The chat agent had two tools -- memory_edit and skill_activate -- so it
could not read a file, search a tree or run a command. ai-sdk's runtime
already drives a tool loop for it (MaxSteps 8, toolExecute wired as the
executor), so the loop was never the missing piece: the registry was empty
of anything useful.
Lifted from tau internal/agent/tools at commit f5289ea, per the recorded
copy-and-mutate strategy: every file carries a provenance header naming its
tau source path, the commit, and the mutations made, so refreshing from
upstream is a diff rather than archaeology.
internal/tools/builtin/ the lifted tools, ~3.1k lines
internal/tools/provider/builtin/ the adapter to tools.ToolEntry
Six tools: read, write, edit, shell, grep, find. Tau's own tests came with
them and pass unmodified, which is the evidence that the lift is faithful.
Deliberately not lifted:
- agent.go (1214 lines): subagent spawning, and the only real coupling in
the package -- 10 tau packages including chat, sessions, store and
registry. Nothing the chat agent needs to do work.
- skill.go: depends on tau's skills package; archie has internal/skill and
already exposes skill_activate.
- docs.go: serves tau's own embedded documentation via tau/docs.
Not lifting the coordinator either. It is tau's agent loop (6.4k lines over
ten packages) and archie already has one in the ai-sdk runtime; porting it
would leave two loops competing. Its cancellation and tool events are worth
having, but they are a few hundred lines built against the existing path
rather than six thousand lifted onto a second one.
The adapter bridges two shape differences: archie hands handlers decoded
arguments where tau's executor takes raw JSON, and tau reports tool-level
failure in Result.IsError rather than as an error -- surfaced as a real
error so the runtime and the guardrail engine both see it. Tools are
classified idempotent or mutating for guardrails and budgets; that is
categorisation, not a jail.
chat.workspace roots the tools and defaults to empty, which registers none
of them. They read, write and execute, so the directory has to be a
deliberate choice rather than whatever the daemon started in -- in the
container that is /.
Verified: go build, go vet, gofmt clean; full suite passes.
41 lines
1.4 KiB
Go
41 lines
1.4 KiB
Go
// Lifted from tau internal/agent/tools/procgroup_windows.go
|
|
// tau commit f5289ea3782c099339c2d26fe3af8ebcf42ba52d (2026-07-27).
|
|
//
|
|
// Mutations from upstream:
|
|
// - package renamed tools -> builtin (archie-core already has an
|
|
// internal/tools package holding the registry these are registered into).
|
|
//
|
|
// Refresh by diffing against that path at a newer tau commit. Do not
|
|
// edit without recording the change above.
|
|
//go:build windows
|
|
|
|
package builtin
|
|
|
|
import (
|
|
"os/exec"
|
|
"syscall"
|
|
)
|
|
|
|
// setProcessGroup configures cmd to start in a new process group on
|
|
// Windows (see docs/specs/agents/02-spawning-and-lifecycle.md, Process
|
|
// group management / Platform behavior).
|
|
func setProcessGroup(cmd *exec.Cmd) {
|
|
if cmd.SysProcAttr == nil {
|
|
cmd.SysProcAttr = &syscall.SysProcAttr{}
|
|
}
|
|
cmd.SysProcAttr.CreationFlags |= syscall.CREATE_NEW_PROCESS_GROUP
|
|
}
|
|
|
|
// signalProcessGroup best-effort terminates cmd's direct process on
|
|
// Windows. Windows has no POSIX-style negative-pid group signal; the spec's
|
|
// documented fallback is TerminateProcess (GenerateConsoleCtrlEvent would
|
|
// require additional job-object/console plumbing this doesn't set up), so
|
|
// descendants spawned by the child are not guaranteed to receive this -
|
|
// a known platform limitation, not an oversight.
|
|
func signalProcessGroup(cmd *exec.Cmd, _ syscall.Signal) error {
|
|
if cmd.Process == nil {
|
|
return nil
|
|
}
|
|
return cmd.Process.Kill()
|
|
}
|