feat(ci): wire Ollama review-run into Patchwarden dry-run #524

Merged

pdurlej merged 1 commit from codex/523-patchwarden-ollama-workflow into main 2026-05-27 15:59:19 +02:00

Conversation 0 Commits 1 Files changed 1 +112 -5

codex commented 2026-05-27 15:33:22 +02:00

Collaborator

Copy link

Canary status: missing - workflow/security-sensitive change; require operator/Iskra review before merge.

Canary Context Pack

Product story

Patchwarden dogfood should visibly exercise the actual Ollama reviewer lane and speak back to eligible boring PRs, instead of only uploading silent deterministic artifacts. This makes the platform loop closer to the operator mental model without widening automerge authority.

What changed

• patchwarden-client-dry-run now grants pull-requests: write for the dry-run job so Patchwarden can post comments when a runner-local comment token exists.
• The workflow now sources the runner-local canary env (PLATFORMCTL_CANARY_ENV) before model review/comment posting.
• The workflow now builds /tmp/patchwarden-client/pr-metadata.json from the PR event and collected file list.
• patchwarden review-run now uses --lane-config, --pr-metadata-file, and --diff-file instead of the deterministic stub flags.
• The live reviewer is explicitly limited to safe_docs_status; workflow/runtime/secrets/policy-governance PRs skip model review/commenting and remain manual.
• A new gated post-findings --execute step posts the rendered Patchwarden findings/no-findings comment to the PR when FORGEJO_TOKEN_CODEX or PLATFORMCTL_PR_SANITY_COMMENT_TOKEN is present in the runner-local env.

Why it changed

Issue #523 identifies that Patchwarden PR #49/#50 capabilities already exist, but platform was not wiring them into the dry-run workflow. This PR is pure platform-side wiring, constrained by the repo CI secret policy.

Files touched

• .forgejo/workflows/patchwarden-client-dry-run.yml

Relevant context

• pdurlej/patchwarden#49: live review-run path via lane config + PR metadata + diff.
• pdurlej/patchwarden#50: post-findings --execute behavior.
• pdurlej/patchwarden#57: D21 allows this workflow wiring under M2 gate amendment.
• docs/ci/README.md: PR workflows must not read provider/comment tokens from Forgejo repo secrets; they use runner-local Infisical-derived env instead.
• policies/platform.v0.toml in Patchwarden remains the source of lane/model config.

Runtime evidence

No runtime/platform service mutation. Local validation only:

• git diff --check
• YAML parse via Ruby/Psych
• python3 control-plane/platformctl/ci/lint_workflows.py --policy .forgejo/ci-policy.yaml --workflows .forgejo/workflows --markdown /tmp/ci-workflow-lint.md --json /tmp/ci-workflow-lint.json -> 0 findings
• PYTHONPATH=control-plane python3 -m platformctl.cli validate all --json -> exitCode 0

Known constraints

• Smoke test requires this workflow to be merged, then a trivial safe_docs_status PR must be opened to verify live Ollama call + PR comment.
• PLATFORMCTL_CANARY_ENV must exist on the runner and include the Ollama key; comment posting also needs FORGEJO_TOKEN_CODEX or PLATFORMCTL_PR_SANITY_COMMENT_TOKEN.
• If this PR itself is classified as workflow, the live reviewer/comment step should intentionally skip; that is expected and preserves the safe-docs-only lane.
• If Ollama is unreachable on an eligible safe-docs PR and the lane is fail-closed, review-run should exit 2 and no comment should post.

Explicit out-of-scope

• No pyfallow/fallow-ts wiring.
• No Patchwarden CLI changes.
• No policy expansion beyond the existing safe_docs_status lane.
• No merge/approval automation.
• No Forgejo repository secret use for provider/comment tokens.

Requested decision

Merge after workflow/security review so the follow-up smoke PR can validate end-to-end behavior on an eligible boring docs/status change.

Merge blockers

• Missing runner-local canary env for live model review/comment posting on the follow-up smoke PR.
• Workflow accidentally executing PR code with comment token.
• Any change that would let Patchwarden approve or merge instead of only comment.

Spec sources read

• docs/forgejo-agent-operations.md - Forgejo write identity and API rules.
• docs/ci/README.md - runner-local Infisical env and no repo-secret token policy.
• .forgejo/ci-policy.yaml - workflow lint policy forbidding direct provider/comment token names and secrets in PR workflows.
• .forgejo/workflows/patchwarden-client-dry-run.yml - target workflow.
• Issue #523 - implementation scope and acceptance criteria.
• /Users/pd/Developer/patchwarden/src/patchwarden/cli.py - review-run and post-findings CLI flags/exit behavior.
• /Users/pd/Developer/patchwarden/policies/platform.v0.toml - existing lane config.
• /Users/pd/Developer/patchwarden/docs/operations/platform-dogfood.md - current dogfood gap.

