feat(automation): run EmbedRelay hourly NVIDIA NIM review repair

.github/workflows/embedrelay-hourly-review-repair.yml

@@ -0,0 +1,37 @@
+name: EmbedRelay Hourly Review Repair
+
+on:
+  schedule:
+    # Minute 20 avoids pg-llm-batch (1), aFIPC (2), kaefa (3), LineageWeave (4),
+    # codec-carver (5), life-os (6), Wardnet (7), mightyETL (8),
+    # psychometrics-commons (9), OriginWeave (10), naruon (11),
+    # DiagramWeave (12), pg-erd-cloud (13), mhtml-etl-gateway (14),
+    # html4tree (15), nonnest2 (16), orchestrator (17), RankWeave (18),
+    # noema (19), Clearfolio (23), Keyverse (29), Scopeweave (31),
+    # DiskSage (37), Appguardrail (41), newsdom-api (43), Inkspan (47),
+    # fast-mlsirm (49), BandScope (53), and semantic-data-portal (59).
+    - cron: "20 * * * *"
+
+concurrency:
+  group: embedrelay-hourly-review-repair
+  # A later heartbeat must not cancel an in-flight embedding-swap RCA.
+  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/EmbedRelay
+      base_branch: main
+      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 }}

.github/workflows/hourly-nvidia-nim-review-repair.yml

@@ -17,6 +17,7 @@ on:
       - .github/workflows/orgmetra-hourly-review-repair.yml
       - .github/workflows/originweave-hourly-review-repair.yml
       - .github/workflows/quarantine-sandbox-hourly-review-repair.yml
+      - .github/workflows/embedrelay-hourly-review-repair.yml
       - scripts/ci/pr_review_conflict_scope.py
       - scripts/ci/pr_review_autofix_context.py
       - tests/test_bandscope_hourly_review_caller.py
@@ -29,6 +30,7 @@ on:
       - tests/test_orgmetra_hourly_review_caller.py
       - tests/test_originweave_hourly_review_caller.py
       - tests/test_quarantine_sandbox_hourly_review_caller.py
+      - tests/test_embedrelay_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
@@ -54,6 +56,7 @@ on:
       - docs/doctoring/orgmetra-hourly-review-caller.md
       - docs/doctoring/originweave-hourly-review-caller.md
       - docs/doctoring/quarantine-sandbox-hourly-review-caller.md
+      - docs/doctoring/embedrelay-hourly-review-caller.md
   push:
     paths:
       - .github/workflows/pr-review-fix-scheduler.yml
@@ -70,6 +73,7 @@ on:
       - .github/workflows/orgmetra-hourly-review-repair.yml
       - .github/workflows/originweave-hourly-review-repair.yml
       - .github/workflows/quarantine-sandbox-hourly-review-repair.yml
+      - .github/workflows/embedrelay-hourly-review-repair.yml
       - scripts/ci/pr_review_conflict_scope.py
       - scripts/ci/pr_review_autofix_context.py
       - tests/test_bandscope_hourly_review_caller.py
@@ -82,6 +86,7 @@ on:
       - tests/test_orgmetra_hourly_review_caller.py
       - tests/test_originweave_hourly_review_caller.py
       - tests/test_quarantine_sandbox_hourly_review_caller.py
+      - tests/test_embedrelay_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
@@ -107,6 +112,7 @@ on:
       - docs/doctoring/orgmetra-hourly-review-caller.md
       - docs/doctoring/originweave-hourly-review-caller.md
       - docs/doctoring/quarantine-sandbox-hourly-review-caller.md
+      - docs/doctoring/embedrelay-hourly-review-caller.md
 
 permissions:
   contents: read
@@ -164,6 +170,7 @@ jobs:
             tests/test_orgmetra_hourly_review_caller.py \
             tests/test_originweave_hourly_review_caller.py \
             tests/test_quarantine_sandbox_hourly_review_caller.py \
+            tests/test_embedrelay_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 \

AGENTS.md

@@ -7,4 +7,5 @@ Materialize accepts only exact SHA-256 pins or a bounded relative `-r` include (
 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).
+EmbedRelay hourly NVIDIA NIM repair is a thin caller at minute 20. See [`docs/doctoring/embedrelay-hourly-review-caller.md`](docs/doctoring/embedrelay-hourly-review-caller.md).
 The materialization contract is also covered by [`docs/doctoring/exact-artifact-sbom-attestation.md`](docs/doctoring/exact-artifact-sbom-attestation.md).

