Metadata-Version: 2.3
Name: brown-octopus
Version: 0.5.2
Summary: Capability-context management for tool-using AI agents
Keywords: AI agents,MCP,tool retrieval,capability context
Author: nana brown
Author-email: nana brown <nanabrownsnr@gmail.com>
License:                                  Apache License
                                    Version 2.0, January 2004
                                 http://www.apache.org/licenses/
         
            TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
         
            1. Definitions.
         
               "License" shall mean the terms and conditions for use, reproduction,
               and distribution as defined by Sections 1 through 9 of this document.
         
               "Licensor" shall mean the copyright owner or entity authorized by
               the copyright owner that is granting the License.
         
               "Legal Entity" shall mean the union of the acting entity and all
               other entities that control, are controlled by, or are under common
               control with that entity. For the purposes of this definition,
               "control" means (i) the power, direct or indirect, to cause the
               direction or management of such entity, whether by contract or
               otherwise, or (ii) ownership of fifty percent (50%) or more of the
               outstanding shares, or (iii) beneficial ownership of such entity.
         
               "You" (or "Your") shall mean an individual or Legal Entity
               exercising permissions granted by this License.
         
               "Source" form shall mean the preferred form for making modifications,
               including but not limited to software source code, documentation
               source, and configuration files.
         
               "Object" form shall mean any form resulting from mechanical
               transformation or translation of a Source form, including but
               not limited to compiled object code, generated documentation,
               and conversions to other media types.
         
               "Work" shall mean the work of authorship, whether in Source or
               Object form, made available under the License, as indicated by a
               copyright notice that is included in or attached to the work
               (an example is provided in the Appendix below).
         
               "Derivative Works" shall mean any work, whether in Source or Object
               form, that is based on (or derived from) the Work and for which the
               editorial revisions, annotations, elaborations, or other modifications
               represent, as a whole, an original work of authorship. For the purposes
               of this License, Derivative Works shall not include works that remain
               separable from, or merely link (or bind by name) to the interfaces of,
               the Work and Derivative Works thereof.
         
               "Contribution" shall mean any work of authorship, including
               the original version of the Work and any modifications or additions
               to that Work or Derivative Works thereof, that is intentionally
               submitted to Licensor for inclusion in the Work by the copyright owner
               or by an individual or Legal Entity authorized to submit on behalf of
               the copyright owner. For the purposes of this definition, "submitted"
               means any form of electronic, verbal, or written communication sent
               to the Licensor or its representatives, including but not limited to
               communication on electronic mailing lists, source code control systems,
               and issue tracking systems that are managed by, or on behalf of, the
               Licensor for the purpose of discussing and improving the Work, but
               excluding communication that is conspicuously marked or otherwise
               designated in writing by the copyright owner as "Not a Contribution."
         
               "Contributor" shall mean Licensor and any individual or Legal Entity
               on behalf of whom a Contribution has been received by Licensor and
               subsequently incorporated within the Work.
         
            2. Grant of Copyright License. Subject to the terms and conditions of
               this License, each Contributor hereby grants to You a perpetual,
               worldwide, non-exclusive, no-charge, royalty-free, irrevocable
               copyright license to reproduce, prepare Derivative Works of,
               publicly display, publicly perform, sublicense, and distribute the
               Work and such Derivative Works in Source or Object form.
         
            3. Grant of Patent License. Subject to the terms and conditions of
               this License, each Contributor hereby grants to You a perpetual,
               worldwide, non-exclusive, no-charge, royalty-free, irrevocable
               (except as stated in this section) patent license to make, have made,
               use, offer to sell, sell, import, and otherwise transfer the Work,
               where such license applies only to those patent claims licensable
               by such Contributor that are necessarily infringed by their
               Contribution(s) alone or by combination of their Contribution(s)
               with the Work to which such Contribution(s) was submitted. If You
               institute patent litigation against any entity (including a
               cross-claim or counterclaim in a lawsuit) alleging that the Work
               or a Contribution incorporated within the Work constitutes direct
               or contributory patent infringement, then any patent licenses
               granted to You under this License for that Work shall terminate
               as of the date such litigation is filed.
         