Closes #523

Canary status: missing - workflow/security-sensitive change; require operator/Iskra review before merge. ## Canary Context Pack ### Product story Patchwarden dogfood should visibly exercise the actual Ollama reviewer lane and speak back to eligible boring PRs, instead of only uploading silent deterministic artifacts. This makes the platform loop closer to the operator mental model without widening automerge authority. ### What changed - `patchwarden-client-dry-run` now grants `pull-requests: write` for the dry-run job so Patchwarden can post comments when a runner-local comment token exists. - The workflow now sources the runner-local canary env (`PLATFORMCTL_CANARY_ENV`) before model review/comment posting. - The workflow now builds `/tmp/patchwarden-client/pr-metadata.json` from the PR event and collected file list. - `patchwarden review-run` now uses `--lane-config`, `--pr-metadata-file`, and `--diff-file` instead of the deterministic stub flags. - The live reviewer is explicitly limited to `safe_docs_status`; workflow/runtime/secrets/policy-governance PRs skip model review/commenting and remain manual. - A new gated `post-findings --execute` step posts the rendered Patchwarden findings/no-findings comment to the PR when `FORGEJO_TOKEN_CODEX` or `PLATFORMCTL_PR_SANITY_COMMENT_TOKEN` is present in the runner-local env. ### Why it changed Issue #523 identifies that Patchwarden PR #49/#50 capabilities already exist, but platform was not wiring them into the dry-run workflow. This PR is pure platform-side wiring, constrained by the repo CI secret policy. ### Files touched - `.forgejo/workflows/patchwarden-client-dry-run.yml` ### Relevant context - `pdurlej/patchwarden#49`: live `review-run` path via lane config + PR metadata + diff. - `pdurlej/patchwarden#50`: `post-findings --execute` behavior. - `pdurlej/patchwarden#57`: D21 allows this workflow wiring under M2 gate amendment. - `docs/ci/README.md`: PR workflows must not read provider/comment tokens from Forgejo repo secrets; they use runner-local Infisical-derived env instead. - `policies/platform.v0.toml` in Patchwarden remains the source of lane/model config. ### Runtime evidence No runtime/platform service mutation. Local validation only: - `git diff --check` - YAML parse via Ruby/Psych - `python3 control-plane/platformctl/ci/lint_workflows.py --policy .forgejo/ci-policy.yaml --workflows .forgejo/workflows --markdown /tmp/ci-workflow-lint.md --json /tmp/ci-workflow-lint.json` -> 0 findings - `PYTHONPATH=control-plane python3 -m platformctl.cli validate all --json` -> exitCode 0 ### Known constraints - Smoke test requires this workflow to be merged, then a trivial `safe_docs_status` PR must be opened to verify live Ollama call + PR comment. - `PLATFORMCTL_CANARY_ENV` must exist on the runner and include the Ollama key; comment posting also needs `FORGEJO_TOKEN_CODEX` or `PLATFORMCTL_PR_SANITY_COMMENT_TOKEN`. - If this PR itself is classified as `workflow`, the live reviewer/comment step should intentionally skip; that is expected and preserves the safe-docs-only lane. - If Ollama is unreachable on an eligible safe-docs PR and the lane is fail-closed, `review-run` should exit 2 and no comment should post. ### Explicit out-of-scope - No pyfallow/fallow-ts wiring. - No Patchwarden CLI changes. - No policy expansion beyond the existing `safe_docs_status` lane. - No merge/approval automation. - No Forgejo repository secret use for provider/comment tokens. ### Requested decision Merge after workflow/security review so the follow-up smoke PR can validate end-to-end behavior on an eligible boring docs/status change. ### Merge blockers - Missing runner-local canary env for live model review/comment posting on the follow-up smoke PR. - Workflow accidentally executing PR code with comment token. - Any change that would let Patchwarden approve or merge instead of only comment. ## Spec sources read - `docs/forgejo-agent-operations.md` - Forgejo write identity and API rules. - `docs/ci/README.md` - runner-local Infisical env and no repo-secret token policy. - `.forgejo/ci-policy.yaml` - workflow lint policy forbidding direct provider/comment token names and secrets in PR workflows. - `.forgejo/workflows/patchwarden-client-dry-run.yml` - target workflow. - Issue #523 - implementation scope and acceptance criteria. - `/Users/pd/Developer/patchwarden/src/patchwarden/cli.py` - `review-run` and `post-findings` CLI flags/exit behavior. - `/Users/pd/Developer/patchwarden/policies/platform.v0.toml` - existing lane config. - `/Users/pd/Developer/patchwarden/docs/operations/platform-dogfood.md` - current dogfood gap. Closes #523

