atmem 2.2.4__tar.gz → 2.2.6__tar.gz

{atmem-2.2.4 → atmem-2.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: atmem
-Version: 2.2.4
+Version: 2.2.6
 Summary: Host-neutral Agent Black Box and reversible memory control plane.
 Author-email: aetna000 <aetna000@gmail.com>
 Maintainer-email: aetna000 <aetna000@gmail.com>
@@ -10,7 +10,7 @@ Project-URL: Repository, https://github.com/aetna000/atmem
 Project-URL: Issues, https://github.com/aetna000/atmem/issues
 Project-URL: Documentation, https://github.com/aetna000/atmem#readme
 Keywords: agent-black-box,agent-memory,audit,mcp,provenance,sqlite
-Classifier: Development Status :: 5 - Production/Stable
+Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: Programming Language :: Python :: 3
@@ -24,12 +24,20 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: atmem-atbot==0.1.0a3
+Requires-Dist: atmem-atbot==0.1.0a6
+Requires-Dist: cryptography<49,>=42
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
 Requires-Dist: tomli>=2.0; python_version < "3.11" and extra == "dev"
 Provides-Extra: semantic
 Requires-Dist: sentence-transformers<6.0.0,>=5.0.0; extra == "semantic"
+Provides-Extra: mem0
+Requires-Dist: mem0ai<3,>=2.0.20; extra == "mem0"
+Provides-Extra: langgraph-provider
+Requires-Dist: langgraph<2,>=1.1.5; extra == "langgraph-provider"
+Provides-Extra: pydantic-provider
+Requires-Dist: pydantic-ai-slim<3,>=2.0; extra == "pydantic-provider"
+Requires-Dist: pydantic<3,>=2.0; extra == "pydantic-provider"
 Provides-Extra: atbot
 Provides-Extra: pydantic-ai
 Requires-Dist: pydantic-ai-slim<3,>=2.0; extra == "pydantic-ai"
@@ -40,11 +48,32 @@ Provides-Extra: frameworks
 Requires-Dist: pydantic-ai-slim<3,>=2.0; extra == "frameworks"
 Requires-Dist: langgraph<2,>=1.1.5; extra == "frameworks"
 Requires-Dist: langchain<2,>=1.0; extra == "frameworks"
+Provides-Extra: openai-agents
+Requires-Dist: openai-agents<1,>=0.2; extra == "openai-agents"
+Provides-Extra: microsoft-agent
+Requires-Dist: agent-framework<2,>=1.0.0b1; extra == "microsoft-agent"
+Provides-Extra: google-adk
+Requires-Dist: google-adk<2,>=1; extra == "google-adk"
+Provides-Extra: smolagents
+Requires-Dist: smolagents<2,>=1; extra == "smolagents"
+Provides-Extra: crewai
+Requires-Dist: crewai<2,>=0.100; extra == "crewai"
+Provides-Extra: postgres
+Requires-Dist: psycopg<4,>=3.2; extra == "postgres"
+Provides-Extra: pgvector
+Requires-Dist: psycopg<4,>=3.2; extra == "pgvector"
+Requires-Dist: pgvector<1,>=0.4; extra == "pgvector"
+Provides-Extra: qdrant
+Requires-Dist: qdrant-client<2,>=1.15; extra == "qdrant"
+Provides-Extra: storage-backends
+Requires-Dist: psycopg<4,>=3.2; extra == "storage-backends"
+Requires-Dist: pgvector<1,>=0.4; extra == "storage-backends"
+Requires-Dist: qdrant-client<2,>=1.15; extra == "storage-backends"
 Dynamic: license-file
 
 # AtMem
 
-[![Version 2.2.4](https://img.shields.io/badge/version-2.2.4-blue)](./docs/releases/v2.2.4.md)
+[![Version 2.2.6](https://img.shields.io/badge/version-2.2.6-blue)](./docs/releases/v2.2.6.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.**
@@ -59,7 +88,7 @@ authorizes, stores, scopes, injects, corrects, and deletes memory.
 ### 1. Install AtMem and choose memory intelligence
 
 ```bash
-python -m pip install --upgrade atmem==2.2.4
+python -m pip install --upgrade atmem==2.2.6
 atmem atbot setup
 atmem atbot doctor
 atmem dashboard
@@ -82,12 +111,16 @@ 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.
+connection. It also offers to download the default local embedding model and
+build, verify, and activate its vector epoch. For unattended setup, make that
+approval explicit with `atmem openclaw install --allow-model-download`; choose
+another Ollama model with `--embedding-model MODEL`. Do not install the npm
+package yourself.
 
 Already using AtMem 2.1 with OpenClaw? Upgrade in place:
 
