ContextualWisdomLab · seonghobae · Aug 17, 2026
@@ -13,6 +13,7 @@ on:
       - .github/workflows/github-hourly-review-repair.yml
       - .github/workflows/governance-risk-compliance-hourly-review-repair.yml
       - .github/workflows/hourly-nvidia-nim-review-repair.yml
+      - .github/workflows/naruon-hourly-review-repair.yml
       - .github/workflows/nonnest2-hourly-review-repair.yml
       - .github/workflows/originweave-hourly-review-repair.yml
       - scripts/ci/pr_review_conflict_scope.py
@@ -25,6 +26,7 @@ on:
       - tests/test_hourly_scheduler_runtime_budget.py
       - tests/test_nonnest2_hourly_review_caller.py
       - tests/test_originweave_hourly_review_caller.py
+      - tests/test_naruon_hourly_review_caller.py
       - tests/test_hourly_autofix_context_quality_gate.py
       - tests/test_pr_review_conflict_scope.py
       - tests/test_pr_review_conflict_scope_control_files.py
@@ -48,6 +50,7 @@ on:
       - docs/doctoring/hourly-nvidia-nim-autofix.md
       - docs/doctoring/nonnest2-hourly-review-caller.md
       - docs/doctoring/originweave-hourly-review-caller.md
+      - docs/doctoring/naruon-hourly-review-caller.md
   push:
     paths:
       - .github/workflows/pr-review-fix-scheduler.yml
@@ -60,6 +63,7 @@ on:
       - .github/workflows/github-hourly-review-repair.yml
       - .github/workflows/governance-risk-compliance-hourly-review-repair.yml
       - .github/workflows/hourly-nvidia-nim-review-repair.yml
+      - .github/workflows/naruon-hourly-review-repair.yml
       - .github/workflows/nonnest2-hourly-review-repair.yml
       - .github/workflows/originweave-hourly-review-repair.yml
       - scripts/ci/pr_review_conflict_scope.py
@@ -72,6 +76,7 @@ on:
       - tests/test_hourly_scheduler_runtime_budget.py
       - tests/test_nonnest2_hourly_review_caller.py
       - tests/test_originweave_hourly_review_caller.py
+      - tests/test_naruon_hourly_review_caller.py
       - tests/test_hourly_autofix_context_quality_gate.py
       - tests/test_pr_review_conflict_scope.py
       - tests/test_pr_review_conflict_scope_control_files.py
@@ -95,6 +100,7 @@ on:
       - docs/doctoring/hourly-nvidia-nim-autofix.md
       - docs/doctoring/nonnest2-hourly-review-caller.md
       - docs/doctoring/originweave-hourly-review-caller.md
+      - docs/doctoring/naruon-hourly-review-caller.md
 
 permissions:
   contents: read
@@ -150,6 +156,7 @@ jobs:
             tests/test_hourly_scheduler_runtime_budget.py \
             tests/test_nonnest2_hourly_review_caller.py \
             tests/test_originweave_hourly_review_caller.py \
+            tests/test_naruon_hourly_review_caller.py \
             tests/test_pr_review_conflict_scope_control_files.py \
             tests/test_hourly_autofix_context_quality_gate.py \
             tests/test_pr_review_conflict_scope_git_executable.py \

@@ -0,0 +1,30 @@
+name: naruon Hourly Review Repair
+
+on:
+  schedule:
+    # Minute 11 avoids Clearfolio (23), DiskSage (37), and fast-mlsirm (49).
+    - cron: "11 * * * *"
+
+concurrency:
+  group: naruon-hourly-review-repair
+  # A later heartbeat must not cancel an in-flight platform RCA or repair.
+  cancel-in-progress: false
+
+permissions:
+  contents: read
+
+jobs:
+  dispatch-review-repair:
+    permissions:
+      contents: read
+      id-token: write
+    uses: ./.github/workflows/pr-review-fix-scheduler.yml
+    with:
+      target_repository: ContextualWisdomLab/naruon
+      base_branch: develop
+      max_prs: "50"
+      max_dispatches: "1"
+      retry_hours: "2"
+    secrets:
+      PR_REVIEW_MERGE_TOKEN: ${{ secrets.PR_REVIEW_MERGE_TOKEN }}
+      OPENCODE_APPROVE_TOKEN: ${{ secrets.OPENCODE_APPROVE_TOKEN }}
@@ -4,6 +4,7 @@
 > **Agents: read the master context FIRST.** Before any work, read [`docs/CWL-MASTER-CONTEXT.md`](docs/CWL-MASTER-CONTEXT.md) (mission · naruon-as-platform + inter-component UML · cross-cutting disciplines · conventions · roadmap · current state), the live **GitHub Project #1** <https://github.com/orgs/ContextualWisdomLab/projects/1> (work/roadmap source of truth), the full spec **ContextualWisdomLab/naruon#974**, and operate the Project per [`docs/agent-github-project-protocol.md`](docs/agent-github-project-protocol.md). The repo/Project — not any private agent memory — is the source of truth.
 