            4. Redistribution. You may reproduce and distribute copies of the
               Work or Derivative Works thereof in any medium, with or without
               modifications, and in Source or Object form, provided that You
               meet the following conditions:
         
               (a) You must give any other recipients of the Work or
                   Derivative Works a copy of this License; and
         
               (b) You must cause any modified files to carry prominent notices
                   stating that You changed the files; and
         
               (c) You must retain, in the Source form of any Derivative Works
                   that You distribute, all copyright, patent, trademark, and
                   attribution notices from the Source form of the Work,
                   excluding those notices that do not pertain to any part of
                   the Derivative Works; and
         
               (d) If the Work includes a "NOTICE" text file as part of its
                   distribution, then any Derivative Works that You distribute must
                   include a readable copy of the attribution notices contained
                   within such NOTICE file, excluding those notices that do not
                   pertain to any part of the Derivative Works, in at least one
                   of the following places: within a NOTICE text file distributed
                   as part of the Derivative Works; within the Source form or
                   documentation, if provided along with the Derivative Works; or,
                   within a display generated by the Derivative Works, if and
                   wherever such third-party notices normally appear. The contents
                   of the NOTICE file are for informational purposes only and
                   do not modify the License. You may add Your own attribution
                   notices within Derivative Works that You distribute, alongside
                   or as an addendum to the NOTICE text from the Work, provided
                   that such additional attribution notices cannot be construed
                   as modifying the License.
         
               You may add Your own copyright statement to Your modifications and
               may provide additional or different license terms and conditions
               for use, reproduction, or distribution of Your modifications, or
               for any such Derivative Works as a whole, provided Your use,
               reproduction, and distribution of the Work otherwise complies with
               the conditions stated in this License.
         
            5. Submission of Contributions. Unless You explicitly state otherwise,
               any Contribution intentionally submitted for inclusion in the Work
               by You to the Licensor shall be under the terms and conditions of
               this License, without any additional terms or conditions.
               Notwithstanding the above, nothing herein shall supersede or modify
               the terms of any separate license agreement you may have executed
               with Licensor regarding such Contributions.
         
            6. Trademarks. This License does not grant permission to use the trade
               names, trademarks, service marks, or product names of the Licensor,
               except as required for reasonable and customary use in describing the
               origin of the Work and reproducing the content of the NOTICE file.
         
            7. Disclaimer of Warranty. Unless required by applicable law or
               agreed to in writing, Licensor provides the Work (and each
               Contributor provides its Contributions) on an "AS IS" BASIS,
               WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
               implied, including, without limitation, any warranties or conditions
               of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
               PARTICULAR PURPOSE. You are solely responsible for determining the
               appropriateness of using or redistributing the Work and assume any
               risks associated with Your exercise of permissions under this License.
         
            8. Limitation of Liability. In no event and under no legal theory,
               whether in tort (including negligence), contract, or otherwise,
               unless required by applicable law (such as deliberate and grossly
               negligent acts) or agreed to in writing, shall any Contributor be
               liable to You for damages, including any direct, indirect, special,
               incidental, or consequential damages of any character arising as a
               result of this License or out of the use or inability to use the
               Work (including but not limited to damages for loss of goodwill,
               work stoppage, computer failure or malfunction, or any and all
               other commercial damages or losses), even if such Contributor
               has been advised of the possibility of such damages.
         
            9. Accepting Warranty or Additional Liability. While redistributing
               the Work or Derivative Works thereof, You may choose to offer,
               and charge a fee for, acceptance of support, warranty, indemnity,
               or other liability obligations and/or rights consistent with this
               License. However, in accepting such obligations, You may act only
               on Your own behalf and on Your sole responsibility, not on behalf
               of any other Contributor, and only if You agree to indemnify,
               defend, and hold each Contributor harmless for any liability
               incurred by, or claims asserted against, such Contributor by reason
               of your accepting any such warranty or additional liability.
         
            END OF TERMS AND CONDITIONS
         
            APPENDIX: How to apply the Apache License to your work.
         
