1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

MODE_ENTER = (
    "Orchestration mode is on: optimize for the most exhaustive, correct answer rather than "
    "the fastest one. Use the Workflow tool on every substantive task, sized to the problem's "
    "natural decomposition rather than the maximum the tool allows. See the Workflow tool's "
    "description for standing consent, granularity guidance, and quality patterns. Work solo "
    "only on conversational or trivial turns."
)
MODE_REFRESH = (
    "Orchestration mode is still on. Use the Workflow tool; see its standing consent section."
)
MODE_EXIT = (
    "Orchestration mode is off. The Workflow tool's standard opt-in rule applies again."
)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66

WORKFLOW_TOOL = {
    "name": "Workflow",
    "description": (
        "Orchestrate a multiagent workflow: split a large task into independent subtasks "
        "and run them as parallel agents, then collect their results.\n\n"
        "Opt-in: only use this tool when the user explicitly asks for a workflow, or when a "
        "system message confirms that orchestration mode is on.\n\n"
        "Quality patterns: adversarial verification (a second wave of agents checks the first "
        "wave's findings against the source), a completeness critic (one agent hunts for what "
        "the others missed), and multiphase sequencing (understand, design, implement, and "
        "review as separate workflow calls, reading results between phases). A useful default "
        "is hybrid: scout inline first to discover the work-list, then fan out over it.\n\n"
        "Granularity: scope each subtask to a distinct concern, component, or question rather "
        "than per line or per file section. Scale the count to what the user asked for: a "
        "focused review of a module of a few hundred lines rarely needs more than about ten "
        "subtasks; a broad audit of a large codebase can justify more.\n\n"
        "Standing consent: while a system message confirms orchestration mode is on, that "
        "opt-in is standing. Author and run a workflow for every substantive task by default, "
        "and lean toward verifying findings adversarially. Work solo only on conversational "
        "turns or trivial mechanical edits. When a system message says the mode is off, "
        "revert to the opt-in rule above."
    ),
    "input_schema": {
        "type": "object",
        "properties": {
            "subtasks": {
                "type": "array",
                "items": {"type": "string"},
                "description": "Independent subtask prompts to run as parallel agents",
            }
        },
        "required": ["subtasks"],
    },
}

BASH_TOOL = {"type": "bash_20250124", "name": "bash"}

REPORT_TOOL = {
    "name": "report_findings",
    "description": (
        "Report the final findings for your subtask. Call this exactly once, when you are "
        "done investigating; it ends your task."
    ),
    "input_schema": {
        "type": "object",
        "properties": {
            "summary": {"type": "string", "description": "Two or three sentences of synthesis"},
            "findings": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "claim": {"type": "string", "description": "The finding, one sentence"},
                        "evidence": {
                            "type": "string",
                            "description": "How it was verified (file, line, or command output)",
                        },
                        "severity": {"type": "string", "enum": ["high", "medium", "low", "info"]},
                    },
                    "required": ["claim", "evidence", "severity"],
                },
            },
        },
        "required": ["summary", "findings"],
    },
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52

def run_subagent(model: str, prompt: str) -> str:
    """One subagent: a small nested agent loop with the bash tool plus report_findings.
    Subagents inherit the main loop's effort level."""
    subagent_system = (
        "You are one agent in a larger parallel fan-out, assigned a single subtask. "
        "Investigate it directly, using bash to check facts rather than guessing, and finish "
        "by calling report_findings exactly once. Return findings, not narration."
    )
    messages = [{"role": "user", "content": prompt}]
    for _ in range(MAX_SUBAGENT_TURNS):
        with client.messages.stream(
            model=model,
            max_tokens=64000,
            system=subagent_system,
            output_config={"effort": EFFORT},
            tools=[BASH_TOOL, REPORT_TOOL],
            messages=messages,
            timeout=REQUEST_TIMEOUT_SECONDS,
        ) as stream:
            response = stream.get_final_message()
        messages.append({"role": "assistant", "content": response.content})
        if response.stop_reason == "pause_turn":
            continue
        if response.stop_reason != "tool_use":
            text = "".join(block.text for block in response.content if block.type == "text")
            if response.stop_reason == "max_tokens":
                text += "\n\n(warning: subagent response was truncated at max_tokens)"
            return text
        tool_results = []
        report = None
        for block in response.content:
            if block.type != "tool_use":
                continue
            if block.name == "report_findings":
                report = json.dumps(block.input, indent=2)
                output, is_error = "Findings recorded.", False
            elif block.name == "bash":
                output, is_error = handle_bash_block(block)
            else:
                output, is_error = f"unknown tool: {block.name}", True
            tool_results.append(
                {
                    "type": "tool_result",
                    "tool_use_id": block.id,
                    "content": output,
                    "is_error": is_error,
                }
            )
        if report is not None:
            return report
        messages.append({"role": "user", "content": tool_results})
    return "(subagent hit the turn limit before finishing)"