 ```bash
-python -m pip install --upgrade atmem==2.2.4
+python -m pip install --upgrade atmem==2.2.6
 atmem openclaw upgrade
 atmem control verify
 ```
@@ -110,7 +143,7 @@ selected by `python`, rather than an unrelated `pip` executable on `PATH`.
 #### Pydantic AI — native capability
 
 ```bash
-python -m pip install 'atmem[pydantic-ai]==2.2.4'
+python -m pip install 'atmem[pydantic-ai]==2.2.6'
 atmem control shadow --host generic --memory-db ~/.atmem/memories.db
 ```
 
@@ -126,6 +159,7 @@ identity = AtMemAdapterIdentity(
     agent_id=scope["agent_id"],
     workspace_id=scope["workspace_id"],
     subject_id=scope["subject_id"],
+    user_id="authenticated-application-user",  # required only for delegation
 )
 memory = PydanticAIAtMemAdapter(manager, identity).capability()
 agent = Agent("openai:gpt-5-mini", capabilities=[memory])
@@ -134,7 +168,7 @@ agent = Agent("openai:gpt-5-mini", capabilities=[memory])
 #### LangChain/LangGraph — native middleware
 
 ```bash
-python -m pip install 'atmem[langgraph]==2.2.4'
+python -m pip install 'atmem[langgraph]==2.2.6'
 atmem control shadow --host generic --memory-db ~/.atmem/memories.db
 ```
 
@@ -150,17 +184,69 @@ identity = AtMemAdapterIdentity(
     agent_id=scope["agent_id"],
     workspace_id=scope["workspace_id"],
     subject_id=scope["subject_id"],
+    user_id="authenticated-application-user",  # required only for delegation
 )
 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
+context injection, exposure proof, and turn/tool evidence. When an enabled
+delegated-provider registration matches the complete scope, they instead carry
+the exact HMAC-authenticated provider workflow through the Pydantic AI or
+LangChain/LangGraph model boundary, without also using native AtMem context.
+This delegated host path is packaged in 2.2.6. The adapters 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.
 
+### Spec 007 milestone: govern work in progress
+
+AtMem 2.2.6 includes Governed Task State: a separate, revisioned authority
+plane for what an agent is doing now, what remains, what is blocked, and
+whether completion is allowed. It is **disabled by default** and never turns
+temporary task progress into long-term personal memory.
+
+Start one exact scope and inspect it from either the CLI or the dashboard:
+
+```bash
+atmem task enable ~/.atmem/memories.db \
+  --subject user-1 --agent agent-1 --workspace workspace-1
+atmem task start ~/.atmem/memories.db --task-id release-007 \
+  --goal "Ship the governed task-state milestone" --actor you@example.com \
+  --required-item verify="Run release verification" \
+  --subject user-1 --agent agent-1 --workspace workspace-1
+atmem task show ~/.atmem/memories.db release-007 \
+  --subject user-1 --agent agent-1 --workspace workspace-1
+atmem dashboard
+```
+
+The dashboard's **Governed tasks** card shows progress, blockers, recent task
+decisions, context delivery, the current revision, and guarded lifecycle
+actions. Model delivery requires an exact task identity. Pydantic AI may supply
+`atmem_task_id` in run dependencies; LangGraph may supply it through
+`configurable`; construction-time `identity.for_task("release-007")` remains a
+backward-compatible fallback. OpenClaw resolves the owner-authorized current
+conversation binding. AtMem never guesses from prompt text or chooses among
+open tasks. AtBot may propose a change, but AtMem revalidates and commits it.
+
+See the [Governed Task State guide](docs/governed-task-state.md) for lifecycle,
+correction, provenance, expiry, benchmark, and automation examples, and read
+the [2.2.6 release notes](docs/releases/v2.2.6.md) before upgrading.
+
+### Prove memory quality locally
+
+```bash
+atmem benchmark run --output benchmark.json
+```
+
+This offline release gate runs 16 isolated extraction, contradiction, recall,
+withholding, injection, privacy, poisoning and fallback cases. Safety must be
+perfect; other quality metrics cannot fall below checked-in baselines. Optional
+local/hosted profiles, LongMemEval import and fair Mem0 OSS comparison are also
