tangle-network · drewstone · Aug 11, 2026 · Aug 11, 2026 · Aug 11, 2026 · Aug 11, 2026
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -88,14 +88,14 @@ jobs:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           repository: tangle-network/agent-eval
-          ref: 4a848f092064e7e0320c716ff472c3f53446409e # v0.144.10
+          ref: dc592024c3049a677b90f3035fcda883b6efd9f3 # v0.144.12
           path: .cohort/agent-eval
           persist-credentials: false
 
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           repository: tangle-network/agent-knowledge
-          ref: 62dd504f0509d9795011efc8addcfdb6971745b8 # v7.2.0
+          ref: 5c5a9f58e35dc44992e7b8cd99911ef2c99cdd0b # v7.2.1
           path: .cohort/agent-knowledge
           persist-credentials: false
 

diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
@@ -143,15 +143,15 @@ jobs:
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           repository: tangle-network/agent-eval
-          ref: 4a848f092064e7e0320c716ff472c3f53446409e # v0.144.10
+          ref: dc592024c3049a677b90f3035fcda883b6efd9f3 # v0.144.12
           path: .cohort/agent-eval
           persist-credentials: false
 
       - name: Check out exact Knowledge release
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           repository: tangle-network/agent-knowledge
-          ref: 62dd504f0509d9795011efc8addcfdb6971745b8 # v7.2.0
+          ref: 5c5a9f58e35dc44992e7b8cd99911ef2c99cdd0b # v7.2.1
           path: .cohort/agent-knowledge
           persist-credentials: false
 

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,10 @@
 # Changelog
 
+## 0.132.1
+
+- Add `candidatePopulation` to `improve(...)` results so consumers can inspect every verified optimizer candidate, including its exact profile, Interface diffs, parent lineage, and selection score.
+- Consume Agent Eval 0.144.12 and Agent Knowledge 7.2.1 as one compatible dependency set.
+
 ## 0.131.7
 
 - Add `superviseDispatch(...)` so `agent-eval` profile matrices admit and record a recursive Runtime tree before it spends.

diff --git a/README.md b/README.md
@@ -14,6 +14,7 @@ pnpm add @tangle-network/agent-runtime @tangle-network/agent-eval @tangle-networ
 - [Quickstart](#quickstart-offline-no-api-keys)
 - [What you do with it](#what-you-do-with-it)
 - [Run a chat turn](#run-a-chat-turn)
+- [Retain and reconnect a run](#retain-and-reconnect-a-run)
 - [Supervise a team of agents](#supervise-a-team-of-agents)
 - [Improve an agent](#improve-an-agent)
 - [Improve a knowledge base](#improve-a-knowledge-base)
@@ -115,6 +116,42 @@ return new Response(result.body, { headers: { 'content-type': result.contentType
 For a stream reconnect, call `streamPrompt` with the same `executionId` and the last event id the client received.
 For a repeated initial dispatch, reuse both `sessionId` and `turnId`; `executionId` alone is not an idempotency key.
 
+### Retain and reconnect a run
+
+Use the retained-run API when the provider owns a job that must outlive one HTTP reader or application process.
+The provider must advertise exact run identity, replay, result identity, and idempotent cancellation.
+
+```ts
+import { reconnectRetainedRun, startRetainedRun } from '@tangle-network/agent-runtime'
+
+const run = await startRetainedRun({
+  provider,
+  environment: { idempotencyKey: 'workspace-42', profile },
+  turn: { turnId: 'turn-7', prompt: 'Finish the migration and run its tests.' },
+  identity: { sessionId: 'thread-42', executionId: 'execution-7' },
+})
+
+await journal.write(run.controlRef)
+
+for await (const event of run.events()) {
+  await journal.write(event)
+}
+
+const recovered = await reconnectRetainedRun({
+  provider: freshProvider,
+  controlRef: await journal.readControlRef(),
+})
+if (!recovered) throw new Error('the provider no longer retains this environment')
+
+const snapshot = await recovered.status({ waitMs: 30_000 })
+const result = await recovered.result()
+```
+
+Persist `controlRef` before acknowledging dispatch to the caller.
+Persist each event cursor and sequence before advancing the visible transcript.
+`reconnectRetainedRun` reconstructs a client from those values and rejects any provider, environment, session, execution, run, or digest mismatch.
+An unknown provider result remains unknown; the runtime never converts it into success or confirmed cancellation.
+
 ### Supervise a team of agents
 
