open-multi-agent-kit 0.98.4 → 0.99.0

package/docs/metrics.md

@@ -160,7 +160,7 @@ node scripts/tb-mini-suite.mjs --json      # feed a runner
 node scripts/tb-mini-suite.mjs --seed 7    # a different fixed subset
 ```
 
-With identical task metadata, seed, size, and collation, selection is repeatable.
+With identical task metadata, selection version, seed, size, and collation, selection is repeatable.
 The default 15-task subset oversamples easy tasks and prioritizes shorter expert
 time estimates; it is a regression signal, not a population-representative score
 or an agent runtime bound. Selection alone is not a capability result. Scoring
@@ -171,12 +171,35 @@ population. Missing difficulty quotas are filled from unselected tasks using the
 same ordering, so a valid request returns exactly that many distinct tasks.
 `--seed` accepts integers from `0` through `4294967295`. Invalid or missing option
 values and oversized requests exit with code `2`; absent, empty, or non-directory
-task paths exit with code `1`. The existing default subset remains unchanged.
+task paths exit with code `1`.
+
+The JSON output now declares `selectionVersion: 2`. Missing, empty, nonfinite, or
+negative expert-time estimates are `null`, not zero. Within each difficulty band
+and in quota refill, known estimates sort before unknown estimates. A genuine zero
+or fractional estimate remains valid. Difficulty quotas still take precedence, so
+unknown-estimate tasks can be selected to fill a band.
+
+`knownExpertMinutes` sums known estimates; `unknownExpertEstimates` counts selected
+tasks with unknown estimates. `totalExpertMinutes` is `null` when any selected
+estimate is unknown. A nonfinite sum is refused with exit `1`, not serialized as
+an apparently missing total. Expert estimates are not agent timeout limits.
+
+For sizes 1–2, available slots go first to the highest-weight difficulty bands
+(medium, then hard), with normal refill if those bands are unavailable. Task names
+no longer decide which excess band quota is discarded. The normal-size quota rule
+is preserved. Human-readable counts use a `Map`, including for labels such as
+`__proto__` that overlap JavaScript object properties.
+
+This is a selection and output-contract change: default membership can change when
+metadata is incomplete, and the prior default JSON digest is historical only.
+Freeze new task manifests before comparison; do not combine version 1 and 2 runs
+as if their selection policy were identical. The limited flat TOML field reader
+is unchanged; this does not add general TOML syntax support.
 
 Run the offline CLI regression tests without downloading tasks or calling models:
 