 Materialize accepts only exact SHA-256 pins or a bounded relative `-r` include (no `.`/`..`); a lone `--require-hashes` directive is not trust evidence. See [`docs/doctoring/hourly-nvidia-nim-autofix.md`](docs/doctoring/hourly-nvidia-nim-autofix.md).
+naruon's platform hourly caller scans `ContextualWisdomLab/naruon` `develop` via the product-neutral NVIDIA NIM scheduler (`NVIDIA_NIM_API_KEY` stays on the worker; never `COPILOT_GITHUB_TOKEN`). See [`docs/doctoring/naruon-hourly-review-caller.md`](docs/doctoring/naruon-hourly-review-caller.md).
 Conflict-scope roots fail closed when the immediate parent directory is a symbolic link.
 OriginWeave hourly NVIDIA NIM repair is a thin caller at minute 10. See [`docs/doctoring/originweave-hourly-review-caller.md`](docs/doctoring/originweave-hourly-review-caller.md).
 nonnest2 hourly NVIDIA NIM repair is a thin caller at minute 16. See [`docs/doctoring/nonnest2-hourly-review-caller.md`](docs/doctoring/nonnest2-hourly-review-caller.md).
@@ -66,9 +66,10 @@ The worker checks out helpers at `${{ github.sha }}` so a later default-branch
 push cannot replace privileged scripts after dispatch (CWE-367). Repair binds
 `NVIDIA_NIM_API_KEY`, never `COPILOT_GITHUB_TOKEN`.
 
-Product callers stagger Clearfolio at minute 23, DiskSage at minute 37, and
-fast-mlsirm at minute 49. Each caller is read-only, dispatches at most one
-repair, and delegates all privileged logic to the same sealed scheduler.
+Product callers stagger naruon at minute 11, Clearfolio at minute 23, DiskSage
+at minute 37, and fast-mlsirm at minute 49. Each caller is read-only,
+dispatches at most one repair, and delegates all privileged logic to the same
+sealed scheduler.
 
 ## Control-plane data flow
 
@@ -123,4 +124,6 @@ trusted `uv` exporter is downloaded from the literal GitHub Releases URL for
 - [`docs/doctoring/hourly-nvidia-nim-autofix.md`](docs/doctoring/hourly-nvidia-nim-autofix.md)
   — current increment's repair-worker decision and APA 7th citations.
 - [`docs/doctoring/fast-mlsirm-hourly-review-caller.md`](docs/doctoring/fast-mlsirm-hourly-review-caller.md)
-  — product-specific psychometric repair heartbeat and scientific gates.
+  — product-specific psychometric repair heartbeat and scientific gates.
+- [`docs/doctoring/naruon-hourly-review-caller.md`](docs/doctoring/naruon-hourly-review-caller.md)
+  — naruon platform hourly NVIDIA NIM repair heartbeat on protected `develop`.
@@ -16,13 +16,15 @@ Semantic Versioning where the repository publishes a release.
 - Added a dedicated Clearfolio hourly caller that invokes the product-neutral central scheduler with the exact repository, protected base branch, one-dispatch budget, one-hour retry floor, single-flight concurrency, and only the established scheduler credentials.
 - Added a dedicated DiskSage hourly caller that invokes the same product-neutral RCA and remediation-feasibility scheduler with an exact repository target, one-dispatch budget, two-hour same-head retry floor, non-cancelling single-flight heartbeat, and explicit established scheduler credentials.
 - Added a dedicated fast-mlsirm hourly caller that preserves Rust-owned psychometric arithmetic while dispatching at most one exact-head, root-cause-driven repair with a two-hour same-head retry floor.
+- Added a dedicated naruon hourly caller that scans `ContextualWisdomLab/naruon` protected `develop` at minute 11 with one dispatch, a two-hour same-head retry floor, job-scoped `id-token: write` for the OpenCode OIDC fallback, and only the established scheduler credentials so platform pull requests receive NVIDIA NIM repair.
 