ARCHITECTURE.md

@@ -39,6 +39,13 @@ only established scheduler credentials, and grants job-scoped
 only established scheduler credentials, and grants job-scoped
 `id-token: write`. The reusable engine stays product-neutral.
 
+## EmbedRelay hourly caller
+
+`embedrelay-hourly-review-repair.yml` is a thin, read-only caller at minute
+20. It names `ContextualWisdomLab/EmbedRelay` and protected `main`, maps
+only established scheduler credentials, and grants job-scoped
+`id-token: write`. The reusable engine stays product-neutral.
+
 ## Hourly NVIDIA NIM repair gate
 
 ```mermaid

CLAUDE.md

@@ -118,7 +118,7 @@ repeatable compile command.
   without running the test suite will break CI.
 - **100% coverage and 100% docstrings on `scripts/ci/`** are hard gates, not aspirations. New helper
   code needs matching tests and docstrings.
-- **Product hourly callers** stay thin. Do not hard-code OriginWeave, naruon, or Keyverse
+- **Product hourly callers** stay thin. Do not hard-code EmbedRelay, naruon, or Keyverse
   into `pr-review-fix-scheduler.yml`. The model credential remains `NVIDIA_NIM_API_KEY`
   on the worker, never `COPILOT_GITHUB_TOKEN`.
 - **`pull_request_target` trust boundary.** The required review workflows run the *base branch's*

docs/doctoring/embedrelay-hourly-review-caller.md

@@ -0,0 +1,136 @@
+# EmbedRelay hourly review-repair caller
+
+검토 기준일: **2026-08-17**
+
+## Decision
+
+ContextualWisdomLab operates one protected hourly caller for
+`ContextualWisdomLab/EmbedRelay` (swap embedding models without stopping
+retrieval). The caller runs at minute 20, delegates to the
+product-neutral central review-fix scheduler, inspects at most 50 open
+pull requests targeting protected `main`, and dispatches at most one
+bounded repair per heartbeat.
+
+A paying buyer of live retrieval continuity would feel EmbedRelay pull
+requests stalling while hourly NVIDIA NIM repair scanned only Clearfolio,
+DiskSage, and fast-mlsirm. The live head
+ContextualWisdomLab/EmbedRelay#3 (retire protected-main M1 materializer)
+targets `main` and never enters those other callers.
+
+The caller does not implement review or mutation logic itself.
+EmbedRelay remains standalone; naruon and RankWeave consume embeddings
+without owning the swap 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 embedding
+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 materializer retirement 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-main activation, the repository variable
+`OPENCODE_REPOSITORY_DISPATCH_TARGETS` must contain the exact
+`ContextualWisdomLab/EmbedRelay` target. Missing or mismatched
+configuration fails before mutation credential materialization.
+
+## Security, standalone operation, and modularity
+
+The caller adds no EmbedRelay runtime dependency, database object,
+network endpoint, tenant authority, or product credential. EmbedRelay
+continues to run as a standalone embedding-swap service. Naruon,
+RankWeave, and other CWL services may consume its vectors, but they
+cannot weaken its exact-head, approval, or security gates.
+
+## Verification and rollback
+
+Machine-checkable contracts require the exact target/base, minute 20
+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-main consumer run proving the exact EmbedRelay repository and
+`main` base. Source checks alone are not protected-main operational acceptance.
+Merge still requires zero unresolved valid findings and a
+qualifying independent non-author approval.
+
+Rollback removes the EmbedRelay 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/

requirements-pip-audit-ci-hashes.txt

@@ -213,9 +213,9 @@ packaging==26.2 \
     # via
     #   pip-audit
     #   pip-requirements-parser
-pip==26.1.2 \
-    --hash=sha256:382ff9f685ee3bc25864f820aa50505825f10f5458ffff07e30a6d96e5715cab \
-    --hash=sha256:f49cd134c61cf2fd75e0ce2676db03e4054504a5a4986d00f8299ae632dc4605
+pip==26.2.1 \
+    --hash=sha256:71138adf1f4ca900cdb7d289c21b7494329f2332b6d85f0e1c42108c0384ed3e \
+    --hash=sha256:f6ad667e89a1fe78046c8f13232b247200f5258d7828f3f7883d660878e0813f
     # via pip-api
 pip-api==0.0.34 \
     --hash=sha256:8b2d7d7c37f2447373aa2cf8b1f60a2f2b27a84e1e9e0294a3f6ef10eb3ba6bb \