open-multi-agent-kit 0.99.0 → 1.0.0

package/docs/runtime-algorithms.md

@@ -1,5 +1,49 @@
 # Runtime Algorithms and Direction
 
+## Current feature status (audit §19.3)
+
+"Implemented", "wired", "enabled", "verified in CI", "released", and
+"measured benefit" are different gates. A pure function passing unit tests is
+not a live product path, and a live path is not a measured improvement. This
+table records each mechanism's actual gate at the pinned commit; the dated
+baseline below is history, not current truth.
+
+| Mechanism | Implemented | Wired into live path | Enabled by default | Verified in CI | Released | Measured benefit |
+| --- | --- | --- | --- | --- | --- | --- |
+| DAG claim scheduler (`tool-dag-scheduler`) | yes | `agent-loop` frontier executor | `toolScheduler: "dag-v2"` | unit + integration tests | v0.99.x line | not measured |
+| Ready-frontier admission (`runDagFrontier`) | yes | `agent-loop` | same | `tool-dag-ready-frontier`, `tool-dag-hook-replan` tests | working tree | not measured |
+| Dynamic-claim conflict check (`conflictsWithUnsettledClaim`) | yes | `agent-loop` | same | `tool-dag-dependencies` + hook tests | working tree | not measured |
+| ECRAF admission planner (`tool-dag-ecraf`) | yes | **no** — no call path wires it | n/a | unit tests only | unreleased | not measured |
+| Context Budget V2 | yes | system-prompt assembly | opt-in policy | planner/selection/cache tests | working tree | not measured |
+| Tier floor reservation | yes | context-budget-v2 planner | when V2 enabled | `context-budget-v2-tier-floor` tests | working tree | not measured |
+| Reasoning router v4 | yes | `/think auto` lane | opt-in | router tests | released | classification only, not success-probability calibration |
+| Workload permit pool | yes | resource admission | default | pool tests | released | not measured |
+| Provider retry/failover classification | yes | `provider-retry`, `session-failure-cause` | default | resilience/classification tests | released | not measured |
+| MCP descriptor injection screen | yes | `mcp/manager` import path | default | quarantine tests | released | pattern rule score, not calibrated risk |
+| verified-run coordinator + evidence | yes | verified-run paths | opt-in command | coordinator/evidence tests | working tree | scope-limited binding, not general correctness |
+
+Gates are reported per row so a green "implemented" never upgrades itself to
+"released" or "measured".
+
+## ECRAF arithmetic boundary (2026-09-17)
+
+The internal `planEcrafAdmissions()` planner rejects non-finite derived density
+denominators, scores, and reserved usage with `RangeError`, even when each input
+number is finite. Scores are computed once per candidate before sorting or
+calling the conflict predicate; singleton and zero-slot batches receive the same
+validation. A bounded resource overflow still defers the candidate and allows
+later feasible candidates. An unbounded resource has no capacity limit, but its
+usage must remain representable as a finite number. Failed passes return no
+partial admission plan and do not mutate caller input.
+
+Regression coverage is in
+`packages/agent/test/tool-dag-ecraf-arithmetic.test.ts`; existing numeric and
+property tests remain in `packages/agent/test/tool-dag-ecraf.test.ts`.
+This is local pure-planner validation, not live frontier wiring, CI confirmation,
+a release, or evidence of latency/quality improvement. Resource normalization,
+slot-aware ranking, fairness, and equal-budget runtime comparisons remain separate
+work.
+
 ## Working-tree shared run budgets
 
 The SDK `prompt(..., { runBudget })` path now shares a monotonic deadline and

package/docs/skills.md

@@ -4,7 +4,7 @@
 
 Skills are self-contained capability packages that the agent loads on-demand. A skill provides specialized workflows, setup instructions, helper scripts, and reference documentation for specific tasks.
 
-OMK ships with **no built-in skills** — every skill is user-installed via the locations below, an OMK package, or `--skill`. The default session has zero skills and zero MCP servers configured.
+This source tree includes six public [Neo skills](neo.md) in `resources/neo/skills`. They fill names not supplied by user, project, or explicit skills. `--no-skills` disables automatic loading, while `OMK_BUNDLED_SKILLS=0` disables only the bundled set. Explicit `--skill` paths remain available. Bundled instructions do not install or connect MCP servers; MCP setup remains opt-in. This source integration does not imply that older published packages include Neo.
 
 OMK implements the [Agent Skills standard](https://agentskills.io/specification), warning about most violations but remaining lenient. OMK allows skill names to differ from their parent directory even though the standard disallows it; that rule is suboptimal for shared skill directories used across multiple agent harnesses.
 

package/docs/usage.md

@@ -146,7 +146,8 @@ When the resolved model ID is exactly `gpt-6-astra`, the built-in preset appends
 such as `openai/gpt-6-astra` and `openrouter/openai/gpt-6-astra` match the same
 model. Similar names, dated variants, and other GPT models do not select this
 preset. Select the configured model through `/model`; the preset does not add
-model availability to an account.
+model availability to an account. `--thinking ultra` is a selector alias for
+Astra's documented ceiling `max`; OMK does not send `reasoning.effort: "ultra"`.
 