               To apply the Apache License to your work, attach the following
               boilerplate notice, with the fields enclosed by brackets "[]"
               replaced with your own identifying information. (Don't include
               the brackets!)  The text should be enclosed in the appropriate
               comment syntax for the file format. We also recommend that a
               file or class name and description of purpose be included on the
               same "printed page" as the copyright notice for easier
               identification within third-party archives.
         
            Copyright [yyyy] [name of copyright owner]
         
            Licensed under the Apache License, Version 2.0 (the "License");
            you may not use this file except in compliance with the License.
            You may obtain a copy of the License at
         
                http://www.apache.org/licenses/LICENSE-2.0
         
            Unless required by applicable law or agreed to in writing, software
            distributed under the License is distributed on an "AS IS" BASIS,
            WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
            See the License for the specific language governing permissions and
            limitations under the License.
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: fastmcp>=4.0.3
Requires-Dist: numpy>=2.2,<2.3
Requires-Dist: packaging>=24.0
Requires-Dist: sentence-transformers>=6.0.1
Requires-Dist: spacy>=3.8.16
Requires-Dist: jev-reranker>=0.1.0 ; extra == 'jev'
Requires-Dist: pymongo>=4.10.0 ; extra == 'mongo'
Requires-Dist: psycopg[binary]>=3.2.0 ; extra == 'postgres'
Requires-Dist: fastapi>=0.115.0 ; extra == 'service'
Requires-Dist: uvicorn[standard]>=0.34.0 ; extra == 'service'
Requires-Dist: pyarrow>=18.0.0 ; extra == 'toolret'
Requires-Python: >=3.12
Project-URL: Repository, https://github.com/nanabrownsnr/brownoctopus
Project-URL: Documentation, https://github.com/nanabrownsnr/brownoctopus/blob/main/docs/production.md
Project-URL: Issues, https://github.com/nanabrownsnr/brownoctopus/issues
Provides-Extra: jev
Provides-Extra: mongo
Provides-Extra: postgres
Provides-Extra: service
Provides-Extra: toolret
Description-Content-Type: text/markdown

# Brown Octopus

Brown Octopus manages the capability context exposed to an AI agent.

Given a user request, it identifies relevant capabilities, retrieves a bounded
set of candidates, and maintains the active capability context for a
conversation. It returns capability definitions to the host application. It
does not call tools, own an LLM, manage credentials, or store conversation
history.

```text
Distribution: brown-octopus
Import:       brown_octopus
Runtime:      Octopus
Index facade: OctopusIndex
```

## Install

Brown Octopus supports Python 3.12 and newer.

```bash
pip install brown-octopus
```

Or with uv:

```bash
uv add brown-octopus
```

Prepare the default runtime models explicitly:

```bash
brown-octopus setup-models
```

This prepares `en_core_web_trf` and `Qwen/Qwen3-Embedding-0.6B`.
`Octopus.initialize()` never downloads models or discovers capabilities
implicitly.

Check the installation:

```bash
brown-octopus doctor
brown-octopus inspect
```

## Quick start

The normal lifecycle is:

```text
CapabilitySource -> OctopusIndex.create() -> persisted index
                                              |
                                              v
                    Octopus.initialize() -> retrieve_result()
```

### 1. Configure a local MCP catalog

Create `data/mcps.json`:

```json
{
  "items": [
    {
      "id": "outlook",
      "name": "Outlook Mail",
      "url": "https://example.com/outlook/mcp"
    }
  ]
}
```

The URL must be a reachable MCP server that the host is authorized to access.

### 2. Build the index

Create `setup_index.py`:

```python
import asyncio
from pathlib import Path

from brown_octopus import OctopusIndex
from brown_octopus.sources import LocalMcpCatalogSource


async def main() -> None:
    index = OctopusIndex.from_sources(
        [LocalMcpCatalogSource(Path("data/mcps.json"))],
        index_path="data/indexes/default",
    )
    report = await index.create()
    print(f"Indexed {report.tool_count} capabilities")


if __name__ == "__main__":
    asyncio.run(main())
```

Run it once after the catalog is configured:

```bash
python setup_index.py
```

`create()` discovers capabilities, builds embeddings, validates a complete
snapshot, and publishes it atomically. It does not execute MCP tools.

