steve
899059a791
The kernel defined run.Ports.Checkpointer + the checkpoint battery but never drove them (the documented "P2 follow-up"). This wires durable recovery into the run loop so a run interrupted by shutdown can resume on the next boot instead of being lost — the executus-side half of mort's durable-agent-recovery parity (mort #1355). Kernel (run/): - Ports.Checkpointer is now a CheckpointerFactory (Begin per run → a per-run Checkpointer, or nil for a non-durable run). The single per-instance Checkpointer couldn't distinguish runs; a factory mints one per run, matching mort's agentexec.CheckpointerFactory. - RunInfo gains GuildID + ModelTier (so the factory can build resume meta); RunCheckpointState gains CompletedPhases + ActivePhase (+ PhaseOutput). - run/checkpoint.go: ResumeState + WithResumeState / WithExistingCheckpointer context carriers, classifyCheckpointOutcome (success→Complete, shutdown→leave for boot recovery, else→Fail using run.ErrShutdown), and finalizeCheckpoint. - run/executor.go: resolve the per-run checkpointer (existing-from-ctx on a recovery re-run, else factory.Begin); single-loop wraps the step observer to accumulate the transcript + Save each step (host throttles), and a recovered run seeds the saved transcript via WithHistory and continues with no new input; finalize on exit. - run/phases.go: phase-boundary checkpointing — record completed phases after each phase; a resumed run skips already-completed phases (the interrupted phase re-runs from its start — boundary-granular, documented; only the single-loop path resumes mid-loop). Battery (checkpoint/): NewFactory wires the battery into the factory port (per-run handle, meta derived from RunInfo); RunCheckpoint + handle.Save carry the phase fields. Tests (run/checkpoint_test.go): the finalize decision matrix; single-loop Save+Complete; terminal-error Fail; resume seeds history; phase-boundary Saves completed phases; resume skips completed phases. Full ./... green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
executus
⚠️ This project is vibe-coded. executus is written almost entirely by an AI coding agent (Claude), with a human steering at the design and review level rather than typing the code. That's a deliberate choice, stated up front — the same way gadfly is. Read the code before you depend on it, pin a version, and file issues if something looks off. It is offered as-is.
A batteries-included base for building LLM agent harnesses in Go. Import it, do a little wiring, and you have agentic capabilities: a bounded run loop, a tool registry with a suite of common tools, context compaction, config-driven model tiering and failover, structured output, and parallel fan-out — with sensible defaults so a brand-new project is agentic with almost no setup, and pluggable seams so a serious host can swap in its own storage, config, delivery, and tools.
executus sits strictly above majordomo — the lean LLM substrate (agent
loop, canonical llm types, providers, media normalization, model parsing /
failover / tiering). majordomo stays the substrate; executus is the opinionated,
batteries-included layer on top. executus requires no changes to majordomo.
Status
Early. Being extracted, phase by phase, from the agent layer of mort (a Discord
bot) — mort and gadfly are the first two consumers (heavy and light). See
CLAUDE.md for the architecture and the extraction roadmap (P0–P6).
Available today:
run/— executus is runnable.run.Executorties model resolution, the tool registry, majordomo's agent loop, context compaction, run-bounding, and step/audit instrumentation into oneRun(ctx, RunnableAgent, inv) Result, with every host concern behind a nil-saferun.Ports(Audit/Budget/Critic/ Checkpointer/PaletteSource/Delivery/InputFiles). Seeexamples/minimal.model/— config-driven tier resolution + failover over majordomo, with pluggableUsageSink/TraceSinkandGenerateWith[T]structured output.tool/— the tool registry + 3-stage permission model + SSRF guard.compact/— the per-run context compactor.lane/— bounded worker pool with fair-share queueing (run- and provider-concurrency).fanout/— programmatic N×M swarm with bounded global + per-key concurrency.config/,deliver/,identity/— host seams (config / output / identity), each with a shipped default.dispatchguard/,pendingattach/— run-safety primitives.examples/reviewer— a gadfly-shaped PR reviewer on the core only (env-config model fleet →fanoutN×M swarm →model.GenerateWith[T]structured findings → consolidation), the light-tier canary; CI asserts it pulls in no battery.
Design
Two tiers in one module (go.mod = majordomo + stdlib only):
- Core — everything a light host needs to be agentic: run loop, tool registry + common tools, model resolution, compaction, lanes, fan-out, structured output. No persistence, no scheduling.
- Batteries (opt-in sibling packages) — persona/agent nouns, saved skills, audit, run-critic, scheduling, budgets, checkpointing. Each is nil-safe and ships a default, so you add only what you use.
Persistence that needs a real database lives in a separate nested module
(contrib/store, pure-Go SQLite) so the core never drags in a DB driver — a
static-binary host (gadfly) stays static.
License
TBD.