+available without adding Mem0 or model SDKs to the base install. See the
+[memory benchmark guide](docs/benchmarks.md) for commands and honest limits.
+
 ### 3. Review, then activate
 
 Every integration starts in **shadow mode**: AtMem learns and shows what it
@@ -178,10 +264,57 @@ 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 2.2.4**. AtBot is a
+> **Release status:** this repository describes the **AtMem 2.2.6 release candidate**, not verified publication. AtBot is a
 > separately packaged, headless component installed and managed by AtMem; it is
 > not an independent agent or a second memory authority.
 
+### Optional: delegate context authority
+
+Beta 10 requires per-instance HMAC request credentials for delegated context and
+health. See the
+[shared profile and beta migration](docs/contracts/delegated-request-auth-v1.md)
+before enabling an older delegated registration.
+
+AtMem uses its own governed retrieval by default. The 2.2.6 beta adds an
+explicit, provider-neutral delegated mode for deployments where another
+compatible provider must make the context decision while AtMem owns
+host integration and flight evidence.
+
+```bash
+atmem delegated register --help
+atmem delegated status
+atmem delegated enable context-provider:local
+atmem delegated doctor
+```
+
+Registration is disabled by default and is bound to exact user, agent, and
+workspace scopes. On matching turns, AtMem verifies the signed result, injects
+the provider's exact bytes once, and separately proves delivery. It does not
+run native retrieval after an accepted delegated decision. Provider failure
+withholds context unless the operator explicitly registered native fallback.
+See the [delegated context-provider guide](docs/delegated-context-provider.md).
+
+AtMem also ships provider-side adapters, each as an independent optional extra:
+
+```bash
+# Mem0 chooses context; AtMem verifies and records delivery
+python -m pip install 'atmem[mem0]'
+atmem provider init mem0-local --kind mem0 --mode oss --port 8788
+
+# Or use an application-owned LangGraph / Pydantic AI factory
+python -m pip install 'atmem[langgraph-provider]'
+atmem provider init graph-context --kind langgraph \
+  --factory myapp.memory_graph:build_graph --port 8789
+
+python -m pip install 'atmem[pydantic-provider]'
+atmem provider init ai-context --kind pydantic-ai \
+  --factory myapp.memory_agent:build_agent --port 8790
+```
+
+`atmem provider init` creates private signing material and prints the exact
+registration command; it does not enable delegated authority. See the
+[context-provider adapter quick starts](docs/context-provider-adapters.md).
+
 It gives agent runtimes one governed memory source and one tamper-evident record
 of what the host observed: memory considered and injected, model boundaries,
 tool requests and completions, turn termination, and linked external outcome
@@ -197,15 +330,17 @@ and restores it exactly.
 ## Installation details
 
 ```bash
-python -m pip install atmem==2.2.4
+python -m pip install atmem==2.2.6
 atmem --version
 ```
 
 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:
+vector sidecar. `atmem openclaw install` can automatically prepare an Ollama
+embedding model, while the semantic extra adds local sentence-transformer
+choices:
 
 ```bash
-python -m pip install 'atmem[semantic]==2.2.4'
+python -m pip install 'atmem[semantic]==2.2.6'
 ```
 
 For repository development, install both workspace packages:
@@ -215,10 +350,10 @@ python -m pip install -e './packages/atbot[dev]' -e '.[dev]'
 atmem atbot setup
 ```
 
-The authority modules remain model-agnostic and do not import AtBot, but the
-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.
+The authority modules remain model-agnostic and do not import AtBot. The AtMem
+distribution requires the separately packaged, exactly pinned AtBot companion,
+whose built-in Ollama and OpenAI-compatible client uses only the Python standard
+library. Framework SDKs enter the environment only through explicit extras.
 