codex added 1 commit 2026-05-27 15:33:22 +02:00

feat(ci): wire patchwarden Ollama dry-run comments 194daf9789

codex added the

class/security-sensitive

tier/full

labels 2026-05-27 15:33:52 +02:00

codex force-pushed codex/523-patchwarden-ollama-workflow from 194daf9789 to 8d1cd290f9 2026-05-27 15:37:47 +02:00 Compare

codex force-pushed codex/523-patchwarden-ollama-workflow from 8d1cd290f9 to b07a44b512 2026-05-27 15:43:54 +02:00 Compare

pdurlej merged commit 99fc08a264 into main 2026-05-27 15:59:19 +02:00

pdurlej referenced this pull request from a commit 2026-05-27 15:59:20 +02:00

Merge pull request 'feat(ci): wire Ollama review-run into Patchwarden dry-run' (#524) from codex/523-patchwarden-ollama-workflow into main

codex referenced this pull request from a commit 2026-05-27 17:46:07 +02:00

docs(state): W6d post-#524 smoke target (Patchwarden Ollama wiring evidence)

codex referenced this pull request from a commit 2026-05-27 22:59:41 +02:00

fix(ci): export MERGE_BASE in patchwarden-client-dry-run step

codex referenced this pull request from a commit 2026-05-27 23:18:32 +02:00

docs(state): W6d post-#524 smoke target (Patchwarden Ollama wiring evidence)

codex referenced this pull request from a commit 2026-05-28 13:30:41 +02:00

docs(operations): Wave Wizji-Wartości evidence-confirmed (2026-05-28)

claude referenced this pull request 2026-06-02 15:28:48 +02:00

WIP: docs(state): W6d post-#524 smoke target (Patchwarden Ollama wiring evidence) #527

Sign in to join this conversation.

Reviewers

No reviewers

Labels

Clear labels   

W6d-automerge-calibration

  

agent/claude-code

Vistula actor: Claude Code.

  

agent/codex

Vistula actor: Codex.

  

agent/hermes

Vistula actor: Hermes Upstream.

  

agent/iskra

Vistula actor: Iskra.

  

agent/ollama

Vistula actor: Ollama or compatible model.

  

agent/patchwarden

Vistula actor: Patchwarden.

  

automerge-candidate

Candidate for narrow W6d autonomous merge readiness pilot

  

class/security-sensitive

Security-sensitive class of service: smallest coherent PRs and full canary

  

cutover-gate

blocks production declare / final RS2000 replacement

  

dependency/blocked

Vistula dependency state: blocked.

  

dependency/blocks-others

Vistula dependency state: blocks other work.

  

dependency/cross-repo

Vistula dependency scope: cross-repository.

  

dependency/needs-confirmation

Vistula dependency state: needs confirmation.

  

domain:agents

Agent identity, delegation, subagents, routing, or workflows.

  

domain:ci

CI, checks, Actions, runners, or release automation.

  

domain:docs

Documentation, packets, practices, or source-of-truth text.

  

domain:forgejo

Forgejo issues, PRs, labels, repo settings, or identity.

  

domain:infra

Infrastructure, storage, backup, DNS, network, or host substrate.

  

domain:memory

Memory, recall, write gates, salience, or Honcho-adjacent behavior.

  

domain:runtime

Runtime services, deploys, daemons, timers, or live behavior.

  

domain:signal

Signal UX, delivery, context, or outbound behavior.

  

domain:ux

Product UX, operator experience, or conversation ergonomics.

  

flow/architecture

Vistula lifecycle: architecture phase in progress.

  

flow/blocked

Vistula lifecycle: blocked on dependency or decision.

  

flow/deployed

Vistula lifecycle: deployed to runtime where applicable.

  

flow/done

Vistula lifecycle: work merged or otherwise done.

  

flow/implementation

Vistula lifecycle: implementation phase in progress.

  

flow/intake

Vistula lifecycle: incoming signal not refined yet.

  

flow/maintained

Vistula lifecycle: maintained/steady state.

  

flow/observed

Vistula lifecycle: observed after delivery.

  

flow/ready

Vistula lifecycle: ready for architecture or implementation.

  

flow/refining

Vistula lifecycle: Hermes/spec refinement in progress.

