No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.
Inspect coverage boundary →MECHANISM · TOOLS · CORE
Tool Dispatch
Validate, authorize, execute, normalize, and record model-requested tool calls.
1 lessons6 agent snapshots1 experiments
toolstool-dispatchproblem → policy → evidence
L0Intuitionpartial
L1Buildcomplete
L2Engineeringpartial
L3Architecturemissing
L4Researchpartial
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 DispatchCurrent research boundary
Validate, authorize, execute, normalize, and record model-requested tool calls.
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.
1 evidence-backed claim.
codex-2026-08-10-source →1 evidence-backed claim.
grok-build-2026-08-10-source →1 evidence-backed claim.
opencode-2026-08-10-source →1 evidence-backed claim.
pi-2026-08-10-source →1 evidence-backed claim.
reasonix-2026-08-10-source →Controlled project baseline only; this implementation is not comparable with a native vendor run.
reference-harness-2026-08-10-controlled →CLAIMS · EVIDENCE LEDGER6 RECORDS
source + sourcereviewed
codex-source-tool-router
The pinned Codex core separates model-visible tool specifications in ToolRouter from runtime registration and collision handling in ToolRegistry, then resolves each parsed call to its registered runtime.
- Agent
- Codex
- Snapshot
- codex-2026-08-10-source
- Reviewed
- 2026-08-10
sourcereviewed
grok-build-source-tool-bridge
Grok Build's pinned ToolBridge owns a finalized registry, exposes model-facing definitions, supports built-in and MCP-backed registrations, and routes calls through typed registry dispatch.
- Agent
- Grok Build
- Snapshot
- grok-build-2026-08-10-source
- Reviewed
- 2026-08-10
sourcereviewed
opencode-source-tool-registry
OpenCode's pinned tool registry combines built-in, custom, plugin, and MCP definitions, permission-filters visibility, validates arguments, and dispatches registered handlers with normalized output metadata.
- Agent
- OpenCode
- Snapshot
- opencode-2026-08-10-source
- Reviewed
- 2026-08-10
sourcereviewed
pi-source-tool-dispatch
Pi validates tool arguments, offers before- and after-tool interception points, and executes a batch sequentially or in parallel according to the configured strategy and individual tool constraints.
- Agent
- Pi
- Snapshot
- pi-2026-08-10-source
- Reviewed
- 2026-08-10
source + sourcereviewed
reasonix-source-tool-dispatch
Reasonix separates batch scheduling from single-call execution, so concurrency decisions, per-call context, capability gates, tool invocation, results, and failure bookkeeping cross explicit boundaries.
- Agent
- Reasonix
- Snapshot
- reasonix-2026-08-10-source
- Reviewed
- 2026-08-10
reproducedreviewed
reference-harness-controlled-tool-roundtrip
In the controlled reference experiment, the project harness validates and executes one declared read_file call, records the successful result between two model turns, and produces the same normalized trace fingerprint across two repetitions.
- Agent
- Reference Harness
- Snapshot
- reference-harness-2026-08-10-controlled
- Reviewed
- 2026-08-10
Snapshot claim →reproduced · Reference tool roundtrip controlled run
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.
s03-tool-dispatchobserve
Verify the tool roundtripThe request, result, and second model request appear in causal order.
python3 -m curriculum.golden verify s03-tool-dispatchs03-tool-dispatchmodify
Test the dispatch contractThe tool result returns to the next turn as a tool message bound to tool_call_id.
python3 -m unittest curriculum.tests.test_vertical_slice.VerticalSliceTests.test_s03_tool_roundtrip -v01
Where should provider tool-call repair end and harness validation begin?