tangle-network · drewstone · Aug 10, 2026 · Aug 10, 2026 · Aug 10, 2026 · Aug 10, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.131.0
+
+- Consume agent-profile-materialize 0.13.1 and Sandbox 0.19.4 with Interface 0.46.1, Eval 0.144.6, and Knowledge 7.1.2.
+- Bind candidate system-prompt launch controls through the native harness plan, including OpenCode's generated primary agent.
+- Keep Codex and Gemini prompt delivery fail-closed, and preserve separate replacement and additive controls for Claude Code, Pi, and Prime.
+
 ## 0.130.0
 
 ### Stability contract + first graduation

diff --git a/README.md b/README.md
@@ -242,7 +242,7 @@ There is no local fallback.
 Install its optional Python process before using it:
 
 ```bash
-python -m pip install "agent-eval-rpc==0.144.4"
+python -m pip install "agent-eval-rpc==0.144.6"
 python -m pip install "gepa[full]==0.1.4"
 ```
 
@@ -256,7 +256,7 @@ python -m pip install "gepa[full] @ git+https://github.com/gepa-ai/gepa.git@f919
 Use `officialSkillOpt(...)` for Microsoft's SkillOpt:
 
 ```bash
-python -m pip install "agent-eval-rpc==0.144.4"
+python -m pip install "agent-eval-rpc==0.144.6"
 python -m pip install "skillopt @ git+https://github.com/microsoft/SkillOpt.git@61735e3922efc2b90c6d6cab561e62e98452ca90"
 ```
 

diff --git a/bench/CHANGELOG.md b/bench/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.8.0
+
+- Consume Runtime 0.131.0, Eval 0.144.6, Interface 0.46.1, Knowledge 7.1.2, and Sandbox 0.19.4 as one compatible dependency set.
+
 ## 0.7.2
 
 - Consume Runtime 0.129.0, Eval 0.144.4, Interface 0.43.1, Knowledge 7.0.11, and Sandbox 0.19.1 so benchmark model calls use the exact-profile execution boundary and the released optimizer callback contract without loading duplicate agent contracts.

diff --git a/bench/package.json b/bench/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-bench",
-  "version": "0.7.2",
+  "version": "0.8.0",
   "type": "module",
   "description": "Benchmark adapters and execution for agent-runtime across coding, tool-use, RAG, memory, browser, and terminal tasks.",
   "repository": {

diff --git a/bench/src/swe-arena/gepa-seat.mts b/bench/src/swe-arena/gepa-seat.mts
@@ -234,7 +234,7 @@ export function innerSmokeJudge(): JudgeConfig<SmokeVerdict, GepaSeatScenario> {
 // ---------------------------------------------------------------------------
 
 export const GEPA_PYTHON_INSTALL_HINT =
-  'install `agent-eval-rpc==0.144.4`, then install ' +
+  'install `agent-eval-rpc==0.144.6`, then install ' +
   '`gepa[full] @ git+https://github.com/gepa-ai/gepa.git@f919db0a622e2e9f9204779b81fe00cc1b2d808f`'
 
 export type GepaMethodFactory = (

diff --git a/docs/api/primitive-catalog.md b/docs/api/primitive-catalog.md
@@ -7,7 +7,7 @@
 
 # Primitive catalog — the never-stale anti-reinvention inventory
 
-> **GENERATED** from `@tangle-network/agent-runtime@0.130.0` and `@tangle-network/agent-eval@0.144.6` by `scripts/gen-primitive-catalog.mjs`. Do NOT hand-edit — run `pnpm run docs:api`. This is the mechanical companion to the JUDGMENT in `canonical-api.md` (§2 decision table + §1.5 AgentProfile law): that doc says WHICH primitive to reach for and what NOT to build; this catalog proves WHAT exists. Per-symbol signatures + `file:line` live in the per-module pages under `docs/api/`.
+> **GENERATED** from `@tangle-network/agent-runtime@0.131.0` and `@tangle-network/agent-eval@0.144.6` by `scripts/gen-primitive-catalog.mjs`. Do NOT hand-edit — run `pnpm run docs:api`. This is the mechanical companion to the JUDGMENT in `canonical-api.md` (§2 decision table + §1.5 AgentProfile law): that doc says WHICH primitive to reach for and what NOT to build; this catalog proves WHAT exists. Per-symbol signatures + `file:line` live in the per-module pages under `docs/api/`.
 
