fix(tools): collapse code-mode executor to run_code for model-direct calls
wireSchemas() already advertised only run_code under mode: 'code', but the executor resolved every call through get(), which returns the full visible map plus the reserved transport. A model could name a native tool directly and bypass run_code entirely. Route the execution-path lookups through a new private resolveExecution() that applies the mode collapse at the operation boundary: model-direct calls under 'code' may only name run_code (UNKNOWN_TOOL otherwise), while SDK sub-dispatches (parent token set) keep every visible tool. get()/schemas() public semantics are unchanged. The denial happens at createExecution, before the extensible policy pipeline — pre-execute listeners, approval ask, and guards never observe a call that is deterministically denied. A collapsed call honors the pre-dispatch cancellation contract, routes aborted results through the visible tool's finalizeContent, and captures the finalizer before argument materialization. Regenerated docs, catalogs, graphs, scoped events, re-recorded translation pairs, and updated test assertions. Fixes #1815
This commit is contained in:
@@ -343,7 +343,7 @@ describe('startInProcessRun', () => {
|
||||
await expect(startInProcessRun({
|
||||
...request(parent),
|
||||
toolFilter: { deny: ['unknown-tool'] },
|
||||
}, {})).rejects.toThrow('unknown inherited tool')
|
||||
}, {})).rejects.toThrow('unknown global tool')
|
||||
expect(ctx.agents.list()).toHaveLength(beforeAgents)
|
||||
expect(ctx.sessions.list()).toHaveLength(beforeSessions)
|
||||
})
|
||||
|
||||
@@ -436,7 +436,7 @@ describe('dsh-subagent-spawn', () => {
|
||||
prompt: [{ type: 'text', text: 'do X' }],
|
||||
parent,
|
||||
toolFilter: { deny: ['no_such_tool'] },
|
||||
})).rejects.toThrow(/unknown inherited tool "no_such_tool"/)
|
||||
})).rejects.toThrow(/unknown global tool "no_such_tool"/)
|
||||
expect(ctx.agents.list().length).toBe(before)
|
||||
})
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user