### 3. Start the runtime

Create `app.py`:

```python
import asyncio

from brown_octopus import Octopus


async def main() -> None:
    octopus = Octopus(index_path="data/indexes/default")
    await octopus.initialize()

    result = octopus.retrieve_result(
        "Reply to Tom's email",
        session_id="conversation-123",
    )

    print(f"Turn: {result.turn}")
    for capability in result.tools:
        print(capability["name"])


if __name__ == "__main__":
    asyncio.run(main())
```

Run it with `python app.py`. Pass `result.tools` to the agent or harness; the
host decides how to bind and execute the definitions.

## Index and runtime

`OctopusIndex` owns index lifecycle:

- `create()` builds the initial index;
- `update()` synchronizes configured sources;
- `add(source)` adds a source and synchronizes;
- `remove_source(source_id)` removes a configured source and synchronizes;
- `reset()` removes the persisted index;
- `runtime()` returns the runtime facade.

`Octopus` owns runtime retrieval:

- `initialize()` loads models and the current snapshot;
- `retrieve()` returns the active capability context;
- `retrieve_result()` returns the typed result contract;
- session methods maintain conversation-specific capability state.

Sources are optional when opening an index:

```python
index = OctopusIndex(index_path="data/indexes/new-index")
octopus = index.runtime()
await octopus.initialize()

result = octopus.retrieve_result("Reply to Tom's email")
assert result.tools == []
assert result.retrieved_tools == []
assert result.tool_ids == []
```

If the path has no snapshot, runtime initialization starts with an empty
capability universe. Configure a source and call `create()` or `update()` when
the host is ready to provision capabilities.

## Updating capabilities

After changing a configured source:

```python
report = await index.update()
print(report.added)
print(report.changed)
print(report.removed)
print(report.failed_sources)
```

`update()` is a synchronization operation, not an append-only operation. It
rediscovers the configured universe and publishes a complete replacement
snapshot:

```text
new capability                      -> added
changed metadata                    -> changed
unchanged capability                -> retained
authoritatively removed capability  -> removed
temporarily failed source           -> previous capabilities preserved
```

The host decides when updates happen. Brown Octopus has no refresh scheduler.

Add a source to an existing index:

```python
from brown_octopus import McpServerSource

await index.add(
    McpServerSource(
        "https://example.com/word/mcp",
        source_id="word",
    )
)
```

`remove_capability()` remains temporarily for older applications but is
deprecated. Prefer changing the authoritative source or removing the source.

## Retrieval results and filtering

```python
result = octopus.retrieve_result(
    "Send Sarah an email",
    session_id="conversation-123",
)
```

The result provides:

```text
result.retrieved_tools  current-turn selection
result.tools            final active context
result.tool_ids         stable IDs for result.tools
result.session_id       conversation identifier
result.turn             current session turn
result.metadata         timing and pipeline metadata
```

The simpler method is also available:

```python
active_tools = octopus.retrieve(
    "Search the web for the latest NVIDIA news",
    session_id="conversation-123",
)
```

Restrict a turn before ranking with `allowed_mcp_urls`:

```python
result = octopus.retrieve_result(
    "Reply to an email",
    session_id="conversation-123",
    allowed_mcp_urls=["https://example.com/outlook/mcp"],
)
```

## Sessions

One engine can serve many conversations:

```python
first = octopus.retrieve_result("Search the web", session_id="conversation-a")
second = octopus.retrieve_result("Reply to Tom", session_id="conversation-b")
```

Each session has its own turn counter and active capability state. A session
ID represents a conversation or workflow identity, not a user identity.

```python
snapshot = octopus.get_session("conversation-a")
octopus.reset_session("conversation-a")
octopus.delete_session("conversation-b")
```

The default store is process-local. A persistent application can inject a
custom atomic `SessionStore`; see `docs/production.md`.

