Context Discipline Rules for Predictable Agent Behavior

Context discipline is the practice of structuring, trimming, and refreshing everything an agent sees so each decision is based on goal-relevant information instead of an unbounded transcript.

Most "the model got dumber mid-run" reports are context problems: noise, contradiction, or sheer volume drowning the current objective.

How to Use This List

• Apply structure rules to system policy first, then trimming rules to the running transcript.
• Pick numeric caps (tool-result size, retained turns) per product and write them down.
• Review context dumps from failing runs the same way you review stack traces.
• Revisit caps when tools start returning larger payloads (HTML, logs, files).

Structure Rules

Trimming and Retention Rules

1. Trim before the window is full. Waiting for overflow forces crude drops; proactive trim preserves signal.
2. Prefer dropping superseded tool results over dropping the goal statement. Old search hits lose value faster than the success criteria.
3. Leave markers when omitting history. The model should know context was reduced, not silently forget it ever happened.
4. Cap retained tool results to a fixed N (or token budget). Choose N from observed runs, not from "keep everything."
5. Collapse failed attempts. Keep the final successful retry, not every intermediate stack trace, unless debugging mode is on.
6. Summarize long plans when entering a new phase. A three-line "current plan" beats a ten-turn argument about abandoned approaches.
7. Never re-inject full files repeatedly. Cache references, hashes, or retrieved slices; do not paste the same blob every turn.

Tool-Boundary Rules

8. Truncate or summarize at the tool adapter, not only in the prompt. Huge raw API responses should never reach the model whole by default.
9. Normalize tool errors into short, structured messages. A 2 KB structured error beats a 50 KB HTML failure page.
10. Strip secrets and PII at the boundary. Context discipline includes what must never enter the window.
11. Label tool results with purpose and timestamp. Ambiguous blobs cause the model to reuse stale observations.
12. Reject oversized results as first-class failures. Trigger a smaller query or summary tool instead of forcing the model to "cope."

Refresh and Consistency Rules

13. Restate the active goal at phase boundaries. Long runs drift toward local tool subgoals without an explicit refresh.
14. Keep output contracts stable for the same task type. Parsers and downstream steps depend on consistent shapes.
15. Separate scratch reasoning from durable conclusions. Persist decisions; drop verbose intermediate monologues when the framework allows.
16. Avoid contradictory instructions via accretion. Prune rules nobody can justify; contradictions look like flaky behavior.
17. Budget tokens for observations vs instructions. If tools consume 90% of the window, policy and goal cannot compete.
18. Version the context policy with the agent. Prompt and trim logic change together in review, not as hot silent edits.

Context Policy Cheatsheet

Minimal Trim Sketch

MAX_TOOL_RESULTS = 6
 
 
def trim_messages(messages: list[dict]) -> list[dict]:
    """Keep recent tool observations; mark older ones as omitted."""
    tool_idxs = [i for i, m in enumerate(messages) if m.get("role") == "tool"]
    if len(tool_idxs) <= MAX_TOOL_RESULTS:
        return messages
    keep_from = tool_idxs[-MAX_TOOL_RESULTS]
    out = []
    for i, m in enumerate(messages):
        if i < keep_from and m.get("role") == "tool":
            out.append({"role": "tool", "content": "[earlier tool result omitted]"})
        else:
            out.append(m)
    return out

This sketch is illustrative only.

Production systems often use token budgets, summarization turns, or framework memory primitives - the rule is explicit policy, not a specific algorithm.

FAQs

Related

• The Core Agent Fundamentals Rules: A Quick-Reference List - condensed context rows.
• Why Fundamentals Rules Prevent Early Agent Project Failures - why context drift becomes an incident class.
• Stopping-Condition Rules Every Agent Must Implement - finite runs that still need a clean window each turn.
• Model-Swapping Rules for Cost and Capability Flexibility - context size drives cost across model tiers.
• AI Agent Fundamentals Rules Best Practices - checklist form including context items.

Stack versions: Pins from the category manifest (verify at build): OpenRouter (~315+ models, July 2026 pricing/fees); LangGraph 1.0+; CrewAI 1.14+; Microsoft Agent Framework 1.0; Vercel AI SDK 6; Pydantic AI (latest); LlamaIndex (latest); OpenAI Agents SDK (latest + MCP); MCP (Linux Foundation governance); A2A (HTTP+SSE+JSON-RPC 2.0); Solana @solana/web3.js + @solana/spl-token.