4aa06f652e
executus CI / test (pull_request) Failing after 58s
From PR #9 (minimax + deepseek): - Run now has a top-level recover() — the "never propagates a panic" promise was unenforced; a panicking host Port (Critic/Audit/Palette) on the run goroutine now becomes Result.Err instead of unwinding into the caller. - The critic deadline-watch goroutine recovers panics from a host Deadline() (it's a separate goroutine, so Run's recover can't catch it) — a buggy CriticHandle can't crash the process. - CriticHandle interface documents its concurrency contract (Record*/Steer on the run goroutine vs Deadline()/Stop() from the watch goroutine — impls must be concurrent-safe; the critic battery already is). - startCritic's dead `soft <= 0 -> noop` guard (withFallbacks already coerces to 90s) replaced with a defensive inline 90s default, so a bypass of withFallbacks still gets a working critic instead of silently none. - Delivery tests made honest: the old "error path" test only checked the early-return (no delivery); added TestDeliverErrorOnRunFailure (in-loop model error -> DeliverError to the target) + renamed the early-return test. Graded all #9 findings in the gadfly MCP. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
174 lines
6.9 KiB
Go
174 lines
6.9 KiB
Go
package run
|
|
|
|
import (
|
|
"context"
|
|
"time"
|
|
|
|
"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
|
|
|
|
"gitea.stevedudenhoeffer.com/steve/executus/deliver"
|
|
)
|
|
|
|
// Ports are the host seams the run executor consumes. Every field is nil-safe:
|
|
// a light host passes the zero Ports and gets a bounded, in-memory run with no
|
|
// persistence, audit, budget, critic, delegation, or delivery — which is
|
|
// exactly a gadfly swarm task. A heavy host (mort) wires each one to a battery.
|
|
//
|
|
// This struct IS the inversion: in mort, agentexec imports agents /
|
|
// agentcritic / skillaudit and skillexec imports skills / paste directly; here
|
|
// the kernel depends only on these interfaces, and the batteries implement
|
|
// them. The mort_*_adapters.go wall becomes the set of impls.
|
|
type Ports struct {
|
|
// Audit records the run trace (start, per-step/per-tool events, final
|
|
// stats). nil = no audit.
|
|
Audit Audit
|
|
// Budget gates and meters per-caller resource use. nil = unbounded.
|
|
Budget Budget
|
|
// Critic optionally monitors a long run for hangs/runaways. nil = none.
|
|
Critic Critic
|
|
// Checkpointer persists resumable progress for durable recovery. nil = no
|
|
// checkpointing (a run interrupted by shutdown is simply lost).
|
|
Checkpointer Checkpointer
|
|
// Palette resolves SkillPalette / SubAgentPalette entries into delegation
|
|
// tools (skill__<name> / agent__<name>). nil = those entries are inert.
|
|
Palette PaletteSource
|
|
// Delivery is where the run's output + artifacts go. nil = the caller
|
|
// reads the Result in-process (the light-host default).
|
|
Delivery deliver.Delivery
|
|
}
|
|
|
|
// RunInfo describes a run at start time — the attribution a recorder/critic
|
|
// needs. Host-neutral rename of mort's SkillRun start fields.
|
|
type RunInfo struct {
|
|
RunID string
|
|
SubjectID string // the agent/skill id being run (audit "skill_id")
|
|
Name string
|
|
CallerID string
|
|
ChannelID string
|
|
ParentRunID string
|
|
Inputs map[string]any
|
|
StartedAt time.Time
|
|
}
|
|
|
|
// RunStats is the terminal roll-up a recorder's Close writes. Mirrors mort's
|
|
// skillaudit/skillexec RunStats.
|
|
type RunStats struct {
|
|
Status string // ok | error | timeout | budget_exceeded | cancelled | dry_run
|
|
Output string
|
|
Error string
|
|
ToolCalls int
|
|
RuntimeSeconds float64
|
|
InputTokens int64
|
|
OutputTokens int64
|
|
ThinkingTokens int64
|
|
}
|
|
|
|
// --- Audit ---
|
|
|
|
// Audit begins recording a run. StartRun returns a per-run RunRecorder (or nil
|
|
// to skip recording this run). The audit battery wires its Storage behind this.
|
|
type Audit interface {
|
|
StartRun(ctx context.Context, info RunInfo) RunRecorder
|
|
}
|
|
|
|
// RunRecorder records the events of one in-flight run and its final stats. It
|
|
// satisfies RunTally so the kernel can surface live token/tool counts to the
|
|
// self-status tool. Mirrors mort's skillaudit.Writer.
|
|
type RunRecorder interface {
|
|
RunTally
|
|
// OnStep records one completed agent-loop iteration's model response.
|
|
OnStep(iter int, resp *llm.Response)
|
|
// OnTool records one executed tool call + its result.
