feat(run): single-loop max-steps salvage + enforce MaxToolCalls

Two gaps surfaced by a live fan-out smoke in a downstream host (mort):

1) A single-loop run that exhausts its step budget (ErrMaxSteps / ErrToolLoop)
   returned empty Output + a hard error, discarding all the reasoning it had
   produced — unlike the phased path, which already salvages a partial
   transcript and continues. Add opt-in single-loop salvage
   (Defaults.SalvageSingleLoopMaxSteps, default off): on budget exhaustion with
   empty Output, reconstruct a best-effort answer from the step narration
   (reusing salvagePhaseTranscript) and downgrade the run to a successful
   partial result. Off by default so a structured-output host keeps its clean
   hard error; an interactive host opts in.

2) RunnableAgent carried no tool-call ceiling — MaxIterations bounds STEPS, but
   one step can dispatch several tool calls, so a host's "max tool calls" cap
   had nowhere to land. Add RunnableAgent.MaxToolCalls (<=0 = unlimited,
   backward-compatible): the step observer counts executed calls and, once the
   cap is reached, stepCeilingOption forces the loop to exit; the resulting
   ErrMaxSteps is relabeled to the new ErrMaxToolCalls sentinel. Enforced
   single-loop only for now (phased is a follow-up). A cap hit is budget
   exhaustion, so salvage recovers its partial reasoning too.

isPhaseBudgetExhaustion becomes the shared isBudgetExhaustion (now also matching
ErrMaxToolCalls) so the phased and single-loop paths never drift, and the
RunStateAccessor now reports the real tool-call cap (was hardcoded 0).

Additive + backward-compatible: new optional DTO field, new opt-in Defaults
flag, new exported sentinel; unlimited/off reproduce prior behavior exactly. No
new dependencies (go mod tidy clean). Tests cover salvage on/off/no-prose, cap
enforcement + sentinel, cap+salvage, unlimited no-op, and cap-overrides-critic.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01Q1eJh5NVR11z6RzyxLANMK

run/executor.go

@@ -41,6 +41,17 @@ type Defaults struct {
 	// absolute max. Never shorter than the run's MaxRuntime. Non-critic runs ignore
 	// it (they keep the literal MaxRuntime kill).
 	CriticAbsoluteMax time.Duration
+
+	// SalvageSingleLoopMaxSteps opts a single-loop run into partial-transcript
+	// salvage on budget exhaustion (ErrMaxSteps / ErrToolLoop / ErrMaxToolCalls):
+	// instead of returning empty Output + a hard error and discarding the
+	// reasoning it produced, the executor reconstructs a best-effort answer from
+	// the step narration (like the phased path) and downgrades the run to a
+	// successful partial result. Default false (off): a structured-output host
+	// (e.g. a bounded review swarm) keeps the clean hard error, where partial
+	// prose masquerading as a valid answer would be worse than a loud failure. A
+	// host that wants the reasoning recovered (interactive research) sets it true.
+	SalvageSingleLoopMaxSteps bool
 }
 
 func (d Defaults) withFallbacks() Defaults {
@@ -159,6 +170,7 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 	if maxRuntime <= 0 {
 		maxRuntime = e.cfg.Defaults.MaxRuntime
 	}
+	maxCalls := ra.MaxToolCalls // <= 0 => unlimited (no tool-call ceiling)
 
 	// Budget gate (pre-run): a rejected run makes no model call.
 	if e.cfg.Ports.Budget != nil {
@@ -203,7 +215,7 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 		rec = e.cfg.Ports.Audit.StartRun(ctx, info)
 	}
 	if rec != nil {
-		stateAcc = NewRunStateAccessor(rec, maxIter, 0, started)
+		stateAcc = NewRunStateAccessor(rec, maxIter, maxCalls, started)
 		inv.RunState = stateAcc
 	}
 