 ```bash
-node --test scripts/test/tb-mini-suite.test.mjs
+node --test --test-concurrency=1 scripts/test/tb-mini-suite.test.mjs scripts/test/tb-mini-suite-ranking.test.mjs
 ```
 
 See [the harness roadmap](../../../ROADMAP.md) for the dated OMK versus Terminus-2
@@ -187,8 +210,8 @@ criteria. Planned runtime improvements are not measured benchmark gains.
 
 The checkout-only `scripts/tb21-audit.mjs` audits explicitly selected Harbor jobs
 against a caller-pinned manifest digest. It rejects duplicate tasks/trials, missing
-results or costs, mismatched task checksums or configured model labels, and
-contradictory success records. It never starts a model, picks the latest job, joins
+results or costs, mismatched task checksums or configured model labels,
+missing/invalid completion times, and contradictory success records. It never starts a model, picks the latest job, joins
 requests by timestamp, or rewrites evidence. See [TB 2.1 offline audit](tb21-audit.md)
 for the schema, invocation, error codes, and limitations.
 
@@ -196,14 +219,32 @@ A complete audit means recorded outcomes passed these checks, not that every
 provider request obeyed a single-model contract. Wire provenance, actual billing,
 repeated-trial analysis, and statistical superiority need separate evidence.
 
-### Explicit output-limit validation
-
-For callers that supply `AgentLoopConfig.modelContract`, both the contract's
-`maxOutputTokens` and an explicitly supplied request `maxTokens` must be positive
-safe integers. Invalid explicit values are refused before `provider_request` and
-before calling the provider stream function; they are not treated as absent.
-
-An omitted request limit still leaves provider defaults unchecked by this
-predicate. This change does not activate a contract in the CLI or impose an
-effective cap on compaction and other provider paths. Full run-wide enforcement
-remains a roadmap item.
+### Output-limit validation: availability history
+
+**2026-09-13 source snapshot (`ca75f4e5cc`):** the logical contract, CLI/SDK
+wiring, and final Chat Completions model/output-limit checks are in the committed
+source. [Model dispatch contracts](model-contract.md) defines their coverage;
+[Verified Run](verified-run.md) describes the separate protected execution path.
+Neither is a universal provider billing cap or a new controlled benchmark result.
+See [the roadmap, section 16](../../../ROADMAP.md) for current local release-preparation checks.
+
+The following paragraphs describe the earlier checkout only. Its missing modules
+and failing collection are historical observations, not active release blockers.
+
+**2026-09-08 follow-up:** the current worktree restores the logical contract and
+connects it through the CLI/SDK, including SDK-stream summaries. See
+[Model dispatch contracts](model-contract.md) and ROADMAP §13 for fresh evidence
+and the remaining final-wire/accounting gaps. The warning below records the
+preceding checkout, not the current availability of the restored module.
+
+The previous worktree checkpoint tested positive-safe-integer validation of
+`modelContract.maxOutputTokens` and explicit request `maxTokens`. During the
+2026-09-08 re-verification, the checkout changed: `run-model-contract.ts` and the
+corresponding `AgentLoopConfig.modelContract` surface were absent. The remaining
+`model-contract-output-limit.test.ts` fails collection against that checkout.
+
+Do not treat the historical passing tests as proof that this guard is currently
+available. Restoring or porting the runtime contract requires an explicit source
+baseline decision and fresh send-boundary tests. No missing code was silently
+recreated and no failing test was deleted. Full run-wide enforcement, including
+omitted limits and compaction, remains unverified; see ROADMAP sections 11–12.

package/docs/providers.md