|
|
OnTool(call llm.ToolCall, result string)
|
|
// LogEvent / LogError append structured events to the run log.
|
|
LogEvent(eventType string, payload map[string]any)
|
|
LogError(msg string)
|
|
// Close writes the terminal roll-up. Detaches from the caller's context
|
|
// internally so a cancelled run still records.
|
|
Close(ctx context.Context, stats RunStats)
|
|
}
|
|
|
|
// --- Budget ---
|
|
|
|
// Budget gates and meters per-caller resource use. Mirrors mort's
|
|
// skillexec.BudgetTracker.
|
|
type Budget interface {
|
|
// Check reports whether the caller has remaining budget (nil = allowed).
|
|
Check(ctx context.Context, callerID string) error
|
|
// Commit records that the caller spent runtimeSeconds on this run.
|
|
Commit(ctx context.Context, callerID string, runtimeSeconds float64)
|
|
}
|
|
|
|
// --- Critic ---
|
|
|
|
// Critic optionally monitors a long-running run (the two-tier soft/hard
|
|
// timeout). Monitor returns a handle the executor feeds progress into and
|
|
// queries for steer/deadline decisions; a nil handle means "not monitored".
|
|
//
|
|
// The exact wiring (how the handle's Steer/Deadline bind into majordomo's
|
|
// agent.WithSteer / agent.WithMaxStepsFunc / run-context cancellation) is
|
|
// finalized in the executor; this is the seam the agentcritic battery adapts.
|
|
type Critic interface {
|
|
Monitor(ctx context.Context, info RunInfo, softTimeout time.Duration) CriticHandle
|
|
}
|
|
|
|
// CriticHandle is the executor's live link to a run's critic.
|
|
//
|
|
// Concurrency: the executor calls RecordStep/RecordToolStart/Steer from the run
|
|
// goroutine while a separate watch goroutine polls Deadline() and the run's end
|
|
// calls Stop() — so implementations MUST be safe for concurrent use across these
|
|
// methods (the critic battery's handle guards its state with a mutex).
|
|
type CriticHandle interface {
|
|
// RecordStep / RecordToolStart keep the critic's activity clock fresh so a
|
|
// healthy-but-slow run is not mistaken for a hang.
|
|
RecordStep(iter int)
|
|
RecordToolStart(name, args string)
|
|
// Steer returns any messages the critic wants injected into the loop (a
|
|
// nudge), drained before each step — matches majordomo agent.WithSteer.
|
|
Steer() []llm.Message
|
|
// Deadline returns the current hard-kill deadline (the critic may extend
|
|
// it); the executor binds the run context to it. Zero = no hard deadline.
|
|
Deadline() time.Time
|
|
// Stop ends monitoring when the run finishes.
|
|
Stop()
|
|
}
|
|
|
|
// --- Checkpointer ---
|
|
|
|
// Checkpointer persists a run's resumable progress for durable recovery.
|
|
// Mirrors mort's agentexec.RunCheckpointer.
|
|
type Checkpointer interface {
|
|
// Save persists the run's current resumable progress (throttled).
|
|
Save(ctx context.Context, st RunCheckpointState) error
|
|
// Complete clears the checkpoint on success.
|
|
Complete(ctx context.Context) error
|
|
// Fail clears the checkpoint on terminal failure. A run interrupted by
|
|
// shutdown is left untouched so boot recovery picks it up.
|
|
Fail(ctx context.Context, err error) error
|
|
}
|
|
|
|
// RunCheckpointState is the resumable snapshot a Checkpointer persists. Kept
|
|
// minimal here; the executor extends what it records during the merge.
|
|
type RunCheckpointState struct {
|
|
Messages []llm.Message
|
|
Iteration int
|
|
}
|
|
|
|
// --- PaletteSource ---
|
|
|
|
// PaletteSource resolves a RunnableAgent's SkillPalette / SubAgentPalette names
|
|
// into delegation tools and invokes them. Mirrors mort's
|
|
// SkillInvokerForPalette + AgentInvokerForPalette. nil Palette => palette
|
|
// entries are inert ("not configured" at first call).
|
|
type PaletteSource interface {
|
|
ResolveSkill(ctx context.Context, callerID, name string) (skillID string, err error)
|
|
InvokeSkill(ctx context.Context, callerID, channelID, name string,
|
|
inputs map[string]any, parentRunID string) (output, runID, status string, err error)
|
|
|
|
ResolveAgent(ctx context.Context, callerID, name string) (agentID string, err error)
|
|
InvokeAgent(ctx context.Context, callerID, channelID, name string,
|
|
prompt, parentRunID, modelTierOverride, promptPrepend string,
|
|
toolsSubset []string,
|
|
onEvent func(ctx context.Context, event, emoji string)) (output, runID, status string, err error)
|
|
}
|