installed automatically** as
+AtMem's private intelligence companion: AtBot proposes and ranks; AtMem alone
+authorizes, stores, scopes, injects, corrects, and deletes memory.
+
+## Start here
+
+### 1. Install AtMem and choose memory intelligence
+
+```bash
+python -m pip install --upgrade atmem==2.2.3
+atmem atbot setup
+atmem atbot doctor
+atmem dashboard
+```
+
+That one Python installation includes the pinned `atmem-atbot` package and an
+always-present local vector index. Do **not** install AtBot separately. During
+`atmem atbot setup`, choose local Ollama, a local OpenAI-compatible model, a
+hosted provider, or the safe deterministic fallback. API keys stay in
+environment variables; AtMem does not save them.
+
+### 2. Connect your agent
+
+#### OpenClaw — fully managed
+
+```bash
+atmem openclaw install
+atmem control verify
+```
+
+AtMem installs the matching npm bridge, discovers OpenClaw agents and
+workspaces, starts in safe shadow mode, restarts the gateway, and verifies the
+connection. Do not install the npm package yourself.
+
+Already using AtMem 2.1 with OpenClaw? Upgrade in place:
+
+```bash
+python -m pip install --upgrade atmem==2.2.3
+atmem openclaw upgrade
+atmem control verify
+```
+
+#### Pydantic AI — native capability
+
+```bash
+python -m pip install 'atmem[pydantic-ai]==2.2.3'
+atmem control shadow --host generic --memory-db ~/.atmem/memories.db
+```
+
+```python
+from pydantic_ai import Agent
+from atmem.adapters import AtMemAdapterIdentity
+from atmem.adapters.pydantic_ai import PydanticAIAtMemAdapter
+from atmem.control import ControlPlaneManager
+
+manager = ControlPlaneManager()
+scope = manager.agent_topology()["agents"][0]
+identity = AtMemAdapterIdentity(
+    agent_id=scope["agent_id"],
+    workspace_id=scope["workspace_id"],
+    subject_id=scope["subject_id"],
+)
+memory = PydanticAIAtMemAdapter(manager, identity).capability()
+agent = Agent("openai:gpt-5-mini", capabilities=[memory])
+```
+
+#### LangChain/LangGraph — native middleware
+
+```bash
+python -m pip install 'atmem[langgraph]==2.2.3'
+atmem control shadow --host generic --memory-db ~/.atmem/memories.db
+```
+
+```python
+from langchain.agents import create_agent
+from atmem.adapters import AtMemAdapterIdentity
+from atmem.adapters.langgraph import create_langgraph_middleware
+from atmem.control import ControlPlaneManager
+
+manager = ControlPlaneManager()
+scope = manager.agent_topology()["agents"][0]
+identity = AtMemAdapterIdentity(
+    agent_id=scope["agent_id"],
+    workspace_id=scope["workspace_id"],
+    subject_id=scope["subject_id"],
+)
+memory = create_langgraph_middleware(manager, identity)
+agent = create_agent(model="openai:gpt-5-mini", tools=[], middleware=[memory])
+```
+
+The framework hooks automate authenticated capture, governed retrieval,
+context injection, exposure proof, and turn/tool evidence. They do not replace
+your agent's model, tools, conversation history, or LangGraph checkpoints. See
+the [complete framework adapter guide](docs/framework-adapters.md) for async,
+multi-agent, and low-level `StateGraph` integration.
+
+### 3. Review, then activate
+
+Every integration starts in **shadow mode**: AtMem learns and shows what it
+would retrieve, but cannot change model context. Review it in the dashboard,
+then explicitly enable governed injection:
+
+```bash
+atmem dashboard
+atmem control status
+atmem control activate
+atmem control verify
+```
+
+If AtBot or its selected model is unavailable, AtMem continues with safe local
+capture and hybrid ranking. Memory authority and agent operation do not depend
+on a hosted model.
+
+> **Release status:** this repository describes **AtMem 2.2.3**. AtBot is a
+> separately packaged, headless component installed and managed by AtMem; it is
+> not an independent agent or a second memory authority.
 
