MECHANISM · CONTEXT · CORE

Tool Output Truncation

Bound oversized tool results while preserving provenance, size, and a useful preview.

1 lessons0 agent snapshots1 experiments

contexttool-output-truncationproblem → policy → evidence

L0Intuitionpartial

L1Buildcomplete

L2Engineeringpartial

L3Architecturemissing

L4Researchmissing

DEPENDENCY GRAPH · READER PATH

What feeds it, and what does it unlock?

Arrows show learning and design dependencies, not runtime data flow. Follow any node to continue through the Atlas.

Prerequisites

tool-dispatchTool Dispatch context-budgetContext Budget

tool-output-truncationTool Output TruncationCurrent research boundary

UnlocksNo dependents yet

Bilingual deep dive missing

Bound oversized tool results while preserving provenance, size, and a useful preview.

The structured record is in the Atlas, but the L0–L4 article has not passed content review.

AGENT MAPPING · EVIDENCE ONLY

Snapshot implementations

An implementation enters the map only when both a snapshot and claims exist; unknowns remain visible.

UNKNOWN · EVIDENCE GAPClaude Code

No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.

Inspect coverage boundary →

UNKNOWN · EVIDENCE GAPCodex

No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.

Inspect coverage boundary →

UNKNOWN · EVIDENCE GAPGrok Build

No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.

Inspect coverage boundary →

UNKNOWN · EVIDENCE GAPOpenCode

No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.

Inspect coverage boundary →

UNKNOWN · EVIDENCE GAPPi

No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.

Inspect coverage boundary →

UNKNOWN · EVIDENCE GAPReasonix

No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.

Inspect coverage boundary →

UNKNOWN · EVIDENCE GAPReference Harness

No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.

Inspect coverage boundary →

No reviewed Agent claims

The teaching-harness reference does not automatically become an architectural claim about any vendor agent.

EXPERIMENTS · EXERCISES

What has actually been tested?

Formal experiments are separate from course exercises. Exercises can validate the reference implementation but cannot replace Native evidence from a real agent.

controlled · completeReference Harness context budget and truncation probeDoes the Reference Harness enforce a declared context budget and record deterministic tool-output truncation?

s06-context-budgetobserve

Verify budget decisions

The trace proves both oversized-result truncation and context.prune before the next request.

python3 -m curriculum.golden verify s06-context-budget

s06-context-budgetmodify

Test the two-level budget

Per-result limiting and history pruning act independently and emit structured observations.

python3 -m unittest curriculum.tests.test_vertical_slice.VerticalSliceTests.test_s06_truncates_and_prunes -v

OPEN QUESTIONS · L4

01

When should output be truncated, summarized, indexed, or stored out of band?