@@ -19,6 +19,7 @@ Use `/login` in interactive mode, then select a provider:
 - Claude Pro/Max
 - GitHub Copilot
 - xAI Grok subscription OAuth
+- Devin CLI subscription (SWE-2)
 
 Run `/login` and choose a configured subscription provider to open its account picker. Select an existing account by its ChatGPT, Claude, or Google email when available, or choose **Add another account** to sign in with a new one. OMK keeps and refreshes each account independently, pins the provider to the account you select, and does not silently fail over to another subscription. `/model` remains dedicated to model selection.
 
@@ -67,6 +68,80 @@ and [plan endpoint separation](https://www.alibabacloud.com/help/en/model-studio
 consulted 2026-09-08. The local tests exercise serialization, not account availability,
 provider compliance, billing, or benchmark performance.
 
+### Devin CLI
+
+Run `/login devin`, select `devin/swe-2`, and use `/think medium`, `/think high`,
+or `/think max`. For a new session after login:
+
+```bash
+omk --provider devin --model swe-2 --thinking max
+```
+
+The default is `medium`. Thinking-off and other levels are unsupported. `max`
+is a reasoning level, not a requirement to buy the Devin Max subscription tier.
+Your account's model access and quota still apply. For presets, effort guidance,
+the 1M-token context budget, and the `devin-harness` loadout, see the
+[Devin SWE-2 harness](devin-harness.md).
+
+**Authentication.** OMK uses the CLI's PKCE flow at
+`app.devin.ai/auth/cli/continue` and `api.devin.ai/auth/cli/token`. Its callback
+binds only to `127.0.0.1:59653`, validates state, and closes after success,
+rejection, cancellation, or a five-minute deadline. If the port is occupied,
+paste the complete callback URL into OMK's local prompt. For remote sessions,
+forward this loopback port to the machine running OMK.
+
+Credentials use the existing protected `auth.json` storage and account picker.
+Expired sessions require `/login devin` again: no refresh endpoint is verified,
+and OMK does not renew the expiry locally. Use `/logout` to remove the stored
+OMK credential. Alternatively, `DEVIN_API_KEY` accepts an already-owned CLI
+session token, **not** a `cog_` REST API key. OMK does not install or invoke the
+Devin agent, read browser cookies, or import another application's credentials.
+
+**Transport and limits.** The Node-only `devin-agent` adapter uses Connect/protobuf
+at the fixed HTTPS origin `https://server.codeium.com`. It exchanges the session
+token for a user JWT and reads `GetCliModelConfigs` before each turn. The server's
+SWE-2 family metadata supplies the effort's exact wire UID; OMK never invents a
+`swe-2-max` ID or downgrades an unavailable route. Disabled, internal, ambiguous,
+and fast-lane entries are excluded. The family's separate 1M-context entries form
+a second lane that is selected only when the model's local `contextWindow` is
+1,000,000 or more (the bundled default); a smaller budget uses the standard lane.
+
+Text, thinking, tool calls/results, and reported usage enter the normal OMK
+agent loop. Image input and enterprise-origin overrides are unsupported.
+Requests reject redirects. Malformed, oversized, or unterminated streams fail;
+remote error bodies are not copied into diagnostics. SDK `onPayload` receives
+protobuf bytes without credential metadata.
+
+The bundled 1,000,000-token context budget and 16,384-token output cap are
+local defaults, **not published SWE-2 limits**. Output is further capped against
+the authenticated catalog. If the selected lane declares a smaller context window,
+the request fails and names the window; lower `contextWindow` through
+`modelOverrides` in [models.json](models.md#per-model-overrides) rather than
+expecting a silent downgrade. Zero catalog pricing means unpriced subscription