 ## Integration boundaries
 
@@ -385,7 +520,7 @@ atmem control restore
 Existing 2.1 installations upgrade without starting a new migration:
 
 ```bash
-python -m pip install --upgrade atmem==2.2.4
+python -m pip install --upgrade atmem==2.2.6
 atmem openclaw upgrade
 atmem control verify
 ```
@@ -445,6 +580,7 @@ atmem mcp --db ~/.atmem/memories.db --subject user-1
 ```
 
 MCP tools: `memory_remember`, `memory_observe`, `memory_recall`,
+`memory_recall_decision`,
 `memory_get_record`, `memory_get_source`, `memory_recall_block`,
 `memory_persona`, `memory_context_pack`, `memory_capture`, `memory_list`,
 `memory_forget`, `memory_forget_artifact`, `memory_promote`, `memory_audit`,
@@ -482,6 +618,7 @@ system-of-record verification.
 
 - [Current implementation status](docs/current-status.md)
 - [Generic runtime adapter](docs/generic-adapter.md)
+- [Delegated context-provider contract](docs/contracts/delegated-context-provider-v1.md)
 - [Agent Black Box](docs/agent-blackbox.md)
 - [Integration guide](docs/integration-guide.md)
 - [OpenClaw setup](docs/openclaw-setup.md)
@@ -490,9 +627,14 @@ system-of-record verification.
 - [Audit log specification](docs/audit-log-spec.md)
 - [Audit investigation](docs/audit-search.md)
 - [Storage, backup, and recovery](docs/data-storage-and-backup.md)
+- [Spec-driven development](docs/spec-kit.md)
 
 ## Development verification
 
+Material features use the repository's GitHub Spec Kit Lean workflow. See
+[Spec-driven development](docs/spec-kit.md) for feature directories, Codex
+skills, and the constitution-backed delivery sequence.
+
 AtMem and its separately packaged AtBot companion share this repository. They
 remain separate processes and communicate only through the loopback companion
 protocol; neither package imports the other's runtime code.
@@ -531,9 +673,9 @@ npm test
 npm run smoke
 ```
 
-Current repository metadata is version **2.2.4**. Python and npm release
-versions are intentionally kept equal because the OpenClaw installer pins the
-matching bridge.
+Current repository metadata is version **2.2.6**, with the matched OpenClaw
+bridge **2.2.6**. Release validation requires exact Python/bridge alignment;
+AtBot retains its independent compatible version **0.1.0a6**.
 
 ## License
 

atmem-2.2.4/atmem.egg-info/PKG-INFO → atmem-2.2.6/README.md

@@ -1,50 +1,6 @@
-Metadata-Version: 2.4
-Name: atmem
-Version: 2.2.4
-Summary: Host-neutral Agent Black Box and reversible memory control plane.
-Author-email: aetna000 <aetna000@gmail.com>
-Maintainer-email: aetna000 <aetna000@gmail.com>
-License-Expression: Apache-2.0
-Project-URL: Homepage, https://github.com/aetna000/atmem
-Project-URL: Repository, https://github.com/aetna000/atmem
-Project-URL: Issues, https://github.com/aetna000/atmem/issues
-Project-URL: Documentation, https://github.com/aetna000/atmem#readme
-Keywords: agent-black-box,agent-memory,audit,mcp,provenance,sqlite
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Environment :: Console
-Classifier: Intended Audience :: Developers
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Database
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: atmem-atbot==0.1.0a3
-Provides-Extra: dev
-Requires-Dist: pytest>=8.0.0; extra == "dev"
-Requires-Dist: tomli>=2.0; python_version < "3.11" and extra == "dev"
-Provides-Extra: semantic
-Requires-Dist: sentence-transformers<6.0.0,>=5.0.0; extra == "semantic"
-Provides-Extra: atbot
-Provides-Extra: pydantic-ai
-Requires-Dist: pydantic-ai-slim<3,>=2.0; extra == "pydantic-ai"
-Provides-Extra: langgraph
-Requires-Dist: langgraph<2,>=1.1.5; extra == "langgraph"
-Requires-Dist: langchain<2,>=1.0; extra == "langgraph"
-Provides-Extra: frameworks
-Requires-Dist: pydantic-ai-slim<3,>=2.0; extra == "frameworks"
-Requires-Dist: langgraph<2,>=1.1.5; extra == "frameworks"
-Requires-Dist: langchain<2,>=1.0; extra == "frameworks"
-Dynamic: license-file
-
 # AtMem
 
