Skip to content

Match toolCallRequest summary to schema #253

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
aaronormerod wants to merge 1 commit into
base: integration
Choose a base branch
from
Open

Match toolCallRequest summary to schema #253

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/spec/instrument/hooks.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -189,7 +189,7 @@ Fires after the framework has parsed a tool call from the LLM's output, but befo

Frameworks MUST fire `toolCallRequest` for every action that escapes the agent's reasoning context, regardless of whether the framework's tool registry models it as a tool. This includes built-in operations such as filesystem reads/writes, network fetches, process execution, and shell commands. The Guardian relies on a complete view of all outward actions; primitives that bypass `toolCallRequest` are invisible to policy.

**Payload:** `tool` (id, capability), `arguments` (each value carrying optional Provenance), agent reasoning.
**Payload:** `tool` (`name` required; `version`, `provider`), `arguments` (a map of objects, each with a required `value` and optional Provenance), and optionally `capability`, `operation`, `raw_command`, and `intent` (`description`, `goal`).

**Decision:** ALLOW / DENY / MODIFY / ASK / DEFER. The full disposition vocabulary applies — this is the hook where most paradigm composition happens.

Expand Down
Loading