+usage, not free inference. Quota percentages are not inferred.
+
+**Account quota.** With a Devin credential configured, the status rail's USAGE
+section calls `SeatManagementService/GetUserStatus` (session-token metadata, no
+user JWT) and renders the plan's daily and weekly quota meters with reset times.
+Accounts whose plan reports no quota windows show the plan name and credit
+balances instead. The rail mirrors the CLI's `/usage` surface; it never sends
+the session token anywhere except `server.codeium.com`.
+
+**Verification.** Local tests exercise the public stream API, real loopback
+callbacks with mocked token exchange, model selection, and protocol fixtures.
+Live login, catalog compatibility, SWE-2 inference, and billing remain unverified
+without a Devin account. Unauthenticated catalog probes returned HTTP 400.
+Live tests require `DEVIN_API_KEY` and `LIVE_E2E=1` and consume subscription quota.
+
+Sources consulted 2026-09-12 and 2026-09-13: the [SWE-2 announcement](https://cognition.com/blog/swe-2)
+(2026-09-10; CLI availability and medium/high/max; no published context window), [CLI commands](https://docs.devin.ai/cli/reference/commands),
+and the [official manifest](https://static.devin.ai/cli/current/manifest.json)
+(observed identity `3000.10.21`). Protocol fields follow the third-party
+[oh-my-pi snapshot](https://github.com/can1357/oh-my-pi/blob/942383f768c5f2f6a620fcab57326c0f59df623a/packages/catalog/src/discovery/devin-proto.ts),
+not a stable public inference contract; attribution is in `packages/ai/DEVIN-NOTICE`.
+Regenerate only this logical model, preserving every other catalog entry, with
+`npm --prefix packages/ai run generate-models -- --devin-only`.
+
 ### OpenAI Codex
 
 - Requires ChatGPT Plus or Pro subscription
@@ -111,6 +186,7 @@ omk
 | Azure OpenAI Responses | `AZURE_OPENAI_API_KEY` | `azure-openai-responses` |
 | OpenAI | `OPENAI_API_KEY` | `openai` |
 | DeepSeek | `DEEPSEEK_API_KEY` | `deepseek` |
+| Devin CLI session token | `DEVIN_API_KEY` | `devin` |
 | NVIDIA NIM | `NVIDIA_API_KEY` | `nvidia` |
 | Google Gemini | `GEMINI_API_KEY` | `google` |
 | Mistral | `MISTRAL_API_KEY` | `mistral` |

package/docs/release-audit-0.98.5.md

@@ -0,0 +1,101 @@
+# Release audit: v0.98.5
+
+Date: 2026-09-12. This records candidate preparation and verification, not proof of
+semantic correctness, comparative performance or completed publication.
+
+## Scope and changelog audit
+
+The candidate retains the public v0.98.4 ancestry and the committed implementation
+range through `b84d0d9b8e`. The audit covers index-preserving Git checks, execution
+ownership/shared budgets, protected verified runs and candidate recovery, input
+checkpoint writer restart, static DAG retry, and TUI diagnostics. Tool timeout
+messages now distinguish requested cancellation from observed termination and use
+a monotonic teardown grace period.
+
+Preparation adds release metadata, this audit, and focused verification fixes:
+initial failure-card expansion is applied at construction, execution wrappers
+preserve lazy context-sensitive timeouts, and the commit hook handles changed-file
+status under Husky's errexit mode. Existing dirty provider, retry,
+parallel-frontier, resource-label and TB changes are excluded.
+Their working files are preserved, and their pending changelog entries stay out of
+the candidate. Published v0.98.4 and earlier changelog bodies remain unchanged.
+Model catalogs are reused rather than fetched or regenerated. Credentials, private
+agent-home configuration and the user's running TUI are not changed.
+
+## Version and artifact contract
+
+All seven public packages target 0.98.5: `open-multi-agent-kit`, `omk-ai`,
+`omk-agent-core`, `omk-tui`, `omk-protocol`, `omk-adaptorch-wpl` and
+`omk-book-to-skill`. Root/example manifests and locks, internal dependency ranges,
