Day 6: Inspect and Steer a Paused Agent

🚧 Early-review WIP: This chapter is public for early review and may change. Use a disposable workspace when running the agent or enabling writes or commands.

Day 4 gave the harness a safe pause after a complete tool observation. Day 5 showed how to make older completed evidence smaller for the model without discarding the full receipts. Those boundaries also create a useful moment for an operator: inspect what the paused run has actually recorded, add one new instruction, and let a fresh model continue.

Day 6 implements only that interaction. It does not inspect hidden reasoning or guess the model’s plan. It reports public facts from the checkpoint, appends one ordinary steering message, and resumes through the existing validated loop.

The Starter Surface

Day 6 adds one module:

Copy and run the six learner tasks:

pdm run copy-test --week 4 --day 6
pdm run test --week 4 --day 6

Use this command for the supplied implementation:

pdm run test-refsol --week 4 --day 6

Before you implement the TODOs, all six Day 6 tasks are expected to fail.

Start at a Safe Pause

run_to_checkpoint(...) saves after the assistant action and its tool result are both present:

original task
    ...
assistant tool action
tool observation
                  ^ inspect and steer here

This is deliberately not mid-token or mid-tool steering. No process is running in the background. The workspace is quiescent, and the checkpoint binds the original task, the complete message prefix, and the fake-model cache metadata.

Task 1: Derive a Public Status

Implement:

inspect_checkpoint(checkpoint, evidence_chars=160) -> AgentStatus

Validate the checkpoint, then require its final two messages to be a parsed assistant tool action followed by a Tool result:\n... user observation. Return four public facts:

AgentStatus(
    task="fix app.py and validate",
    last_action='{"new":"2","old":"1","path":"app.py","tool":"edit_file"}',
    last_evidence="edited app.py",
    next_step="resume the model after the completed edit_file observation",
)

last_evidence is a bounded prefix of the recorded observation. When it is too long, reserve the final character for an ellipsis so its length never exceeds evidence_chars.

The status function must not receive or call a model or workspace. It reads the validated immutable checkpoint and returns a new frozen value.

Task 2: State Only What the Harness Knows

The checkpoint knows the current task and the last completed action/result. It does not know what the model will decide next. Therefore next_step is a deterministic harness boundary:

resume the model after the completed edit_file observation

Do not replace this with a semantic guess such as “update the tests next.” That would present invented intent as agent state. A richer plan would need its own explicit, model-visible artifact; Day 6 does not add one.

Reject an incomplete boundary rather than producing a misleading card. A checkpoint ending with an ordinary user message, malformed assistant text, or anything other than a complete action/observation pair is not inspectable by this API.

Task 3: Append One Steering Message

Implement:

resume_with_steering(
    checkpoint,
    steering,
    fresh_generate,
    workspace,
    limits=None,
) -> AgentRun

Reject an empty or whitespace-only instruction. For a valid instruction, restore the checkpoint into the fresh generator and derive a mutable copy of the saved transcript. Append exactly one ordinary user message:

{
    "role": "user",
    "content": "Operator steering:\nvalidate before answering",
}

Then pass that list to the existing bounded loop. Do not add a separate queue, control channel, hidden prompt, or special protocol action.

Task 4: Keep the Message in Stable Order

The steering message belongs immediately after the saved checkpoint prefix. If the resumed model chooses another tool, the existing loop appends that assistant action and its observation after the steering:

saved task and evidence
Operator steering: validate before answering
assistant run_command action
validation observation
assistant final answer

Append the steering message once. Because the loop carries its message list forward, every later model call sees the same single message at the same position. Reinserting it on every call would duplicate the instruction and change the conversation.

Task 5: Continue Without Replaying Effects

The focused scenario starts with the original task “fix app.py and validate.” The first model reads and edits app.py, and the harness checkpoints after the complete edit observation. At that point:

• app.py already contains the new value;
• the edit approval happened once;
• the receipt store contains the edit receipt; and
• inspection reports the saved edit evidence without touching the workspace.

The operator adds “validate before answering.” A fresh scripted model restores the saved prefix, sees the original task, edit evidence, and steering message, then runs the exact allowed validation command and returns its final answer. The test proves the edit approval remains single, validation executes once, and the edit and command retain separate receipts.

Steering changes the next model input. It does not undo, replay, or rewrite the completed prefix.

Task 6: Keep the Boundary Small

Fail clearly when the checkpoint identity is invalid, the generator cannot restore the saved fake-model state, the evidence limit is not a positive integer, or steering is blank. Reuse AgentError, AgentCheckpoint, AgentLimits, AgentRun, and the existing loop rather than creating parallel versions.

The Day 6 module does not add concurrent interruption, mid-token control, a background worker or status server, a durable steering queue, session trees, branch/rewind, exactly-once reconciliation, or an evaluator. It is one visible pause → inspect → steer → resume path for the course’s scripted model.

Checkpoint

You can now pause after a complete observation, show an operator a bounded status made only from recorded facts, add one visible instruction, and resume a fresh model without replaying the completed effect. Inspect the model inputs in the focused test to verify the original task, saved evidence, and steering stay in order through a later tool turn and final answer.

Continue with Day 7: Evaluate Observable Outcomes to turn the final workspace, tool results, and durable receipts into a structured pass/fail report without grading hidden reasoning or exact transcript shape.

Your feedback is greatly appreciated. Join our Discord community.
Found an issue? Open an issue or pull request at github.com/skyzh/tiny-llm.
tiny-llm-book © 2025 by Alex Chi Z is licensed under CC BY-NC-SA 4.0.