Bug: Agent instructions from .md files are never loaded in spawn pipeline

Summary

Agent definitions in .md files within the agents/ directory are never loaded when spawning sub-sessions via the task tool. The resolve_agent_path() method exists but is never called in the spawn pipeline.

Affected component: amplifier-foundation

Root Cause Analysis

1. Agent Parsing Only Stores Names

In amplifier_foundation/bundle.py, the _parse_agents() function only stores agent names, not their content:

def _parse_agents(agents_config, base_path):
    if "include" in agents_config:
        for name in agents_config["include"]:
            result[name] = {"name": name}  # ← Just the name, NO instruction!
    return result

2. resolve_agent_path() Exists But Is Never Called

The method Bundle.resolve_agent_path() correctly handles both:

• source_base_paths[namespace] for included bundles
• Fallback to self.base_path when namespace == self.name

But this method is never called in the spawn pipeline.

3. Spawn Expects Pre-populated Instruction

In the CLI's session_spawner.py, the code expects agent_config to already contain {"system": {"instruction": "..."}}:

system_instruction = agent_config.get("system", {}).get("instruction")
if system_instruction:
    await context.add_message({"role": "system", "content": system_instruction})

But it only has {"name": "bundle:agent-name"}.

Impact

• Agents spawn without their specialized system prompts
• Custom agents defined by bundle authors are effectively ignored
• The agents/ directory structure provides no value beyond documentation

Proposed Fix

In the spawn pipeline, before using agent_config, load agent content from the .md file using the existing resolve_agent_path() method.

Steps to Reproduce

1. Create a bundle with an agent in agents/my-agent.md
2. Register the bundle with amplifier bundle register
3. Try to spawn the agent: Use bundle:my-agent to do X
4. Observe that the agent's instructions are not loaded

Expected Behavior

Agent instructions from .md files should be loaded and injected as system prompts when spawning.

Start in amplifier_foundation/bundle.py with _parse_agents() and Bundle.resolve_agent_path(), then trace the spawn path in session_spawner.py where agent_config supplies the system instruction. Reproduce the issue with an agents/my-agent.md file and the task tool. Done means the markdown instructions are loaded and injected as the spawned agent's system prompt.