@@ -372,6 +384,14 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 	// calls with their executed results PAIRWISE — a result without a matching
 	// call (or a call without a result) is skipped rather than recorded as an
 	// empty-name "ghost" step.
+	// Tool-call budget accounting (single-loop enforcement, RunnableAgent.
+	// MaxToolCalls). The step observer runs on majordomo's Run goroutine — the
+	// SAME goroutine that reads the step ceiling — so plain ints suffice (no
+	// atomics). stepCeilingOption reads these to force the loop to exit once the
+	// cap is reached; the caller then relabels the resulting ErrMaxSteps to
+	// ErrMaxToolCalls. maxCalls <= 0 (unlimited) leaves this inert.
+	var toolCallsSeen, stepsSeen int
+	var capHit bool
 	emitter := newStepEmitter(inv.OnStep)
 	stepObserver := func(s agent.Step) {
 		if stateAcc != nil {
@@ -398,6 +418,21 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 				rec.OnTool(call, r.Content)
 			}
 		}
+		// Tool-call budget: accumulate executed calls and note the crossing once.
+		// Only single-loop runs enforce the cap (phased pipelines are a follow-up),
+		// so gate the crossing detection on Phases to avoid a misleading audit
+		// event on a phased run that merely happens to carry a cap.
+		toolCallsSeen += n
+		stepsSeen = s.Index + 1
+		if len(ra.Phases) == 0 && maxCalls > 0 && toolCallsSeen >= maxCalls && !capHit {
+			capHit = true
+			if rec != nil {
+				rec.LogEvent("max_tool_calls_reached", map[string]any{
+					"max_tool_calls": maxCalls,
+					"tool_calls":     toolCallsSeen,
+				})
+			}
+		}
 	}
 
 	// Shared agent options used by BOTH the single-loop path and every phase: the
@@ -480,7 +515,7 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 		}
 		opts := append([]agent.Option{
 			agent.WithToolbox(toolbox),
-			critic.maxStepsOption(maxIter),
+			critic.stepCeilingOption(maxIter, maxCalls, &toolCallsSeen, &stepsSeen),
 			agent.WithStepObserver(obs),
 		}, sharedOpts...)
 		ag := agent.New(model, e.systemPrompt(ra), opts...)
@@ -492,6 +527,15 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 			runRes, runErr = runAgent(runCtx, ag, input, inv.Images, agent.WithSteer(steer))
 		}
 
+		// A tool-call-cap exit surfaces from majordomo as ErrMaxSteps (we drove
+		// the step ceiling down to force the loop to stop). Relabel it so status,
+		// salvage, and audit report the real cause. A capped step always carries
+		// tool calls (a final-answer turn has zero), so capHit + ErrMaxSteps
+		// pinpoints a cap-triggered exit.
+		if capHit && errors.Is(runErr, agent.ErrMaxSteps) {
+			runErr = fmt.Errorf("%w (max %d)", ErrMaxToolCalls, maxCalls)
+		}
+
 		// ResultSchema (optional): validate the final answer and let the model
 		// self-repair on the same conversation before the host sees it. Runs
 		// BEFORE FinalGuard so the delivery check inspects the answer that will
@@ -570,6 +614,27 @@ func (e *Executor) Run(ctx context.Context, ra RunnableAgent, inv tool.Invocatio
 				}
 			}
 		}
+
+		// Single-loop budget-exhaustion salvage (opt-in). A loop that hit its
+		// step/tool-call budget without composing a final answer returns empty
+		// Output + a hard error, discarding the reasoning it DID produce. Mirror
+		// the phased path: reconstruct a best-effort answer from the step
+		// narration and downgrade the hard error to a successful partial result.
+		// This runs only after a budget error — ResultSchema + FinalGuard above
+		// are gated on runErr == nil, so neither fired. Gated on the host default
+		// so a structured-output host keeps its clean hard error.
+		if e.cfg.Defaults.SalvageSingleLoopMaxSteps &&
+			isBudgetExhaustion(runErr) && runRes != nil &&
+			strings.TrimSpace(runRes.Output) == "" {
+			if salvaged := salvagePhaseTranscript(runRes); salvaged != "" {
+				runRes.Output = salvaged +
+					"\n\n(Note: reached its step budget before composing a final answer; the above is its partial reasoning.)"
+				if rec != nil {
+					rec.LogEvent("single_loop_salvaged", map[string]any{"error": runErr.Error()})
+				}
+				runErr = nil // downgrade: status becomes "ok" and Output is delivered
+			}
+		}
 	} else {
 		// Multi-phase pipeline: each phase runs its own prompt/tier/tools/step-cap
 		// sequentially, threading outputs through {{.<PhaseName>}} templates. The