 It gives agent runtimes one governed memory source and one tamper-evident record
 of what the host observed: memory considered and injected, model boundaries,
@@ -65,10 +179,10 @@ evidence, activate AtMem explicitly, and return to shadow at any time. The
 OpenClaw adapter additionally copies native memory, freezes it during takeover,
 and restores it exactly.
 
-## Install
+## Installation details
 
 ```bash
-python -m pip install atmem==2.2.0
+python -m pip install atmem==2.2.3
 atmem --version
 ```
 
@@ -76,11 +190,10 @@ AtMem requires Python 3.10 or newer. It always creates a dependency-free local
 vector sidecar; the semantic extra adds an optional local embedding upgrade:
 
 ```bash
-python -m pip install 'atmem[semantic]==2.2.0'
+python -m pip install 'atmem[semantic]==2.2.3'
 ```
 
-For repository development, install both packages so the exact companion
-version is satisfied locally:
+For repository development, install both workspace packages:
 
 ```bash
 python -m pip install -e './packages/atbot[dev]' -e '.[dev]'
@@ -92,7 +205,7 @@ AtMem distribution requires the separately packaged, exactly pinned AtBot
 companion. Consequently a complete 2.2 installation has AtBot's transitive
 dependencies even when the user selects AtMem's deterministic fallback.
 
-## Choose an integration
+## Integration boundaries
 
 | Runtime | Start command | What AtMem supplies | What the runtime supplies |
 | --- | --- | --- | --- |
@@ -257,7 +370,7 @@ atmem control restore
 Existing 2.1 installations upgrade without starting a new migration:
 
 ```bash
-python -m pip install --upgrade atmem==2.2.0
+python -m pip install --upgrade atmem==2.2.3
 atmem openclaw upgrade
 atmem control verify
 ```
@@ -403,7 +516,7 @@ npm test
 npm run smoke
 ```
 
-Current repository metadata is version **2.2.0**. Python and npm release
+Current repository metadata is version **2.2.3**. Python and npm release
 versions are intentionally kept equal because the OpenClaw installer pins the
 matching bridge.
 

{atmem-2.2.0 → atmem-2.2.3}/atmem.egg-info/SOURCES.txt

@@ -92,6 +92,9 @@ docs/releases/v2.0.0.md
 docs/releases/v2.0.1.md
 docs/releases/v2.1.0.md
 docs/releases/v2.2.0.md
+docs/releases/v2.2.1.md
+docs/releases/v2.2.2.md
+docs/releases/v2.2.3.md
 integrations/openclaw/README.md
 integrations/openclaw/index.ts
 integrations/openclaw/openclaw.plugin.json

{atmem-2.2.0 → atmem-2.2.3}/atmem.egg-info/requires.txt

@@ -1,4 +1,4 @@
-atmem-atbot==0.1.0a1
+atmem-atbot==0.1.0a2
 
 [atbot]
 

{atmem-2.2.0 → atmem-2.2.3}/docs/agent-blackbox.md

@@ -61,6 +61,11 @@ a small model charge.
 A structurally complete flight has covered integrity, lifecycle, context, model,
 tools, and response-binding components. In particular:
 
+OpenClaw normally observes `turn.input` at `before_model_resolve`. Execution
+paths such as `claude-cli` that omit that hook use `before_prompt_build` as an
+idempotent fallback. If both hooks fire, the bridge records and stages the
+authenticated input only once.
+
 - the retained Black Box hash chain verifies;
 - the run has `turn.input` and terminal `turn.ended` events;
 - one explicit context disposition records what memory reached the model, or why none did;

{atmem-2.2.0 → atmem-2.2.3}/docs/atbot-release.md

@@ -31,7 +31,7 @@ stored in GitHub.
 2. Run both Python suites and build both distributions locally.
 3. Push the reviewed changes.
 4. Create and push a tag matching `atbot-v<VERSION>`, for example
-   `atbot-v0.1.0a1`.
+   `atbot-v0.1.0a2`.
 5. Approve the protected `pypi-atbot` environment deployment.
 6. Confirm `python -m pip install atmem-atbot==<VERSION>` installs an `atbot`
    command with the same version.