From 787b7fb1aed92c2b701724a7741576053b93cccb Mon Sep 17 00:00:00 2001 From: Claude Sonnet 5 Date: Fri, 3 Jul 2026 23:01:50 +0000 Subject: feat(role): add versioned role configs + escalation ladder + scheduler (Phase 5) Two parts: Part A (fixes a gap from Phase 1): Groq/OpenRouter/OpenAI were documented in docs/api-keys-setup.md as usable once configured, but nothing actually constructed runners for them. internal/cli/cloudrunners.go consolidates anthropic/google/groq/openrouter/openai NativeRunner construction into one table-driven registerCloudRunners() helper, replacing the two hand-written per-provider blocks in serve.go/run.go. Groq/OpenRouter/OpenAI reuse openaicompat (no new adapter code) at SandboxKind: "docker". Part B: the token-husbanding harness's core routing mechanism. - internal/role: RoleConfig/Tier/Rung -- a role's system prompt and a multi-tier (provider, model) escalation ladder, versioned via config_json. - storage: new role_configs table (draft/active/retired, UNIQUE(role, version)) with transactional activate-retires-prior-active semantics; new executions.escalation_rung column. - task.AgentConfig.Role string -- purely additive; every existing task shape (Agent.Role == "") is unaffected, proven by TestPool_Execute_NonRoleTask_Unaffected plus the full pre-existing suite passing unchanged. - executor.Pool.execute(): role-typed tasks with no Agent.Type yet resolve tier 0 of their active ladder (round-robin across multi-candidate tiers, skipping rate-limited providers, falling back to soonest-clearing) before the existing pickAgent/Classifier path runs; SystemPrompt applies to Agent.SystemPromptAppend. Already-resolved role tasks (scheduler resubmits) get their escalation_rung re-derived read-only via findTierIndex. - internal/scheduler: polls role-typed FAILED tasks, retries at the same rung under MaxRetries or escalates to the next tier's first candidate when budget.Accountant.Allow() permits (emitting event.KindEscalated), else leaves the task FAILED with a final:true KindEscalated event. An in-memory per-execution-ID "handled" set keeps the poll loop convergent. Started by `serve` only, config knob [scheduler].poll_interval_seconds. - internal/api: POST/GET /api/roles/{role}/versions, POST /api/roles/{role}/activate -- unauthenticated, matching the existing projects/tasks REST endpoints' auth posture (only chatbot MCP, agent MCP, and WebSocket are api_token-gated in this codebase today). Documented as stored-but-not-yet-enforced (CLAUDE.md Design Debt, matching how task.Priority/RetryConfig are already documented): RoleConfig.Tools/ SandboxKind don't affect dispatch yet; DefaultBudgetUSD is read narrowly as the scheduler's escalation cost estimate, not enforced at initial dispatch; scheduler escalation always targets Candidates[0] (no round-robin, unlike initial-dispatch tier-0 resolution); the scheduler's dedupe is per-process and resets on restart (idempotent, harmless). go build/vet/test -race -count=1 all pass, 21 packages. Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs --- internal/cli/serve.go | 63 +++++++++++++++++++-------------------------------- 1 file changed, 23 insertions(+), 40 deletions(-) (limited to 'internal/cli/serve.go') diff --git a/internal/cli/serve.go b/internal/cli/serve.go index 57c2cbd..656ee66 100644 --- a/internal/cli/serve.go +++ b/internal/cli/serve.go @@ -16,9 +16,8 @@ import ( "github.com/thepeterstone/claudomator/internal/config" "github.com/thepeterstone/claudomator/internal/executor" "github.com/thepeterstone/claudomator/internal/notify" - "github.com/thepeterstone/claudomator/internal/provider/anthropic" - "github.com/thepeterstone/claudomator/internal/provider/google" "github.com/thepeterstone/claudomator/internal/provider/openaicompat" + "github.com/thepeterstone/claudomator/internal/scheduler" "github.com/thepeterstone/claudomator/internal/storage" "github.com/thepeterstone/claudomator/internal/version" ) @@ -156,44 +155,10 @@ func serve(addr, basePath string) error { logger.Info("local runner registered", "endpoint", cfg.LocalModel.Endpoint, "model", cfg.LocalModel.Model) } - if pc, ok := cfg.Providers["anthropic"]; ok && pc.APIKey != "" && cfg.Runners.AnthropicEnabled() { - timeout := time.Duration(0) - if pc.TimeoutSeconds > 0 { - timeout = time.Duration(pc.TimeoutSeconds) * time.Second - } - runners["anthropic"] = &executor.NativeRunner{ - Provider: anthropic.New(pc.APIKey, pc.Endpoint, timeout), - Logger: logger, - LogDir: cfg.LogDir, - DefaultModel: pc.DefaultModel, - // Native cloud providers get real container isolation - // (sandbox.DockerSandbox) rather than HostSandbox's host-side - // path-prefix confinement. - SandboxKind: "docker", - SandboxImage: cfg.SandboxImage, - } - logger.Info("anthropic runner registered", "default_model", pc.DefaultModel, "sandbox", "docker") - } - - if pc, ok := cfg.Providers["google"]; ok && pc.APIKey != "" && cfg.Runners.GoogleEnabled() { - timeout := time.Duration(0) - if pc.TimeoutSeconds > 0 { - timeout = time.Duration(pc.TimeoutSeconds) * time.Second - } - runners["google"] = &executor.NativeRunner{ - Provider: google.New(pc.APIKey, pc.Endpoint, timeout), - Logger: logger, - LogDir: cfg.LogDir, - DefaultModel: pc.DefaultModel, - // Native cloud providers get real container isolation - // (sandbox.DockerSandbox) rather than HostSandbox's host-side - // path-prefix confinement — same reasoning as the "anthropic" - // runner above. - SandboxKind: "docker", - SandboxImage: cfg.SandboxImage, - } - logger.Info("google runner registered", "default_model", pc.DefaultModel, "sandbox", "docker") - } + // Native cloud providers (anthropic/google's own wire formats, plus + // groq/openrouter/openai via the OpenAI-compatible adapter) — see + // internal/cli/cloudrunners.go. + registerCloudRunners(runners, cfg, logger, cfg.LogDir) pool := executor.NewPool(cfg.MaxConcurrent, runners, store, logger) pool.Classifier = &executor.Classifier{ @@ -282,6 +247,24 @@ func serve(addr, basePath string) error { srv.SetContext(ctx) srv.StartHub() + // Retry-then-escalate scheduler for role-typed tasks (internal/role, + // internal/scheduler). Only `serve` runs this background loop — the + // one-shot `run` command has no long-lived process to host it in. + sch := &scheduler.Scheduler{ + Store: store, + Pool: pool, + Logger: logger, + } + if accountant != nil { + // Only assign when non-nil: a nil *budget.Accountant boxed into the + // scheduler.BudgetGate interface would be a non-nil interface value + // whose methods panic on the nil receiver — same reason pool.Budget + // above is only ever assigned inside the `if accountant configured` + // branch, never unconditionally. + sch.Budget = accountant + } + go sch.Run(ctx, cfg.Scheduler.PollInterval()) + httpSrv := &http.Server{ Addr: addr, Handler: srv.Handler(), -- cgit v1.2.3