-[![Version 2.2.4](https://img.shields.io/badge/version-2.2.4-blue)](./docs/releases/v2.2.4.md)
+[![Version 2.2.6](https://img.shields.io/badge/version-2.2.6-blue)](./docs/releases/v2.2.6.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.**
@@ -59,7 +15,7 @@ authorizes, stores, scopes, injects, corrects, and deletes memory.
 ### 1. Install AtMem and choose memory intelligence
 
 ```bash
-python -m pip install --upgrade atmem==2.2.4
+python -m pip install --upgrade atmem==2.2.6
 atmem atbot setup
 atmem atbot doctor
 atmem dashboard
@@ -82,12 +38,16 @@ 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.
+connection. It also offers to download the default local embedding model and
+build, verify, and activate its vector epoch. For unattended setup, make that
+approval explicit with `atmem openclaw install --allow-model-download`; choose
+another Ollama model with `--embedding-model MODEL`. Do not install the npm
+package yourself.
 
 Already using AtMem 2.1 with OpenClaw? Upgrade in place:
 
 ```bash
-python -m pip install --upgrade atmem==2.2.4
+python -m pip install --upgrade atmem==2.2.6
 atmem openclaw upgrade
 atmem control verify
 ```
@@ -110,7 +70,7 @@ selected by `python`, rather than an unrelated `pip` executable on `PATH`.
 #### Pydantic AI — native capability
 
 ```bash
-python -m pip install 'atmem[pydantic-ai]==2.2.4'
+python -m pip install 'atmem[pydantic-ai]==2.2.6'
 atmem control shadow --host generic --memory-db ~/.atmem/memories.db
 ```
 
@@ -126,6 +86,7 @@ identity = AtMemAdapterIdentity(
     agent_id=scope["agent_id"],
     workspace_id=scope["workspace_id"],
     subject_id=scope["subject_id"],
+    user_id="authenticated-application-user",  # required only for delegation
 )
 memory = PydanticAIAtMemAdapter(manager, identity).capability()
 agent = Agent("openai:gpt-5-mini", capabilities=[memory])
@@ -134,7 +95,7 @@ agent = Agent("openai:gpt-5-mini", capabilities=[memory])
 #### LangChain/LangGraph — native middleware
 
