Go to file
rabbitblood 4bafea58ae fix(llm_auth): tighten base-URL hostname match + strip whitespace + no token in logs
Self-review findings on #38:

1. **Token substring leak**: the "unknown prefix" warning included the
   first 12 chars of the token in the log message. Logs get shipped to
   Langfuse / CloudWatch / slack-firehose — 12 bytes of a secret in a
   log is still 12 bytes too many. Warning no longer references the
   token value at all.

2. **Base-URL substring match was too loose**: `"anthropic.com" not in
   base` would accept `https://proxy.anthropic.com.evil.example/` as
   "looks like Anthropic, keep the URL." Replaced with an allowlist of
   exact hostnames parsed via urllib.parse.urlparse.

3. **Whitespace in pasted tokens**: operators frequently paste tokens
   from terminals with a trailing newline. The token would flow through
   startswith() detection but then fail downstream auth with a
   confusing "malformed token" error. Strip and persist the cleaned
   value.

4. **Malformed base URL crash guard**: if someone sets ANTHROPIC_BASE_URL
   to something urlparse can't handle, don't crash — fall through to
   clearing it, which is the safe choice in OAuth mode.

Added 5 new tests covering each of the above. 16/16 tests pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-23 10:46:07 -07:00
.github/workflows fix(CI): remove conflicting bandit flags from security linter step 2026-04-21 00:58:43 +00:00
molecule_runtime fix(llm_auth): tighten base-URL hostname match + strip whitespace + no token in logs 2026-04-23 10:46:07 -07:00
tests fix(llm_auth): tighten base-URL hostname match + strip whitespace + no token in logs 2026-04-23 10:46:07 -07:00
.gitignore chore: gitignore credentials for molecule-ai-workspace-runtime 2026-04-16 09:18:48 -07:00
pyproject.toml chore: bump 0.1.8 — executor_helpers phantom-busy fix confirmed in tree 2026-04-21 07:16:47 -07:00
README.md feat: initial release of molecule-ai-workspace-runtime 0.1.0 2026-04-16 04:26:06 -07:00

molecule-ai-workspace-runtime

Shared Python runtime infrastructure for all Molecule AI agent adapters.

This package provides the core machinery that every Molecule AI workspace container needs:

  • A2A server — Registers with the platform, heartbeats, serves A2A JSON-RPC
  • Adapter interfaceBaseAdapter / AdapterConfig / SetupResult
  • Built-in tools — delegation, memory, approvals, sandbox, telemetry
  • Skill loader — loads and hot-reloads skill modules from /configs/skills/
  • Plugin system — per-workspace + shared plugin discovery and install
  • Config / preflight — YAML config loading with validation

Installation

pip install molecule-ai-workspace-runtime

Adapter Discovery

The runtime discovers adapters in two ways:

  1. ADAPTER_MODULE env var (standalone adapter repos):

    ADAPTER_MODULE=my_adapter molecule-runtime
    

    The module must export an Adapter class extending BaseAdapter.

  2. Built-in subdirectory scan (monorepo local dev): Scans molecule_runtime/adapters/ subdirectories for Adapter classes.

Writing an Adapter

from molecule_runtime.adapters.base import BaseAdapter, AdapterConfig
from a2a.server.agent_execution import AgentExecutor

class Adapter(BaseAdapter):
    @staticmethod
    def name() -> str:
        return "my-runtime"

    @staticmethod
    def display_name() -> str:
        return "My Runtime"

    @staticmethod
    def description() -> str:
        return "My custom agent runtime"

    async def setup(self, config: AdapterConfig) -> None:
        result = await self._common_setup(config)
        # Store result attributes for create_executor

    async def create_executor(self, config: AdapterConfig) -> AgentExecutor:
        # Return an AgentExecutor instance
        ...

Set ADAPTER_MODULE=my_package.adapter and run molecule-runtime.

License

BSL-1.1 — see LICENSE for details.