  

flow/retired

Vistula lifecycle: retired or intentionally closed.

  

flow/review

Vistula lifecycle: review phase in progress.

  

iterating

Orchestrator/Codex actively amending in response to review — operator can ignore until resolved

  

judge/codex-candidate

Candidate for Codex implementation.

  

judge/hermes-candidate

Candidate for Hermes discovery/research.

  

judge/low-confidence

Judgment confidence is low.

  

judge/needs-refinement

Needs clearer evidence or scope.

  

judge/operator-needed

Needs Piotr decision or input.

  

judge/p0

Urgent, operator attention or unblock now.

  

judge/p1

High value, schedule soon.

  

judge/p2

Useful, normal queue.

  

judge/p3

Low priority, keep but do not chase.

  

judge/park

Parked from current attention.

  

judge/patchwarden-candidate

Needs Patchwarden merge-safety attention.

  

judge/stale-priority

Existing priority judgment appears stale.

  

kind/adr

Vistula work kind: architecture decision record.

  

kind/bug

Vistula work kind: bug fix.

  

kind/chore

Vistula work kind: chore.

  

kind/feature

Vistula work kind: feature.

  

kind/infra

Vistula work kind: infrastructure.

  

kind/ops

Vistula work kind: operations.

  

kind/refactor

Vistula work kind: refactor.

  

kind/research

Vistula work kind: research/discovery.

  

large-impact

Per charter §3 review-by-impact: large impact (≥300 LOC OR new module OR identity/secret change OR architectural pivot) — Oracle pre-review recommended

  

merge/auto

Vistula merge mode: automated merge.

  

merge/manual

Vistula merge mode: manual merge.

  

merge/manual-dependency-conflict

Manual merge reason: dependency conflict.

  

merge/manual-failing-tests

Manual merge reason: failing tests.

  

merge/manual-merge-conflict

Manual merge reason: merge conflict.

  

merge/manual-missing-review

Manual merge reason: missing review.

  

merge/manual-operator-preference

Manual merge reason: operator preference.

  

merge/manual-red-zone

Manual merge reason: red-zone risk.

  

merge/manual-security-sensitive

Manual merge reason: security-sensitive work.

  

merge/manual-unclear-scope

Manual merge reason: unclear scope.

  

merge/manual-unknown

Manual merge reason: unknown.

  

meta

meta-decomposition issue; first agent decomposes into atomic children

  

mode:operator-only

Apply step requires explicit operator approval.

  

mode:patchwarden-iskra-approved

Work eligible for Patchwarden/Iskra approval inside repo policy.

  

mode:safe-auto

Low-risk work eligible for lightweight autonomous handling.

  

needs-operator-decision

PR is blocked on operator yes/no decision — fresh-Claude/Codex won't make this call alone

  

needs-triage

decomposing agent has open questions / unknowns

  

not-ready

reviewed but blocked on a precondition

  

observed/erroring

Vistula observation: erroring.

  

observed/needs-followup

Vistula observation: needs follow-up.

  

observed/pending

Vistula observation: pending.

  

observed/retire-candidate

Vistula observation: retire candidate.

  

observed/unused

Vistula observation: unused.

  

observed/used

Vistula observation: used.

  

operator-emotional

operator-emotional importance (Iskra memory etc.)

  

owner-attention

owner must decide; blocks default path

  

phase/02

Phase 02 cataloging

  

phase/03

Phase 03 control plane (platformctl)

  

priority:p0

Immediate safety, uptime, data, or operator-blocking issue.

  

priority:p1

Important active work; should be pulled soon.

  

priority:p2

Useful normal-priority work.

  

priority:p3

Opportunistic cleanup, research, or backlog work.

  

proposed

auto-generated by meta-decomposition; awaiting human review

  

ready-for-agent

reviewed and pickable; agents may claim per cookbook

  

ready-for-operator

PR is ready for operator review/merge — orchestrator finished its part

  

recovery

disaster recovery / restore semantics relevant

  

review:claude-reviewed

Reviewed by Claude-family agent.

  

review:codex-reviewed

Reviewed by Codex-family agent.

  

review:dziadek-reviewed

Reviewed by Dziadek pinch-point reviewer.

  

review:needs-human

Needs human review before merge or apply.

  

risk/exposure

incorrectly public/private/tailnet/auth/routed

  

risk/process

workflow/review/orchestration may produce bad outcomes

  

risk/product

work may have lost owner/user value

  

risk/runtime

platform may not run, recover, validate, behave reproducibly

  

safety:external-write

May write to external systems, users, rooms, repos, or services.

