From d1306506aa7f504b0e91c9c6ed7314afbf99978e Mon Sep 17 00:00:00 2001
From: t <t@tjp.lol>
Date: Wed, 19 Aug 2026 19:02:30 -0600
Subject: Add background Lua workflows, inline child prompts, and layered
 config

subagents.lua now starts a workflow on its own coroutine and returns a
session-scoped id immediately, so fan-out continues while the primary keeps
working; completion wakes the primary, and later calls read immutable records
from subagents.workflows. Every ctx:agent takes a workflow-unique name so those
records are addressable. A session_start guidance message tells the primary when
to reach for run vs lua.

Children no longer inherit the primary's system context: a child starts from the
fixed child-role instruction plus its profile, and subagents.run/ctx:agent
accept an inline system_prompt instead of a profile. The now-redundant `agent`
form of subagents.models is gone.

Concurrency defaults to five and is configurable through [subagents]
max_concurrent in any layered config.toml; turn boundaries reap only settled
jobs so background workflows survive, while interrupt and session end cancel.

Config roots come from panto.ext.dirs.layers rather than a hand-rolled XDG
lookup, which picks up the base and git-ignored local layers for both agents/
and workflows/.

TOML workflows tighten up: the subagents.workflow tool takes a discovered name
only (inline `steps` duplicated subagents.lua at less power), an optional
top-level `output` array chooses the reported steps and their order instead of
the terminal set, a step with no workflow input gets no empty input heading, and
a workflow naming an undiscovered agent is rejected at discovery rather than
part-way through a run.
---
 subagents/jobs.lua | 35 +++++++++++++++++++++++++++--------
 1 file changed, 27 insertions(+), 8 deletions(-)

(limited to 'subagents/jobs.lua')

diff --git a/subagents/jobs.lua b/subagents/jobs.lua
index a774b27..9fe5c93 100644
--- a/subagents/jobs.lua
+++ b/subagents/jobs.lua
@@ -11,10 +11,9 @@
 -- an edge trigger, never a count, so every wake drains the pipe, then drains
 -- `job:next_event()` to exhaustion, then checks `job:result()`.
 --
--- Waiting parks the CALLING coroutine — the tool handler's — and a poll
--- callback resumes exactly that coroutine. subagents/workflow.lua's rule that
--- a workflow callback must never run on a nested coroutine follows from this:
--- the parked thread is the one the resume goes to.
+-- Waiting parks the CALLING coroutine and a poll callback resumes that exact
+-- coroutine. Foreground tools use their handler coroutine; background
+-- workflows provide a dedicated coroutine anchored in their registry record.
 --
 -- The wake pipe is therefore mandatory wherever luv is: a started job whose
 -- pipe or poll could not be armed is a start failure, not a degraded job.
@@ -43,9 +42,9 @@ local READ_CHUNK = 4096
 
 local M = {}
 
--- The session-wide bound. A field, not a constant, so a caller (or a spec) can
--- lower it without reaching into the queue.
-M.MAX_CONCURRENT = 4
+-- The activation-time default is five; init.lua may replace it from the
+-- layered `[subagents] max_concurrent` setting before any child can start.
+M.MAX_CONCURRENT = 5
 
 local handle_mt = {}
 handle_mt.__index = handle_mt
@@ -58,6 +57,7 @@ local queued = {}
 local waiters = {}
 local running = 0
 local pumping = false
+local cancelling = false
 
 -- ---------------------------------------------------------------------------
 -- Wake pipes
@@ -191,7 +191,7 @@ end
 -- Start queued jobs while the gate has room. Reentrant: a job that settles the
 -- instant it starts calls back in here, and the outer loop keeps going.
 function pump_queue()
-    if pumping then
+    if pumping or cancelling then
         return
     end
     pumping = true
@@ -442,9 +442,28 @@ end
 -- The turn was interrupted: ask every child to stop. Cancellation is a request,
 -- not a settle — each job still reports its own cancelled result.
 function M.cancel_all()
+    cancelling = true
     for index = #live, 1, -1 do
         live[index]:cancel()
     end
+    cancelling = false
+    pump_queue()
+    wake()
+end
+
+-- Close settled jobs without disturbing queued or running background work.
+-- Called at ordinary turn boundaries; session teardown still uses close_all.
+function M.reap()
+    local kept = {}
+    for _, handle in ipairs(live) do
+        if handle.settled ~= nil then
+            close_pipe(handle)
+            close_job(handle)
+        else
+            kept[#kept + 1] = handle
+        end
+    end
+    live = kept
 end
 
 -- The turn is over: cancel every child and drop the state. Never blocks — a
-- 
cgit v1.3