 ### Changed
 
 - Require the hourly repair worker to establish an exact-head root cause, enumerate the smallest remediation candidates, and prove writer authority, sealed-path scope, credentials, dependency order, verifiability, and causal effect before editing; infeasible or external blockers leave the tree unchanged while the broader loop continues with another eligible PR or buyer-visible product gap.
 - Run the bounded Clearfolio PR review-feedback repair caller at minute 23 of every hour while keeping the shared scheduler free of product-specific timers and repository names for modular reuse by naruon, contextual-orchestrator, Inkspan, and other CWL services.
 - Run the bounded DiskSage repair heartbeat at minute 37 of every hour, dispatch no more than one exact-head repair, and wait two hours before redispatching an unchanged head so legitimate OpenCode or NVIDIA NIM latency does not create duplicate writers.
 - Run the bounded fast-mlsirm repair heartbeat at minute 49 of every hour with one-dispatch scope and a two-hour same-head floor, without weakening true-parameter recovery, CPU/GPU parity, skipped-test, or Rust-ownership gates.
+- Run the bounded naruon platform repair heartbeat at minute 11 of every hour against protected `develop`, dispatching at most one exact-head repair and waiting two hours before redispatching an unchanged head.
 - Use NVIDIA NIM `mistralai/mistral-small-4-119b-2603` with explicit high reasoning for scheduled repair and `nvidia/nemotron-3-nano-30b-a3b` for bounded helper work instead of GitHub Models in the write-capable autofix worker.
 - Apply one NUL-delimited exact-path and complete pre/post-worktree verification contract to both ordinary review repair and merge-conflict repair rather than relying on a visible post-model diff for the ordinary path.
 

@@ -69,6 +69,7 @@ Details: `README.md` and `PR_GOVERNANCE_AUDIT.md`.
   `scorecard-governance.md`, SBOM inventory. Doctoring records live under
   `docs/doctoring/`. [`ARCHITECTURE.md`](ARCHITECTURE.md) is the control-plane
   diagram for review, hourly NVIDIA NIM repair, and merge trust boundaries.
+  naruon's platform caller is `naruon-hourly-review-repair.yml` (minute 11, `develop`).
 - `.jules/` — recorded performance (`bolt.md`) and security (`sentinel.md`) learnings from past work
   on `scripts/ci/`; worth scanning before optimizing or hardening those scripts.
 

@@ -5,6 +5,8 @@ engine**.
 
 - `clearfolio-hourly-review-repair.yml` owns Clearfolio's heartbeat at minute 23
   of every hour.
+- `naruon-hourly-review-repair.yml` owns naruon's platform heartbeat at minute 11
+  of every hour against protected `develop`.
 - `pr-review-fix-scheduler.yml` is the reusable, product-neutral scheduler
   module. It has no product-specific timer and can be called by naruon,
   contextual-orchestrator, Inkspan, or another CWL service with an explicit
@@ -39,6 +41,28 @@ The caller passes only the established `PR_REVIEW_MERGE_TOKEN` and
 `NVIDIA_NIM_API_KEY`; the model credential is scoped exclusively to the two
 OpenCode execution steps in the separately reviewed autofix worker.
 