+the book compiler's source version constant, CLI shrinkwrap and README pointers
+are synchronized. External dependency versions and integrity values are unchanged.
+
+The release candidate is selected by path/hunk and inspected as a complete staged
+diff. Verification uses an isolated candidate, not the mixed working tree. Temporary
+homes contain no provider credentials; live inference and benchmarks are not run.
+
+## Observed verification
+
+- The diagnostics implementation passed type checking and 104 focused tests in its
+  staged snapshot. Its canonical installed launcher passed offline 120/80-column
+  inspection, save, failure, reload and quit checks without model prompts.
+- Version preparation passed 13-manifest/root-lock parity, source-version tests,
+  book metadata tests and the canonical `omk --version` check for 0.98.5.
+- The isolated candidate build and `npm run check` exited 0. Module-size and
+  import-cycle baselines were not raised.
+- The final full offline run exited 0: 8,181 passed, 837 environment/live-condition
+  skips, no failures. Package passes were WPL 149, agent 870, AI 631, book compiler
+  22, coding-agent 5,653, protocol 126 and TUI 730. Vitest workers were bounded at
+  four; the TUI package used its Node test runner.
+- Seven-package npm pack dry runs and release-surface checks passed. They checked
+  package version/file metadata without publication or lifecycle scripts.
+- Gitleaks found no leaks in the staged changes or the six implementation commits
+  since v0.98.4. Reports were redacted; this is not clearance for private histories
+  outside that range.
+
+## Verification repairs
+
+The isolated candidate exposed a two-line module-size overrun that the mixed tree
+hid. Passing initial expansion to the failure-card constructor avoids a redundant
+rebuild and keeps the existing size baseline; both initial states are tested.
+
+The full suite exposed an execution wrapper spreading a tool's dynamic timeout
+getter into a fixed value. The wrapper now projects tool metadata and forwards
+that getter lazily. Regression checks cover no eager evaluation, timeout changes,
+stale-context rejection and retained execution metadata.
+
+The commit hook had only been tested under plain `sh`, while Husky invokes `sh -e`.
+A changed-file `git diff --quiet` status of 1 therefore stopped valid release
+commits. Capturing that status in an OR-list preserves errexit for real failures;
+all six hook fixtures now run under `sh -e`, including changed paths with spaces,
+index preservation and a fatal git-diff error.
+
+An initial test launch resolved to the wrong checkout and was cancelled, not counted
+as candidate evidence. Subsequent launches fix both process cwd and npm prefix.
+An isolated HOME also hid the installed Rust toolchain: explicitly supplying its
+location restored the real cargo diagnostic check without changing the test or
+copying credentials. Neither fixture failure was treated as a product pass.
+
+## CI environment recovery
+
+The first v0.98.5 tag run built the binaries, but its test step could not find
+`/usr/bin/bwrap`. npm publication was not attempted and GitHub Release creation
+was skipped. The default-branch CI workflows now install `bubblewrap` and run an
+unprivileged namespace probe before the suite. Ubuntu 24.04 subsequently refused
+loopback setup inside the namespace. The runtime-test jobs are pinned to Ubuntu
+22.04 LTS, with the same namespace and capability-drop checks. They do not skip
+verified-run tests, disable host security controls or enable a sandbox fallback.
+The older distribution `fd` lacked `--no-require-git`; CI installs the official
+fd 10.4.2 static archive with SHA-256 verification before extraction and probes
+that option before tests. File-search behavior and tests are not weakened.
+
+Recovery dispatches the official workflow from `main` with both `tag` and