 ## 1. agent-runtime — own public surface
 

diff --git a/docs/canonical-api.md b/docs/canonical-api.md
@@ -4,11 +4,11 @@
 Generated signatures and the complete export list live in docs/api/.
 Run pnpm docs:freshness after editing this file. -->
 
-> **Version 0.130.0.**
+> **Version 0.131.0.**
 > [`docs/api/primitive-catalog.md`](./api/primitive-catalog.md) lists every export and import path.
-> `agent-eval` must satisfy `>=0.144.4 <0.145.0`.
-> `sandbox` must satisfy `>=0.19.1 <0.20.0`.
-> Portable profile and tool-part types come from `@tangle-network/agent-interface` `>=0.43.1 <0.44.0`.
+> `agent-eval` must satisfy `>=0.144.6 <0.145.0`.
+> `sandbox` must satisfy `>=0.19.4 <0.20.0`.
+> Portable profile and tool-part types come from `@tangle-network/agent-interface` `>=0.46.1 <0.47.0`.
 >
 > **`./kernel` is the execution kernel**: `package.json` maps it to `src/runtime/index.ts`. Everything below labelled `/kernel` lives there — the recursive atom (`Scope`/`Supervisor`), the executor registry, budget conservation, the finalizer seam, analyst wiring, and the round-synchronous loop.
 >

diff --git a/examples/coding-benchmark/coding-benchmark.test.ts b/examples/coding-benchmark/coding-benchmark.test.ts
@@ -24,7 +24,7 @@ import { leaderboard } from '@tangle-network/agent-runtime/kernel'
 import { describe, expect, it } from 'vitest'
 import { main, offlineAgentScripts } from './benchmark'
 import { type CheckBox, composeScore, runChecks, runHeldout } from './eval'
-import { harnessProfiles } from './profiles'
+import { harnesses, harnessOf, harnessProfiles } from './profiles'
 import { type CodingScenario, checkCmds, routeCodingFields, scenarios } from './scenarios'
 
 const execAsync = promisify(execCb)
@@ -95,6 +95,11 @@ async function gradeSolution(
 }
 
 describe('coding-benchmark (offline)', () => {
+  it('uses the canonical AgentProfile harness field', () => {
+    expect(harnessProfiles.map((profile) => profile.harness)).toEqual(harnesses)
+    expect(harnessProfiles.map(harnessOf)).toEqual(harnesses)
+  })
+
   // Integration smoke: runs the real matrix end-to-end (real box.exec on the offline
   // toolchain, all refine rounds since the dev checks can't pass without tsc).
   it('runs the full matrix and returns a defined leaderboard', async () => {

diff --git a/examples/coding-benchmark/profiles.ts b/examples/coding-benchmark/profiles.ts
@@ -4,14 +4,13 @@
  * Each profile is deliberately bare (name + model, no skills, no injected prompt) so we
  * measure the HARNESS, not our scaffolding; the tool surface is a separate orthogonal knob
  * (`withTools`), making harness × tool a clean cartesian. Two non-obvious facts about the
- * shape: `AgentProfile` (`@tangle-network/agent-interface`) has no `harness` field (harness
- * is a SANDBOX concept), so the harness selector rides `metadata.harness` (`harnessOf()` is
- * the one reader); and `runProfileMatrix` REQUIRES a snapshot-dated `model.default` — see
- * `harnessModel` below.
+ * shape: `AgentProfile.harness` is the canonical selector, while Sandbox owns validation
+ * that the selected harness is an executable backend; and `runProfileMatrix` REQUIRES a
+ * snapshot-dated `model.default` — see `harnessModel` below.
  */
 
 import type { AgentProfile, AgentProfileMcpServer } from '@tangle-network/agent-interface'
-import type { BackendType } from '@tangle-network/sandbox'
+import { type BackendType, parseBackendType } from '@tangle-network/sandbox'
 
 /** The harnesses we sweep. `cli-base` is the plain-CLI baseline (no agent harness). */
 export const harnesses = [
@@ -21,13 +20,12 @@ export const harnesses = [
   'cli-base',
 ] as const satisfies readonly BackendType[]
 
-/** Read the harness a profile targets. The ONE place metadata.harness is decoded. */
+/** Read and validate the executable harness a profile targets. */
 export function harnessOf(profile: AgentProfile): BackendType {
-  const h = profile.metadata?.harness
-  if (typeof h !== 'string') {
-    throw new Error(`profile "${profile.name}" is missing metadata.harness — see profiles.ts`)
+  if (profile.harness === undefined) {
+    throw new Error(`profile "${profile.name}" is missing harness — see profiles.ts`)
   }
-  return h as BackendType
+  return parseBackendType(profile.harness)
 }
 
 /** The default model each harness runs (override per-harness via env). The model id MUST
@@ -57,8 +55,8 @@ const harnessModel: Record<BackendType, string> = {
 /** One bare baseline profile per harness — the harness's out-of-the-box behavior. */
 export const harnessProfiles: AgentProfile[] = harnesses.map((harness) => ({
   name: `${harness}-baseline`,
+  harness,
   model: { default: harnessModel[harness] },
-  metadata: { harness },
 }))
 