+## naruon execution contract
+
+The naruon caller provides the following immutable operating parameters:
+
+```yaml
+target_repository: ContextualWisdomLab/naruon
+base_branch: develop
+max_prs: "50"
+max_dispatches: "1"
+retry_hours: "2"
+```
+
+The scheduled heartbeat is `11 * * * *`. The caller job grants `id-token: write`
+so the reusable NVIDIA NIM scheduler can mint its OpenCode App fallback from
+GitHub OIDC. It does not receive or forward `NVIDIA_NIM_API_KEY` and never
+introduces `COPILOT_GITHUB_TOKEN`.
+
+The caller passes only the established `PR_REVIEW_MERGE_TOKEN` and
+`OPENCODE_APPROVE_TOKEN` scheduler credentials. It does not receive or forward
+`NVIDIA_NIM_API_KEY`; the model credential is scoped exclusively to the two
+OpenCode execution steps in the separately reviewed autofix worker.
+
 ## Reusable target-selection contract
 
 The shared scheduler resolves its target in this order:

@@ -0,0 +1,132 @@
+# naruon hourly review-repair caller
+
+검토 기준일: **2026-08-17**
+
+## Decision
+
+ContextualWisdomLab operates one protected hourly caller for
+`ContextualWisdomLab/naruon` (naruon.net / naruon.io — the email-workspace
+platform). The caller runs at minute 11, delegates to the product-neutral
+central review-fix scheduler, inspects at most 50 open pull requests targeting
+protected `develop`, and dispatches at most one bounded repair per heartbeat.
+
+A paying buyer of the email workspace would feel live naruon pull requests
+stalling while hourly NVIDIA NIM repair scanned only Clearfolio, DiskSage, and
+fast-mlsirm, all against `main`. Live heads such as
+ContextualWisdomLab/naruon#1388 (NetworkGraph lookup), #1387 (calendar
+sidebar), #1386 (graph rendering), #1383 (NVIDIA NIM review config), #1382
+(first-wins graph ids), and #1380 (DAV capability honesty) target `develop`
+and never enter those other callers.
+
+The caller does not implement review or mutation logic itself. Naruon remains
+standalone; wardnet, keyverse, and inkspan plug into it without owning its
+runtime. Privileged automation stays in `ContextualWisdomLab/.github`.
+
+## Root-cause analysis and remediation feasibility
+
+The reusable worker performs exact-head root-cause analysis and tests
+remediation feasibility before it edits. The reusable worker must:
+
+1. Refetch the exact live head, base, reviews, checks, changed paths, and
+   writer state.
+2. Establish the causal chain rather than repeat the terminal symptom.
+3. Enumerate materially distinct minimal remedies.
+4. Reject remedies that lack writer authority, cross sealed paths, require
+   unavailable credentials or protected-setting changes, violate stack order,
+   cannot be verified, or do not alter the diagnosed cause.
+5. Dispatch at most one feasible repair. Otherwise leave the tree unchanged.
+
+A queued or pending check remains a merge blocker but is not itself a code
+finding. The independent non-author approval remains an external authorization
+gate and is never synthesized by the repair worker. The worker cannot approve,
+merge, release, resolve review findings by inference, change protection, or
+manufacture passing checks.
+
+## Cadence and concurrency
+
+The caller uses a single concurrency group and `cancel-in-progress: false`.
+This preserves an in-flight bounded RCA instead of discarding platform
+evidence when the next hourly heartbeat arrives. The reusable scheduler
+cancels only its own superseded short queue scan.
+
+The caller sets a **two-hour same-head retry floor**. Central OpenCode and
+NVIDIA NIM work, plus naruon's dense-KG and connector analysis, can
+legitimately approach two hours. An hourly redispatch of the same unchanged
+head would create duplicate writer pressure rather than faster remediation.
+
+GitHub scheduled workflows can be delayed under load and execute only from the
+default branch. The cron expression is a heartbeat, not a real-time SLA.
+
+## Credential and model boundary
+
+The caller keeps workflow `GITHUB_TOKEN` at `contents: read` and grants the
+reusable job `id-token: write` so the central scheduler can mint the OpenCode
+GitHub App token from GitHub OIDC when the mapped PAT is absent (GitHub,
+n.d.-c). It maps only `PR_REVIEW_MERGE_TOKEN` and `OPENCODE_APPROVE_TOKEN`.