+`source_ref` fixed to `v0.98.5`. The release tag and its source commit stay unchanged;
+the existing source/tag equality checks remain mandatory.
+
+A source-file fingerprint is not an executed-build attestation. Linux observations
+do not establish behavior on every target platform. CI must validate the exact tag,
+build the six platform archives, run checks/tests, publish all seven npm packages
+and create the GitHub Release. Existing token-based CI authentication is unchanged;
+OIDC/Sigstore provenance is not claimed. Publication is complete only when the main
+tag, GitHub Release and seven npm `latest` values agree.

package/docs/release-audit-0.99.0.md

@@ -0,0 +1,68 @@
+# Release audit: v0.99.0
+
+기준일: 2026-09-13. 사용자가 배포 준비 결과를 확인한 뒤 즉시 배포를 요청했다.
+이 기록은 후보의 검증 근거이며 GitHub/npm 게시 완료를 미리 선언하지 않는다.
+
+## 범위와 변경 로그
+
+이전 공개 릴리스 `v0.98.5`는 main의 조상이며, 준비 시점의 GitHub Release와 공개 npm
+`latest` 7개도 0.98.5로 일치했다. 원격 `v0.99.0`이 없음을 확인한 뒤 준비했다.
+
+`decee7f157`부터 `ca75f4e5cc`까지의 frontier·Devin·Codex SSE·재시도·TUI·설계 문서와,
+이번에 확정한 `3c7d3b4613`(TB 선택 v2), `b21daf1a76`(TB 감사 v2),
+`003f7b081a`(문서·변경 로그·로컬 캡처 제외)을 포함한다. 마지막 세 단위는 각각
+pre-commit 전체 검사를 통과했고, 선택기 40개·감사기 66개 CLI 검사를 통과했다.
+
+TB 출력 계약 변경은 minor 증가로 처리했다. `selectionVersion: 2`의 nullable 예상
+시간·총량과 `omk-tb21-audit-report-2`의 필수 완료시각을 Breaking Changes에 기록했다.
+입력 manifest는 v1을 유지한다. 이전 버전 changelog 본문은 바꾸지 않았으며 다음
+작업용 `[Unreleased]`는 비워 두었다. 새로운 벤치마크 성능이나 SOTA 우위는 주장하지 않는다.
+
+## 버전·의존성
+
+공개 7개 패키지, root/example manifests, 내부 의존 범위, lockfiles, CLI shrinkwrap,
+book compiler의 `PACKAGE_VERSION`, README 버전 링크와 릴리스 노트를 0.99.0에 맞춘다.
+외부 의존성의 버전·resolved URL·integrity 값은 변경하지 않았다. 모델 카탈로그도
+재생성하지 않았다. 운영자 설정·인증·MCP·스킬 활성 목록은 변경하지 않았다.
+
+첫 `version:minor` 실행은 manifest 증가 뒤 아직 이전 버전을 가리키는 내부 의존성을
+npm 출시일 제한에 대조하다 중단됐다. 버전 증가를 재실행하지 않고, 기존
+`sync-versions.js`와 lockfile/설치 동기화 단계만 이어갔다. 제한을 완화하거나 기존
+태그를 이동하지 않았다. 추가적인 registry 패키지 버전 변경은 없음을 대조했다.
+
+## 관측한 로컬 검증
+
+- 환경: Linux, Node.js 24.19.0, npm 11.14.1.
+- 새 버전의 `npm run build`가 7개 workspace 전체에서 종료 0이었다.
+- `test.sh`를 인증 없는 별도 HOME·최소 환경에서 실행했다. 실제 운영자 auth 파일은
+  건드리지 않았다. `taskset`으로 네 CPU에 제한했고 `LIVE_E2E=0`,
+  `OMK_NO_LOCAL_LLM=1`, `OMK_OFFLINE=1`을 사용했다.
+- 전체 테스트: **8,279 통과, 852 환경·실계정 조건 skip, 실패 0, 종료 0**.
+  WPL 149, agent 870, AI 676, book compiler 22, coding-agent 5,695,
+  protocol 137, TUI 730개가 통과했다. 이 수치는 CI 실행 결과가 아니다.
+- 준비 단계의 TB 106개와 전체 guard 378개 통과를 전체 제품 테스트 수에 다시 더하지 않는다.
+- 최종 후보 확인 중 공유 트리에 Devin 요청 코드·테스트·문서와 그 변경 로그가 별도로
+  바뀐 것을 발견했다. 이 4개 파일의 후속 변경은 제외하고 `003f7b081a`와 릴리스
+  메타데이터만 별도 detached worktree에 옮겼다. 변경 로그의 같은 파일에 섞인 후속
+  항목도 원래 커밋의 본문과 대조해 분리했다. 운영자의 변경·인증은 덮어쓰지 않는다.
+- 격리 후보에서도 전체 테스트 8,279개 통과·852개 조건 skip·실패 0을 재확인했다.
+  공유 트리 실행과 같은 검사를 중복 합산하지 않았다.
+- 격리 후보의 `npm run check`(Node guard 378개 포함), 7개 pack dry-run·공개 entrypoint
+  import, 빌드 CLI의 `--version`·`--help`·`run --help`가 모두 종료 0이었다.
+  모든 pack의 버전은 0.99.0이고, 필수 진입점 누락·비공개 상태 경로는 없었다.
+- 후보 diff의 Gitleaks 검사는 완전 redaction과 기존 규칙으로 종료 0, 탐지 0건이었다.
+- `--release`의 stale-worktree guard는 별도 최종 배포 gate다. 후보를 main에 연결하고
+  이 작업의 임시 체크아웃을 제거한 뒤 기본 checkout에서 실행한다. guard나 이름을
+  바꿔 검사를 피하지 않는다.
+
+## 배포 완료 조건
+
+기존 `build-binaries.yml`의 태그 기반 경로만 사용한다. 로컬 `npm publish`, 인증 변경,
+새로운 실행 권한·모델 호출은 없다. release source와 tag의 동일 SHA 검사를 유지한다.
+후보는 검토한 명시 경로만 stage하고 staged diff 전체를 확인한 뒤 commit·tag·push한다.
+
+공식 workflow가 6개 플랫폼 바이너리 빌드, 검사·테스트, npm 7개 패키지 게시,
+GitHub Release 생성을 완료해야 한다. 최종 판정은 태그의 main 포함,
+GitHub `v0.99.0` Release와 7개 npm `latest`의 일치다. 기존 token 기반 인증을 사용하며
+OIDC/Sigstore provenance는 주장하지 않는다. 실패 시 원인을 확인하고 기존 배포의
+무결성 경계를 유지하며, 완료 전에는 배포 성공이라고 보고하지 않는다.

package/docs/run-protocol.md

@@ -6,7 +6,7 @@ The OMK Run Protocol defines one versioned contract for task execution and evalu
 TaskSpec -> ExecutionAttempt -> Observation -> EvaluationResult -> RuntimeDecision
 ```
 