 // ── the tool knob ─────────────────────────────────────────────────────────────

diff --git a/package.json b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-runtime",
-  "version": "0.130.0",
+  "version": "0.131.0",
   "description": "Shared task-lifecycle skeleton for agents: a recursive loop kernel for chat turns, one-shot tasks, and multi-attempt loops, with trace capture and eval-gated self-improvement. Domain behavior lives in adapters; scoring and ship-gates in @tangle-network/agent-eval.",
   "homepage": "https://github.com/tangle-network/agent-runtime#readme",
   "repository": {
@@ -171,7 +171,7 @@
   "peerDependencies": {
     "@tangle-network/agent-eval": ">=0.144.6 <0.145.0",
     "@tangle-network/agent-interface": ">=0.46.1 <0.47.0",
-    "@tangle-network/sandbox": ">=0.19.3 <0.20.0"
+    "@tangle-network/sandbox": ">=0.19.4 <0.20.0"
   },
   "peerDependenciesMeta": {
     "@tangle-network/sandbox": {

diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
diff --git a/pnpm-workspace.yaml b/pnpm-workspace.yaml
@@ -22,9 +22,9 @@ catalog:
   '@tangle-network/agent-eval': 0.144.6
   '@tangle-network/agent-interface': 0.46.1
   '@tangle-network/agent-knowledge': 7.1.2
-  '@tangle-network/agent-profile-materialize': 0.12.0
+  '@tangle-network/agent-profile-materialize': 0.13.1
   '@tangle-network/agent-trace-contract': ^1.0.2
-  '@tangle-network/sandbox': 0.19.3
+  '@tangle-network/sandbox': 0.19.4
   publint: 0.3.22
   tsdown: 0.22.14
   tsx: 4.23.1

diff --git a/src/candidate-execution/prepare.ts b/src/candidate-execution/prepare.ts
@@ -26,10 +26,7 @@ import {
   agentCandidateWorkspaceSnapshotEvidenceSchema,
   sha256DigestSchema,
 } from '@tangle-network/agent-interface'
-import {
-  applyAgentCandidateWorkspacePlan,
-  materializeCandidateProfile,
-} from '@tangle-network/agent-profile-materialize'
+import { applyAgentCandidateWorkspacePlan } from '@tangle-network/agent-profile-materialize'
 
 import {
   readMaterializedWorkspaceFiles,
@@ -63,8 +60,7 @@ import {
 } from './knowledge'
 import { sealAgentCandidateModelSettlement, usdToNanos } from './model-settlement'
 import { createPreparedCandidateExecution } from './prepared-state'
-import { candidateMaterializerHarness } from './profile'
-import { projectCandidateSystemPrompt } from './system-prompt'
+import { materializeAgentCandidateProfilePlan } from './profile'
 import {
   type AgentCandidateExecutionPorts,
   type AgentCandidateTaskExecution,
@@ -109,7 +105,6 @@ export async function prepareAgentCandidateExecution(
     maxAttempts: benchmarkTask.attempt.maxAttempts,
     retryPolicy: benchmarkTask.attempt.retryPolicy,
   } as const
-  const harness = candidateMaterializerHarness(bundle.execution.harness)
   assertTaskInput(task, bundle.execution.instructionDelivery)
   const resultTimeoutMs = candidateResultTimeout(
     options.resultTimeoutMs,
@@ -178,13 +173,14 @@ export async function prepareAgentCandidateExecution(
   }
 
   await assertEmptyDirectory(task.stagingRoots.profileRoot)
-  const profileWorkspacePlan = projectCandidateSystemPrompt(
-    materializeCandidateProfile(bundle.profile, harness, {
-      resolvedResources: verifiedResourceTextByDigest(candidate),
-    }),
-    bundle.execution.launch,
-    profileSystemPromptExecutionPath(bundle.execution.cwd.workspace, task.executionRoots),
-  )
+  const profileWorkspacePlan = materializeAgentCandidateProfilePlan({
+    profile: bundle.profile,
+    harness: bundle.execution.harness,
+    launch: bundle.execution.launch,
+    workspace: bundle.execution.cwd.workspace,
+    workspaces: task.executionRoots,
+    resolvedResources: verifiedResourceTextByDigest(candidate),
+  })
   const profileApplication = applyAgentCandidateWorkspacePlan(
     profileWorkspacePlan,
     task.stagingRoots.profileRoot,
@@ -935,15 +931,6 @@ function absoluteExecutionCwd(
   return absolute
 }
 
-function profileSystemPromptExecutionPath(
-  workspace: VerifiedAgentCandidate['bundle']['execution']['cwd']['workspace'],
-  roots: AgentCandidateTaskExecution['executionRoots'],
-): string {
-  const root = workspace === 'task' ? roots.taskRoot : roots.candidateRoot
-  if (!root) throw new Error('candidate profile target is missing its execution workspace root')
-  return posix.join(root, '.tangle/system-prompt.md')
-}
-
 function validateProtectedModelReservation(
   reservation: {
     preparationId: string