+It never uses `secrets: inherit`, receives `NVIDIA_NIM_API_KEY`, or introduces
+`COPILOT_GITHUB_TOKEN`. CWE-250 forbids executing the caller with write or
+model privileges it does not need (MITRE, 2026).
+
+Model execution remains inside the central worker. The model credential is the
+GitHub Secret `NVIDIA_NIM_API_KEY`; the caller does not receive or forward it.
+
+Before protected-develop activation, the repository variable
+`OPENCODE_REPOSITORY_DISPATCH_TARGETS` must contain the exact
+`ContextualWisdomLab/naruon` target. Missing or mismatched configuration
+fails before mutation credential materialization.
+
+## Security, standalone operation, and modularity
+
+The caller adds no naruon runtime dependency, database object, network
+endpoint, tenant authority, or product credential. Naruon continues to run as
+a standalone email workspace. Sibling services may plug into naruon, but they
+cannot weaken its local validation, protected-branch, exact-head, approval,
+or security gates.
+
+## Verification and rollback
+
+Machine-checkable contracts require the exact target/base, minute 11 cadence,
+non-cancelling single-flight group, one dispatch, two-hour retry floor,
+explicit secret mapping, read-only contents plus job-scoped `id-token: write`,
+focused path-filter coverage, and absence of model or Copilot credentials.
+Independent `pull_request`, `push`, and `compileall` path blocks must each
+name the caller, doctoring, or contract they own.
+
+After source integration, closure requires a scheduled or manual
+protected-develop consumer run proving the exact naruon repository and
+`develop` base. Source checks alone are not protected-develop operational acceptance.
+Merge still requires zero unresolved valid findings and a
+qualifying independent non-author approval.
+
+Rollback removes the naruon caller, its focused test, doctoring, and central
+path-filter/documentation entries. It must not remove scheduler dispatch
+validation or affect independent product callers.
+
+## APA 7th references
+
+GitHub, Inc. (n.d.-a). *Events that trigger workflows*. GitHub Docs. Retrieved
+August 17, 2026, from
+https://docs.github.com/en/actions/reference/workflows-and-actions/events-that-trigger-workflows#schedule
+
+GitHub, Inc. (n.d.-b). *Reuse workflows*. GitHub Docs. Retrieved August 17,
+2026, from
+https://docs.github.com/en/actions/how-tos/sharing-automations/reuse-workflows
+
+GitHub, Inc. (n.d.-c). *Automatic token authentication*. GitHub Docs.
+Retrieved August 17, 2026, from
+https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#permissions-for-the-github_token
+
+MITRE. (2026). *CWE-250: Execution with unnecessary privileges*.
+https://cwe.mitre.org/data/definitions/250.html
+
+National Institute of Standards and Technology. (2022). *Secure software
+development framework (SSDF) version 1.1: Recommendations for mitigating the
+risk of software vulnerabilities* (NIST Special Publication 800-218).
+https://doi.org/10.6028/NIST.SP.800-218
+
+NVIDIA. (n.d.). *NVIDIA NIM for large language models documentation*.
+Retrieved August 17, 2026, from
+https://docs.nvidia.com/nim/large-language-models/latest/
+
+OpenCode. (n.d.). *OpenCode documentation*. Retrieved August 17, 2026, from
+https://opencode.ai/docs/
@@ -6,6 +6,7 @@
 REUSABLE = Path(".github/workflows/pr-review-fix-scheduler.yml")
 CLEARFOLIO = Path(".github/workflows/clearfolio-hourly-review-repair.yml")
 DISKSAGE = Path(".github/workflows/disksage-hourly-review-repair.yml")
+NARUON = Path(".github/workflows/naruon-hourly-review-repair.yml")
 QUALITY = Path(".github/workflows/hourly-nvidia-nim-review-repair.yml")
 
 
@@ -25,8 +26,8 @@ def test_queue_scanner_has_a_bounded_superseding_runtime() -> None:
 
 
 def test_product_callers_do_not_cancel_an_in_flight_rca() -> None:
-    """Clearfolio and DiskSage preserve the non-cancelling product lease."""
-    for caller_path in (CLEARFOLIO, DISKSAGE):
+    """Clearfolio, DiskSage, and naruon preserve the non-cancelling product lease."""
+    for caller_path in (CLEARFOLIO, DISKSAGE, NARUON):
         caller = _read(caller_path)
         assert "cancel-in-progress: false" in caller
         assert "cancel-in-progress: true" not in caller