## Capability sources

Built-in adapters include:

| Adapter | Use it for |
| --- | --- |
| `LocalMcpCatalogSource` | local JSON catalog of MCP servers |
| `McpServerSource` | one HTTP MCP server |
| `McpRegistrySource` | API returning MCP server records |
| `JsonCapabilitySource` | normalized capabilities from JSON |
| `ApiCapabilitySource` | normalized capabilities from an HTTP API |
| custom `CapabilitySource` | application-specific discovery |

Convenience constructor:

```python
index = OctopusIndex.from_mcp_server(
    "https://example.com/outlook/mcp",
    source_id="outlook",
    index_path="data/indexes/outlook",
)
```

Detailed source contracts, pagination, authentication, and field mapping are
documented in `docs/production.md`.

## Embedding providers

The default provider is local Qwen. A compatible local model can be supplied:

```python
from brown_octopus import LocalEmbeddingProvider, OctopusIndex

provider = LocalEmbeddingProvider(
    model_name="sentence-transformers/all-MiniLM-L6-v2",
)
index = OctopusIndex.from_sources(
    [source],
    index_path="data/indexes/minilm",
    embedding_provider=provider,
)
await index.create()
```

An HTTP provider can target a remote or self-hosted service:

```python
from brown_octopus import HttpEmbeddingProvider, OctopusIndex

provider = HttpEmbeddingProvider(
    url="http://localhost:11434/api/embed",
    model="qwen3-embedding:0.6b",
)
index = OctopusIndex.from_sources(
    [source],
    index_path="data/indexes/http-embeddings",
    embedding_provider=provider,
)
await index.create()
```

Use the same provider when loading that index. Provider dimensions are checked
against index metadata.

## CLI

```bash
brown-octopus --help
brown-octopus --version
brown-octopus version
brown-octopus setup-models
brown-octopus doctor
brown-octopus inspect
brown-octopus inspect --json
```

Help and version do not load models. `doctor` checks package, models, and the
configured index. `inspect` reports configuration and index metadata.

## Runtime context limits

The default active-context policy is:

```text
TTL:       8 turns
Active cap: 30 capabilities
```

These defaults preserve the validated behavior, but applications can tune
them when their context budget requires it:

```python
from brown_octopus import OctopusIndex

index = OctopusIndex(index_path="data/indexes/default")
await index.create()
octopus = index.runtime(
    capability_ttl=3,
    active_cap=20,
)
await octopus.initialize()
```

`capability_ttl` controls how many later turns a retrieved capability can
remain active without being retrieved again. `active_cap` limits the total
number of active capabilities in a session. These settings affect session
context management, not candidate ranking or the V3 selection algorithm.

The same values can be configured through environment variables:

```text
OCTOPUS_CAPABILITY_TTL=3
OCTOPUS_ACTIVE_CAP=20
```

## Architecture boundary

Brown Octopus owns capability discovery adapters, indexing, intent analysis,
retrieval, selection, active capability context, and capability session state.

The host owns the LLM, conversation history, tool binding and execution,
credentials, authentication, authorization, user identity, update timing, and
session lifecycle policy.

Returned MCP metadata such as `mcp_url` and `tool_name` describes execution
context. Brown Octopus does not execute the capability.

## Retrieval behavior

The default V3 pipeline is unchanged:

```text
user request -> deterministic spaCy intent analysis
             -> capability-oriented representation
             -> dense embedding retrieval
             -> Min-4 + Bounded Max Gap
             -> active capability context
             -> TTL 8 and active cap 30
```

The strategy is recall-oriented within bounded limits. It may expose extra
plausible capabilities rather than aggressively pruning a capability that may
be required. It does not guarantee perfect recall.

## Development and research

```bash
uv sync
uv run brown-octopus setup-models
uv run pytest -q -m "not external" tests
uv build
```

Product code, tests, examples, and research/evaluation history are kept
separate. Evaluation material under `evals/` and `docs/research/` is retained
for reproducibility and is not required at runtime.

See [`docs/production.md`](docs/production.md) for the complete integration
reference.

## License

See [`LICENSE`](LICENSE).