 ```bash
-python -m pip install 'atmem[langgraph]==2.2.4'
+python -m pip install 'atmem[langgraph]==2.2.6'
 atmem control shadow --host generic --memory-db ~/.atmem/memories.db
 ```
 
@@ -150,17 +111,69 @@ identity = AtMemAdapterIdentity(
     agent_id=scope["agent_id"],
     workspace_id=scope["workspace_id"],
     subject_id=scope["subject_id"],
+    user_id="authenticated-application-user",  # required only for delegation
 )
 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
+context injection, exposure proof, and turn/tool evidence. When an enabled
+delegated-provider registration matches the complete scope, they instead carry
+the exact HMAC-authenticated provider workflow through the Pydantic AI or
+LangChain/LangGraph model boundary, without also using native AtMem context.
+This delegated host path is packaged in 2.2.6. The adapters 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.
 
+### Spec 007 milestone: govern work in progress
+
+AtMem 2.2.6 includes Governed Task State: a separate, revisioned authority
+plane for what an agent is doing now, what remains, what is blocked, and
+whether completion is allowed. It is **disabled by default** and never turns
+temporary task progress into long-term personal memory.
+
+Start one exact scope and inspect it from either the CLI or the dashboard:
+
+```bash
+atmem task enable ~/.atmem/memories.db \
+  --subject user-1 --agent agent-1 --workspace workspace-1
+atmem task start ~/.atmem/memories.db --task-id release-007 \
+  --goal "Ship the governed task-state milestone" --actor you@example.com \
+  --required-item verify="Run release verification" \
+  --subject user-1 --agent agent-1 --workspace workspace-1
+atmem task show ~/.atmem/memories.db release-007 \
+  --subject user-1 --agent agent-1 --workspace workspace-1
+atmem dashboard
+```
+
+The dashboard's **Governed tasks** card shows progress, blockers, recent task
+decisions, context delivery, the current revision, and guarded lifecycle
+actions. Model delivery requires an exact task identity. Pydantic AI may supply
+`atmem_task_id` in run dependencies; LangGraph may supply it through
+`configurable`; construction-time `identity.for_task("release-007")` remains a
+backward-compatible fallback. OpenClaw resolves the owner-authorized current
+conversation binding. AtMem never guesses from prompt text or chooses among
+open tasks. AtBot may propose a change, but AtMem revalidates and commits it.
+
+See the [Governed Task State guide](docs/governed-task-state.md) for lifecycle,
+correction, provenance, expiry, benchmark, and automation examples, and read
+the [2.2.6 release notes](docs/releases/v2.2.6.md) before upgrading.
+
+### Prove memory quality locally
+
+```bash
+atmem benchmark run --output benchmark.json
+```
+
+This offline release gate runs 16 isolated extraction, contradiction, recall,
+withholding, injection, privacy, poisoning and fallback cases. Safety must be
+perfect; other quality metrics cannot fall below checked-in baselines. Optional
+local/hosted profiles, LongMemEval import and fair Mem0 OSS comparison are also
+available without adding Mem0 or model SDKs to the base install. See the
+[memory benchmark guide](docs/benchmarks.md) for commands and honest limits.
+
 ### 3. Review, then activate
 
 Every integration starts in **shadow mode**: AtMem learns and shows what it
@@ -178,10 +191,57 @@ 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 2.2.4**. AtBot is a
+> **Release status:** this repository describes the **AtMem 2.2.6 release candidate**, not verified publication. AtBot is a
 > separately packaged, headless component installed and managed by AtMem; it is
 > not an independent agent or a second memory authority.
 
+### Optional: delegate context authority
+
+Beta 10 requires per-instance HMAC request credentials for delegated context and
+health. See the
+[shared profile and beta migration](docs/contracts/delegated-request-auth-v1.md)
+before enabling an older delegated registration.
+
+AtMem uses its own governed retrieval by default. The 2.2.6 beta adds an
+explicit, provider-neutral delegated mode for deployments where another
+compatible provider must make the context decision while AtMem owns
+host integration and flight evidence.
+
+```bash
+atmem delegated register --help
+atmem delegated status
+atmem delegated enable context-provider:local
+atmem delegated doctor
+```
+
+Registration is disabled by default and is bound to exact user, agent, and
+workspace scopes. On matching turns, AtMem verifies the signed result, injects
+the provider's exact bytes once, and separately proves delivery. It does not
+run native retrieval after an accepted delegated decision. Provider failure
+withholds context unless the operator explicitly registered native fallback.
+See the [delegated context-provider guide](docs/delegated-context-provider.md).
+
+AtMem also ships provider-side adapters, each as an independent optional extra:
+
+```bash
+# Mem0 chooses context; AtMem verifies and records delivery
+python -m pip install 'atmem[mem0]'
+atmem provider init mem0-local --kind mem0 --mode oss --port 8788
+
+# Or use an application-owned LangGraph / Pydantic AI factory
+python -m pip install 'atmem[langgraph-provider]'
+atmem provider init graph-context --kind langgraph \
+  --factory myapp.memory_graph:build_graph --port 8789
+
+python -m pip install 'atmem[pydantic-provider]'
+atmem provider init ai-context --kind pydantic-ai \
+  --factory myapp.memory_agent:build_agent --port 8790
+```
+
+`atmem provider init` creates private signing material and prints the exact
+registration command; it does not enable delegated authority. See the
+[context-provider adapter quick starts](docs/context-provider-adapters.md).
+
 It gives agent runtimes one governed memory source and one tamper-evident record
 of what the host observed: memory considered and injected, model boundaries,
 tool requests and completions, turn termination, and linked external outcome
@@ -197,15 +257,17 @@ and restores it exactly.
 ## Installation details
 
