Skip to main content

Model-agnostic Python substrate for the swarph-mesh ecosystem. v0.4.0 adds ClaudeAdapter (Phase 4 #3, subscription-billed via claude -p) on top of v0.3.0's GeminiAdapter + DeepSeekAdapter + MeshClient.

Project description

swarph-mesh

Model-agnostic Python substrate for the swarph-mesh ecosystem. Pure library, no CLI.

Designed to fill the gap left by existing tools (aichat, mods, Simon Willison's llm, gemini-cli, claude-cli): none expose mesh-gateway participation, per-caller attribution, structured-output discipline, or the cooperative-protocol patterns the swarph encodes.

This is one of three repos in the v0.3.x architecture:

Repo Role
swarph-mesh This package — typed Protocol + adapters + SwarphCall + MeshClient
swarph-cli The swarph binary. Thin client over swarph-mesh
swarph-meshlm Simon Willison llm plugin. Same primitives wired into llm's plugin host

All three sit on top of swarph-shared which provides the cross-billing-path attribution + subprocess env scrubbing + JSON-mode harness + peer-name registry primitives.

Status

v0.4.0 — Phase 1 substrate + Phase 3 MeshClient + Phase 4 #2 DeepSeek + Phase 4 #3 Claude (subscription). Four PLAN.md §13 falsifiability gates PASSED end-to-end against live infrastructure (real Gemini API + real DeepSeek API + real lab-OVH mesh-gateway + real claude -p subscription path).

Public surface:

  • LLMAdapter Protocol (runtime-checkable) + ChatMessage + LLMResponse
  • SwarphCall — caller-convention-validated entry point with hooks + attribution
  • GeminiAdapter — wraps langgraph-genai-bridge (Flex tier, context caching)
  • DeepSeekAdapter (v0.3.0) — OpenAI-protocol-compatible client for V4-Flash / V4-Pro / V3 aliases; preserves reasoning content as [reasoning] preamble for portability
  • ClaudeAdapter (NEW v0.4.0) — subprocess-based wrapper around claude -p for subscription billing path (no ANTHROPIC_API_KEY needed; reads ~/.claude/.credentials.json). Reuses swarph_shared.scrub_env_for_subprocess to keep billing-relevant env keys out of the subprocess. cost_usd=0.0 for subscription calls (honest flat-rate); metered-equivalent cost preserved in raw_response["api_metered_cost_usd"] for auditors.
  • JSON-mode harness — retry-once with [USER]-turn feedback (per swarph-shared invariant)
  • Attribution: FileAttributionWriter default; set_default_writer() for production TSDB consumers
  • MeshClient (v0.2.0) — async wrapper around mesh-gateway HTTP API; replaces hand-rolled curl in lab_loop_drain.py / mesh_inbox_watcher.py / science_claude_inbox_drain.py

Tests: 131+ passing (127 offline + 1 live claude subscription + 1 live deepseek + 2 live mesh + 1 live gemini smoke; live tests gated on respective env/creds).

from swarph_mesh import SwarphCall, ChatMessage

# Phase 1 — LLM call with attribution
result = await SwarphCall(
    provider="gemini",
    caller="orchestrator.boss",
).chat(
    messages=[ChatMessage(role="user", content="hi")],
)
print(result.text, result.cost_usd, result.input_tokens)
from swarph_mesh import MeshClient
import os

# Phase 3 — mesh-gateway DM coordination
async with MeshClient(node="lab-ovh") as client:  # token from MESH_GATEWAY_TOKEN env
    peers = await client.list_peers()
    msgs = await client.fetch(unread_only=True)
    sent = await client.send(to="droplet", kind="fyi", content="hello")
    await client.mark_read(msgs[0].id)

MeshClient.send() enforces two structural invariants:

  1. Recipient name validation via swarph_shared.validate_node_name — closes the framing-contagion class (Vector A peer-onboarding chatter, Vector B human-prompt shorthand).
  2. Mesh-secrets out-of-band guard — best-effort regex sniff for credential-shaped content (PyPI tokens, Anthropic keys, GitHub tokens, JWTs, AWS keys). Hits raise MeshSecretLeakError BEFORE the POST. Operator escape hatch via skip_secret_check=True for legitimate prose mentioning credential shapes. CLAUDE.md "Mesh secrets out-of-band only" is non-negotiable; the guard catches obvious cases.

Spec

The canonical PLAN with sequencing, falsifiability gates, and design rationale lives at:

hedge-fund-mcp / research/swarph_cli/PLAN.md

Phase rollout

Phase Scope
0 (v0.0.1) Typed substrate — Protocol + dataclasses + exceptions
1 (v0.1.0) Gemini adapter + SwarphCall surface + caller convention import + JSON-mode harness + attribution hook
3 (v0.2.0) MeshClient async wrapper + recipient validation + mesh-secrets guard
4 #2 (v0.3.0) DeepSeek adapter — OpenAI-protocol-compatible, V4-Flash default, V4-Pro premium, V3 aliases preserved, reasoning_content kept as [reasoning] preamble
4 #3 (v0.4.0 — this release) Claude subscription adapter — wraps claude -p via subprocess, reads ~/.claude/.credentials.json, billing-leak prevention via scrub_env_for_subprocess
4 #4-#5 OpenAI + Grok adapters (subsequent PRs, built on AsyncOpenAI per issue #7)
5.5 swarph onboard + swarph ratify (lives in swarph-cli, depends on this)
5.7 swarph daemon + REPL drain coroutine (lives in swarph-cli)
6 (already done) PyPI publish
7 swarph-meshlm plugin (separate repo, this dep)

Install (dev)

git clone https://github.com/darw007d/swarph-mesh
cd swarph-mesh
python -m venv venv && source venv/bin/activate
pip install -e ".[dev]"
pytest

License

MIT. Pierre Samson + Claude Opus, 2026.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

swarph_mesh-0.4.0.tar.gz (47.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

swarph_mesh-0.4.0-py3-none-any.whl (35.2 kB view details)

Uploaded Python 3

File details

Details for the file swarph_mesh-0.4.0.tar.gz.

File metadata

  • Download URL: swarph_mesh-0.4.0.tar.gz
  • Upload date:
  • Size: 47.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.3

File hashes

Hashes for swarph_mesh-0.4.0.tar.gz
Algorithm Hash digest
SHA256 e0d18877b8913093fd7f39fe56279de2a32ffba67fb533e089436b26ba4369f8
MD5 db4e4cbd4cf2054e950f8962926f1b87
BLAKE2b-256 e025e7361c72cff18d28438bcb9fa5f09b4b8479c39294b88f1fa72014b6b02a

See more details on using hashes here.

File details

Details for the file swarph_mesh-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: swarph_mesh-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 35.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.3

File hashes

Hashes for swarph_mesh-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1e6865af5d4fa12b886fe31b9fc07dcb81cb39cffe6d5e84281a3fb8d6480175
MD5 f8cef726e79a50ff1a1bac282b1d2829
BLAKE2b-256 807eea1a27d0da8a92a0a53ef293258a88791e773bec06f660f82621b30f6c9a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page