-`omk-protocol` owns these records and the pure reducers that connect them. Tool execution, persistence, scheduling, routing, and topology remain outside the package.
+`omk-protocol` owns these records and the pure reducers that connect them. Tool execution, persistence, runtime scheduling, routing, and topology selection remain outside the package.
 
 ## Implemented scope
 
@@ -24,6 +24,39 @@ The first v1 slice is available under `packages/protocol` with schema version `o
 
 Every top-level record carries `schemaVersion`. Parsers reject unsupported versions, malformed timestamps, duplicate claim IDs, invalid JSON facts, and empty logical conditions.
 
+## Isolated command-run profile
+
+`RunContract` and `RunStartCommand` add strict, immutable parsers for the opt-in
+`linux-command-v1` and `linux-scripted-agent-v1` profiles. They pin the input digest,
+write scope, commands, stdout assertions and finite phase/snapshot limits. The
+scripted profile also pins 1–16 approved steps and a 1–32 logical request cap for
+an offline AgentSession reference adapter. Unknown authority/provider fields are
+rejected; the host must separately authorize the exact contract digest.
+`RunResumeCommand` / `parseRunResumeCommand()` pin the contract, candidate and exact
+expected revision/generation. The host may acquire at most three generations under
+`MAX_VERIFIED_RUN_GENERATIONS`; a resume command does not authorize replay of a writer.
+The separate `RunWriterRestartCommand` / `parseRunWriterRestartCommand()` binds
+`baseDigest` to a durable input checkpoint for an explicit local writer restart.
+Recovery commands share command IDs and the generation cap; none resets budgets.
+
+`linux-command-dag-v1` adds `RunDagWriter` / `RunDagTask` with 1–16 nodes, explicit
+artifact dependencies, disjoint write scopes and 1–2 preapproved command attempts per
+node. Optional `maxConcurrentTasks` accepts only 1 or 2; omission preserves legacy
+serialization and serial execution. `orderRunDag()` provides deterministic FIFO topological order and
+`runDagAncestors()` includes the full transitive input closure. `RunTaskRetryCommand`
+/ `parseRunTaskRetryCommand()` pins a task selection to the original input and exact
+run revision/generation. These pure contracts never authorize dispatch or authenticate
+cached output; the Coordinator checks stored material and records adoption before reuse.
+
+The coding-agent's `RunCoordinator` owns execution and its separate v2 journal.
+It binds native v3 receipt cores to the candidate through a supervisor attestation,
+then supplies authenticated checks to the existing claim-closure reducer.
+This does not replace the task/attempt/evaluation contracts or add execution to
+this package. See [Verified Run](verified-run.md) for the implemented CLI/SDK
+path, candidate recovery and checkpoint-based local writer restart, plus the
+bounded command DAG, eager frontier and selective retry, plus remaining live-model,
+verification-edge, plan amendment and control-surface work.
+
 ## Durable goal lifecycle
 
