steve
dfbc5a42b9
The capstone of the run kernel: run.Executor.Run(ctx, RunnableAgent, inv)
ties model resolution + the tool registry + majordomo's agent loop +
context compaction + run-bounding + step/audit instrumentation into one
path, with every host concern behind the nil-safe run.Ports.
- run/executor.go: New(Config{Registry, Models, Defaults, Ports, Compactor,
ContextTokens, SystemHeader}) + Run -> Result{RunID, Output, Steps, Usage,
Err}. Budget gate (pre-run), model resolve, Audit StartRun/recorder
(satisfies RunTally, stamped on inv.RunState), toolbox build, step observer
(zips tool calls/results -> emitter + recorder.OnStep/OnTool), V10
detached-MaxRuntime context with caller-cancel merged back, compaction wired
from ContextTokens×ratio, audit Close + Budget Commit on a detached cleanup
ctx. Zero Ports = a bounded in-memory run (gadfly's case).
- run/executor_test.go: hermetic end-to-end run against majordomo's fake
provider (hello-world), Budget-rejection (no model call), Audit-port wiring
(StartRun + Close with terminal status/output). All green under -race.
- examples/minimal upgraded to the real "hello, agentic world" (~15 lines:
Configure tiers -> run.New -> Run -> print). README/CLAUDE.md updated.
Remaining P2 follow-ups (incremental): wire Critic/Checkpointer/PaletteSource/
Delivery into the loop, multi-phase Pipelines, and the no-tools direct path.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
50 lines
1.7 KiB
Go
50 lines
1.7 KiB
Go
// Command minimal is executus's "hello, agentic world": wire a model resolver,
|
|
// a tool registry, and the run executor, then run an agent. With no batteries
|
|
// (Audit/Budget/Critic/Checkpointer/Palette/Delivery all nil) this is a
|
|
// bounded, in-memory run — the light-host shape (gadfly's case).
|
|
//
|
|
// Run it with a provider key for the configured tier, e.g.
|
|
//
|
|
// ANTHROPIC_API_KEY=sk-... go run ./examples/minimal
|
|
//
|
|
// Override a tier from the environment without touching code, e.g.
|
|
//
|
|
// EXECUTUS_MODEL_TIER_FAST=openai/gpt-4o-mini ANTHROPIC_API_KEY= OPENAI_KEY=sk-... go run ./examples/minimal
|
|
package main
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"log"
|
|
|
|
"gitea.stevedudenhoeffer.com/steve/executus/config"
|
|
"gitea.stevedudenhoeffer.com/steve/executus/model"
|
|
"gitea.stevedudenhoeffer.com/steve/executus/run"
|
|
"gitea.stevedudenhoeffer.com/steve/executus/tool"
|
|
)
|
|
|
|
func main() {
|
|
// 1. Configure model tiers: live values come from the environment
|
|
// (EXECUTUS_MODEL_TIER_<NAME>), falling back to these defaults.
|
|
model.Configure(config.Env("EXECUTUS_"), map[string]string{
|
|
"fast": "anthropic/claude-haiku-4-5",
|
|
"thinking": "anthropic/claude-opus-4-8",
|
|
}, 0)
|
|
|
|
// 2. Build the executor: a tool registry + the model resolver. No batteries.
|
|
ex := run.New(run.Config{
|
|
Registry: tool.NewRegistry(),
|
|
Models: model.ParseModelForContext,
|
|
})
|
|
|
|
// 3. Run an agent and print its answer.
|
|
res := ex.Run(context.Background(),
|
|
run.RunnableAgent{Name: "assistant", SystemPrompt: "You are concise.", ModelTier: "fast"},
|
|
tool.Invocation{RunID: "demo-1", CallerID: "local"},
|
|
"In one sentence, what is an agent harness?")
|
|
if res.Err != nil {
|
|
log.Fatalf("run failed: %v", res.Err)
|
|
}
|
|
fmt.Println(res.Output)
|
|
}
|