What does this PR do?

This PR addresses two correctness issues in the Honcho integration introduced in pr-#736:

1. It enforces memoryMode=local at runtime so that Hermes does not initialize or prewarm remote Honcho when both active peers are configured as local.
2. It preserves Honcho session-scoped write semantics in the gateway by reusing a persistent Honcho manager across request-scoped AIAgent instances for the same gateway session.

Related Issue

Follow-up to #736

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Security fix
• Documentation update
• Tests (adding or improving test coverage)
• Refactor (no behavior change)
• New skill (bundled or hub)

Changes Made

• Updated run_agent.py to:
  • treat memoryMode=local as a real runtime disablement for remote Honcho activation when both active peers resolve to local
  • support injection of an existing Honcho manager/config from the gateway
  • keep first-turn prompt warmup cache-safe by avoiding dynamic Honcho dialectic prewarm in the cached prompt path
• Updated gateway/run.py to:
  • persist Honcho managers per gateway session key
  • reuse those managers across short-lived request handlers
  • shut them down at real gateway session boundaries instead of per request
• Added regression tests in tests/test_run_agent.py for:
  • memoryMode=local skipping Honcho activation
  • injected Honcho managers bypassing fresh client initialization
• Added regression tests in tests/gateway/test_honcho_lifecycle.py for:
  • gateway Honcho manager reuse across requests
  • local mode skipping gateway Honcho manager creation
  • session reset shutting down the persistent manager

How to Test

1. Configure Hermes with Honcho enabled and set both active peers to memoryMode=local.
2. Run a Hermes session and verify that remote Honcho is not initialized or prewarmed.
3. Start the gateway and send multiple messages in the same session; verify that the same Honcho manager is reused and only shut down at the gateway session boundary.

Validation run for this branch:

1. pytest tests/ -q
2. pytest tests/test_run_agent.py -q
3. pytest tests/gateway/test_honcho_lifecycle.py -q
4. python -m hermes_cli.main doctor
5. python -m hermes_cli.main config check
6. python -m hermes_cli.main chat -q "test message"

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform: macOS

Documentation & Housekeeping

• N/A: no user-facing documentation changes were required
• N/A: no config keys changed, so cli-config.yaml.example did not require updates
• N/A: no contributor workflow or architecture guide changes were required
• I've considered cross-platform impact per the compatibility guide
• N/A: no tool schema or description changes were required

Screenshots / Logs

Test summary:

• pytest tests/ -q -> 2692 passed, 5 skipped, 23 deselected

Commits included:

• 7ffaaa0 fix(honcho): enforce local mode and cache-safe warmup
• 353a9e7 fix(gateway): persist Honcho managers across session requests