 A durable goal is working-directory state, not a session-file field or a `TaskSpec`. `/goal <objective>` creates or edits `.omk/goals/current.json`; `/goal` without arguments shows its status and round count.

package/docs/runtime-algorithms.md

@@ -1,5 +1,31 @@
 # Runtime Algorithms and Direction
 
+## Working-tree shared run budgets
+
+The SDK `prompt(..., { runBudget })` path now shares a monotonic deadline and
+logical request/concurrency limits across the active prompt's main stream,
+retries, continuations, and first-party summaries using that stream. Exhaustion
+is a non-retryable `budget_exhausted` termination; snapshots keep outstanding
+streams until terminal metadata arrives. No request/time budget is imposed by
+default. Preflight is now owned even for unbounded prompts; unresolved streams
+block a later prompt instead of being discarded when their budget scope closes.
+See [Shared run budgets](sdk.md#shared-run-budgets-sdk-opt-in) for units, zero
+semantics, cancellation, and uncovered paths. This is not billing enforcement,
+a persisted budget, or a hard process-termination deadline.
+
+## Working-tree execution ownership (2026-09-10)
+
+The live session now retains registered tool-promise ownership after timeout or
+abort, defers prompt settlement/resource-lease release until actual termination,
+and rejects overlapping prompt admission. Shared permits capture request values,
+honor zero capacity, and wake FIFO followers after head cancellation/expiry.
+The internal lane launcher forwards cancellation and respects zero/heavy caps.
+Independent bash calls now own separate cancellation controllers, and one call's
+completion cannot hide another active call. Core teardown waits use a monotonic
+clock, preserving the existing grace interval across wall-clock changes.
+See [Prompt settlement](sdk.md#prompt-settlement) for tests, compatibility, and
+uncovered paths. These changes do not implement a durable verified-run product.
+
 ## v0.98.3 release delta (2026-09-06)
 
 The explicit advisory SDK requires normal first-party model completion, honors cancellation,
@@ -128,15 +154,18 @@ Evidence:
 - `packages/coding-agent/test/context-budget-selection-policy-version.test.ts`
 - `packages/coding-agent/test/context-budget-cache-disk.test.ts`
 
-**Working tree:** non-queued native `xai` requests started through `AgentSession.prompt()` now derive a bounded automatic skill grant from live discovered descriptions after ordinary prompt-template expansion. The selector scores task text separately from camelCase-aware path-to-skill-name signals, excludes explicit-only skills, caps automatic matches at three, and adds `headroom` only under lexical or measured context pressure. `AgentSession.prompt()` merges the result with settings/SDK/bang selections only for that request. Queued steering/follow-up messages reuse the active run's system prompt and do not trigger another selection pass.
+**Working tree:** non-queued native `xai` and `devin` requests started through `AgentSession.prompt()` now derive a bounded automatic skill grant from live discovered descriptions after ordinary prompt-template expansion. The selector scores task text separately from camelCase-aware path-to-skill-name signals, excludes explicit-only skills, caps automatic matches at three, and adds `headroom` only under lexical or measured context pressure. `AgentSession.prompt()` merges the result with settings/SDK/bang selections only for that request. Queued steering/follow-up messages reuse the active run's system prompt and do not trigger another selection pass.
 
 Evidence:
 
 - `packages/coding-agent/src/core/active-skill-state.ts`
 - `packages/coding-agent/src/core/skill-selector.ts`
+- `packages/coding-agent/src/core/harness-skills.ts`
 - `packages/coding-agent/src/core/grok-harness.ts`
+- `packages/coding-agent/src/core/devin-harness.ts`
 - `packages/coding-agent/src/core/agent-session.ts`
 - `packages/coding-agent/test/grok-active-skills.test.ts`
+- `packages/coding-agent/test/devin-active-skills.test.ts`
 - `packages/coding-agent/test/skill-selector.property.test.ts`
 
 **Working tree:** context files now treat their global/local relevance baseline