 One supervisor spawns and steers workers toward a goal. Where the workers run (an in-process loop, or a sandboxed coding harness) is one data value; the budget, journaling, and stopping are handled for you.
@@ -238,11 +275,15 @@ With `resume: 'if-compatible'`, agent-eval resumes only when the saved run ident
 Set `trustResumeState: true` only when that run directory is private to the current operator.
 Use `resume: 'required'` to fail when no matching run exists.
 `result.provenance` reports the upstream package, run ID, resume status, evaluation count, and artifact directory.
+`result.candidatePopulation` verifies and joins callback observations with an optimizer's official candidate graph.
+It returns every unique candidate as a complete profile with ordered Interface diffs, or as an explicit materialization refusal.
+GEPA candidates retain exact parent indices and selection scores; callback-only proposals report lineage as unavailable.
+Methods without either artifact return `status: 'unavailable'` instead of treating the winner as the full population.
 There is no local fallback.
 Install its optional Python process before using it:
 
 ```bash
-python -m pip install "agent-eval-rpc==0.144.8"
+python -m pip install "agent-eval-rpc==0.144.12"
 python -m pip install "gepa[full]==0.1.4"
 ```
 
@@ -256,7 +297,7 @@ 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==0.144.8"
+python -m pip install "agent-eval-rpc==0.144.12"
 python -m pip install "skillopt @ git+https://github.com/microsoft/SkillOpt.git@61735e3922efc2b90c6d6cab561e62e98452ca90"
 ```
 
@@ -490,6 +531,7 @@ The general-purpose pieces, by import path. Every export with its one-line summa
 | Primitive | What it does | Import |
 |---|---|---|
 | Chat-turn runtime | Stream and persist one production chat turn (`handleChatTurn`); derive its stable execution and turn identity (`deriveExecutionId`); normalize any backend's stream into one event shape (`streamAgentTurn`) | `/durable` · `/kernel` |
+| Retained provider runs | Start one detached provider job, replay exact events, reconnect after restart, continue its native context, and cancel idempotently (`startRetainedRun`, `reconnectRetainedRun`) | root |
 | Tool-call loop | Run one model turn, execute requested tools, feed results back, and stop on completion, repetition, time, or cost limits (`runToolLoop`, `streamToolLoop`) | `/tool-loop` |
 | Supervision | One agent spawns, budgets, and steers workers toward a goal (`supervise`, `delegate`), on an in-process loop or a sandboxed coding harness | `/kernel` · `/mcp` |
 | Loop kernel + combinators | Write a driver (`plan`/`decide`) and run it (`runAgentRounds`), or compose fixed shapes: refine (`loopUntil`), best-of-N (`fanout`), chain (`pipeline`), multi-judge (`panel`) | `/kernel` |

diff --git a/bench/CHANGELOG.md b/bench/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.8.3
+
+- Consume Runtime 0.132.1, Eval 0.144.12, and Knowledge 7.2.1 as one compatible dependency set.
+
 ## 0.8.2
 
 - Consume Runtime 0.131.7, Eval 0.144.10, and Knowledge 7.2.0.

diff --git a/bench/package.json b/bench/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-bench",
-  "version": "0.8.2",
+  "version": "0.8.3",
   "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==0.144.10`, then install ' +
+  'install `agent-eval-rpc==0.144.12`, then install ' +
   '`gepa[full] @ git+https://github.com/gepa-ai/gepa.git@f919db0a622e2e9f9204779b81fe00cc1b2d808f`'
 
 export type GepaMethodFactory = (