 ```bash
-python -m pip install atmem==2.2.4
+python -m pip install atmem==2.2.6
 atmem --version
 ```
 
 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:
+vector sidecar. `atmem openclaw install` can automatically prepare an Ollama
+embedding model, while the semantic extra adds local sentence-transformer
+choices:
 
 ```bash
-python -m pip install 'atmem[semantic]==2.2.4'
+python -m pip install 'atmem[semantic]==2.2.6'
 ```
 
 For repository development, install both workspace packages:
@@ -215,10 +277,10 @@ python -m pip install -e './packages/atbot[dev]' -e '.[dev]'
 atmem atbot setup
 ```
 
-The authority modules remain model-agnostic and do not import AtBot, but the
-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.
+The authority modules remain model-agnostic and do not import AtBot. The AtMem
+distribution requires the separately packaged, exactly pinned AtBot companion,
+whose built-in Ollama and OpenAI-compatible client uses only the Python standard
+library. Framework SDKs enter the environment only through explicit extras.
 
 ## Integration boundaries
 
@@ -385,7 +447,7 @@ atmem control restore
 Existing 2.1 installations upgrade without starting a new migration:
 
 ```bash
-python -m pip install --upgrade atmem==2.2.4
+python -m pip install --upgrade atmem==2.2.6
 atmem openclaw upgrade
 atmem control verify
 ```
@@ -445,6 +507,7 @@ atmem mcp --db ~/.atmem/memories.db --subject user-1
 ```
 
 MCP tools: `memory_remember`, `memory_observe`, `memory_recall`,
+`memory_recall_decision`,
 `memory_get_record`, `memory_get_source`, `memory_recall_block`,
 `memory_persona`, `memory_context_pack`, `memory_capture`, `memory_list`,
 `memory_forget`, `memory_forget_artifact`, `memory_promote`, `memory_audit`,
@@ -482,6 +545,7 @@ system-of-record verification.
 
 - [Current implementation status](docs/current-status.md)
 - [Generic runtime adapter](docs/generic-adapter.md)
+- [Delegated context-provider contract](docs/contracts/delegated-context-provider-v1.md)
 - [Agent Black Box](docs/agent-blackbox.md)
 - [Integration guide](docs/integration-guide.md)
 - [OpenClaw setup](docs/openclaw-setup.md)
@@ -490,9 +554,14 @@ system-of-record verification.
 - [Audit log specification](docs/audit-log-spec.md)
 - [Audit investigation](docs/audit-search.md)
 - [Storage, backup, and recovery](docs/data-storage-and-backup.md)
+- [Spec-driven development](docs/spec-kit.md)
 
 ## Development verification
 
+Material features use the repository's GitHub Spec Kit Lean workflow. See
+[Spec-driven development](docs/spec-kit.md) for feature directories, Codex
+skills, and the constitution-backed delivery sequence.
+
 AtMem and its separately packaged AtBot companion share this repository. They
 remain separate processes and communicate only through the loopback companion
 protocol; neither package imports the other's runtime code.
@@ -531,9 +600,9 @@ npm test
 npm run smoke
 ```
 
-Current repository metadata is version **2.2.4**. Python and npm release
-versions are intentionally kept equal because the OpenClaw installer pins the
-matching bridge.
+Current repository metadata is version **2.2.6**, with the matched OpenClaw
+bridge **2.2.6**. Release validation requires exact Python/bridge alignment;
+AtBot retains its independent compatible version **0.1.0a6**.
 
 ## License
 

atmem-2.2.6/atmem/adapters/__init__.py

@@ -0,0 +1,6 @@
+"""Optional framework adapters for automatic governed memory lifecycle hooks."""
+
+from atmem.adapters.base import AtMemAdapterIdentity, AtMemTurnLifecycle
+from atmem.adapters.callbacks import CallbackAtMemAdapter, callback_adapter
+
+__all__ = ["AtMemAdapterIdentity", "AtMemTurnLifecycle", "CallbackAtMemAdapter", "callback_adapter"]