 The Astra guidance encourages completing authorized work, asking only material
 clarifying questions, explaining any skill instruction that blocks progress,

package/examples/extensions/custom-provider-anthropic/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "omk-extension-custom-provider-anthropic",
-  "version": "0.99.0",
+  "version": "1.0.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omk-extension-custom-provider-anthropic",
-      "version": "0.99.0",
+      "version": "1.0.0",
       "dependencies": {
         "@anthropic-ai/sdk": "0.52.0"
       }

package/examples/extensions/custom-provider-anthropic/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "omk-extension-custom-provider-anthropic",
 	"private": true,
-	"version": "0.99.0",
+	"version": "1.0.0",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/custom-provider-gitlab-duo/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "omk-extension-custom-provider-gitlab-duo",
 	"private": true,
-	"version": "0.99.0",
+	"version": "1.0.0",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/gondolin/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "omk-extension-gondolin",
-	"version": "0.99.0",
+	"version": "1.0.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "omk-extension-gondolin",
-			"version": "0.99.0",
+			"version": "1.0.0",
 			"dependencies": {
 				"@earendil-works/gondolin": "0.12.0"
 			}

package/examples/extensions/gondolin/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "omk-extension-gondolin",
 	"private": true,
-	"version": "0.99.0",
+	"version": "1.0.0",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/sandbox/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "omk-extension-sandbox",
-	"version": "0.99.0",
+	"version": "1.0.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "omk-extension-sandbox",
-			"version": "0.99.0",
+			"version": "1.0.0",
 			"dependencies": {
 				"@anthropic-ai/sandbox-runtime": "0.0.26"
 			}

package/examples/extensions/sandbox/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "omk-extension-sandbox",
 	"private": true,
-	"version": "0.99.0",
+	"version": "1.0.0",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/subagent/adaptive-agent-runtime.ts

@@ -28,6 +28,7 @@ import {
 	remainingExecutionMs,
 } from "./deadline-budget.ts";
 import type { DeadlineProfileStore } from "./deadline-profile-store.ts";
+import type { ManagedProcessResult } from "./managed-process.ts";
 import type {
 	DeadlineAttemptMetadata,
 	DeadlineOutcome,
@@ -99,6 +100,7 @@ export async function runAdaptiveAgent(options: RunAdaptiveAgentOptions): Promis
 	let duplicateResumeBlocked = false;
 	let lastCheckpoint: Awaited<ReturnType<typeof readCheckpoint>> | undefined;
 	let terminalOutcome: DeadlineOutcome = "budget-exhausted";
+	let unsettledProcess: ManagedProcessResult | undefined;
 	const checkpointPrefix = options.checkpointPrefix ?? path.join(os.tmpdir(), "omk-subagent-checkpoint-");
 	const workspace = await createCheckpointWorkspace(checkpointPrefix);
 
@@ -183,7 +185,11 @@ export async function runAdaptiveAgent(options: RunAdaptiveAgentOptions): Promis
 					processReason: attempt.process.reason,
 					cleanup: attempt.process.cleanup,
 				});
-
+				if (attempt.process.terminationObserved === false) {
+					unsettledProcess = attempt.result.process;
+					terminalOutcome = "failed";
+					break outer;
+				}
 				if (outcome === "completed") {
 					completedShardIds.push(shard.id);
 					terminalOutcome = "completed";
@@ -228,6 +234,13 @@ export async function runAdaptiveAgent(options: RunAdaptiveAgentOptions): Promis
 		attempts,
 		...(lastCheckpoint === undefined ? {} : { checkpoint: lastCheckpoint }),
 	};
+	if (unsettledProcess) {
+		aggregate.exitCode = 1;
+		aggregate.stopReason = "unsettled";
+		aggregate.errorMessage = "Subagent termination unconfirmed (unsettled)";
+		aggregate.process = unsettledProcess;
+		return aggregate;
+	}
 	return aggregate;
 }
 

package/examples/extensions/subagent/graph-result.ts

@@ -0,0 +1,48 @@
+import { createHash } from "node:crypto";
+import { emptyUsage, type SingleResult } from "./subagent-runtime-types.ts";
+import type { GraphTask } from "./workflow-graph.ts";
+
+export function failedResult(result: SingleResult): boolean {
+	return (
+		result.process?.terminationObserved === false ||
+		result.exitCode !== 0 ||
+		result.stopReason === "error" ||
+		result.stopReason === "aborted"
+	);
+}
+
+export function laneResult(
+	result: SingleResult,
+): void | { status: "failed" } | { status: "unsettled"; settlement: Promise<void> } {
+	if (result.process?.terminationObserved === false)
+		return { status: "unsettled", settlement: result.process.settlement };
+	if (failedResult(result)) return { status: "failed" };
+}
+
+export function blockedResult(task: GraphTask, reason = "blocked-dependency"): SingleResult {
+	return {
+		nodeId: task.id,
+		agent: task.agent,
+		agentSource: "unknown",
+		task: task.task,
+		exitCode: 1,
+		messages: [],
+		stderr: reason,
+		stopReason: reason,
+		usage: emptyUsage(),
+	};
+}
+
+export function dependencyDigests(
+	task: GraphTask,
+	outputs: ReadonlyMap<string, string>,
+): Readonly<Record<string, string>> {
+	return Object.fromEntries(
+		(task.dependsOn ?? []).map((id) => [
+			id,
+			createHash("sha256")
+				.update(outputs.get(id) ?? "")
+				.digest("hex"),
+		]),
+	);
+}