  

safety:no-prod-mutation

Must not mutate production or live external state.

  

safety:prod-impact

May affect production/runtime behavior.

  

safety:secret-touch

Touches secrets, credentials, auth, or secret-adjacent config.

  

size/large

Vistula size: large.

  

size/medium

Vistula size: medium.

  

size/small

Vistula size: small.

  

size/tiny

Vistula size: tiny.

  

size/unknown

Vistula size: not classified yet.

  

source/adr

Vistula source: ADR.

  

source/agent-generated

Vistula source: agent generated.

  

source/manual

Vistula source: manual entry.

  

source/operator-chat

Vistula source: operator chat.

  

source/voice-note

Vistula source: voice note.

  

status:blocked

Blocked by missing dependency, evidence, access, or operator decision.

  

status:codex-ready

Ready for a Codex implementation pass.

  

status:merged:pending-evidence

Merged but waiting for live or artifact evidence before closure.

  

status:needs-evidence

Needs proof, logs, tests, or operator-visible evidence.

  

status:operator-needed

Requires explicit operator input before safe progress.

  

status:parked

Intentionally deferred; not active campaign work.

  

tier/full

Full review tier per ADR-0007

  

tier/lite

Lite review tier per ADR-0007

  

tier/stacked

Stacked PR (base != main) escape hatch per ADR-0017. Requires consolidator-PR plan in PR body.

  

tier:0-platform-substrate

Data, secrets, backup, storage, or critical platform substrate.

  

tier:1-iskra-value-layer

Iskra/OpenClaw behavior, memory, runtime, or value-layer work.

  

tier:2-tools-products-modules

Tools, products, modules, experiments, and lower-blast-radius work.

  

type:bug

Incorrect behavior or regression.

  

type:chore

Maintenance, cleanup, metadata, or operational task.

  

type:docs

Documentation-only work.

  

type:feat

New capability or product behavior.

  

type:policy

Governance, protocol, boundary, or decision-contract change.

  

type:research

Investigation, spike, or evidence-gathering task.

No labels

W6d-automerge-calibration

agent/claude-code

agent/codex

agent/hermes

agent/iskra

agent/ollama

agent/patchwarden

automerge-candidate

class/security-sensitive

cutover-gate

dependency/blocked

dependency/blocks-others

dependency/cross-repo

dependency/needs-confirmation

domain:agents

domain:ci

domain:docs

domain:forgejo

domain:infra

domain:memory

domain:runtime

domain:signal

domain:ux

flow/architecture

flow/blocked

flow/deployed

flow/done

flow/implementation

flow/intake

flow/maintained

flow/observed

flow/ready

flow/refining

flow/retired

flow/review

iterating

judge/codex-candidate

judge/hermes-candidate

judge/low-confidence

judge/needs-refinement

judge/operator-needed

judge/p0

judge/p1

judge/p2

judge/p3

judge/park

judge/patchwarden-candidate

judge/stale-priority

kind/adr

kind/bug

kind/chore

kind/feature

kind/infra

kind/ops

kind/refactor

kind/research

large-impact

merge/auto

merge/manual

merge/manual-dependency-conflict

merge/manual-failing-tests

merge/manual-merge-conflict

merge/manual-missing-review

merge/manual-operator-preference

merge/manual-red-zone

merge/manual-security-sensitive

merge/manual-unclear-scope

merge/manual-unknown

meta

mode:operator-only

mode:patchwarden-iskra-approved

mode:safe-auto

needs-operator-decision

needs-triage

not-ready

observed/erroring

observed/needs-followup

observed/pending

observed/retire-candidate

observed/unused

observed/used

operator-emotional

owner-attention

phase/02

phase/03

priority:p0

priority:p1

priority:p2

priority:p3

proposed

ready-for-agent

ready-for-operator

recovery

review:claude-reviewed

review:codex-reviewed

review:dziadek-reviewed

review:needs-human

risk/exposure

risk/process

risk/product

risk/runtime

safety:external-write

safety:no-prod-mutation

safety:prod-impact

safety:secret-touch

size/large

size/medium

size/small

size/tiny

size/unknown

source/adr

source/agent-generated

source/manual

source/operator-chat

source/voice-note

status:blocked

status:codex-ready

status:merged:pending-evidence

status:needs-evidence

status:operator-needed

status:parked

tier/full

tier/lite

tier/stacked

tier:0-platform-substrate

tier:1-iskra-value-layer

tier:2-tools-products-modules

type:bug

type:chore

type:docs

type:feat

type:policy

type:research

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

1 participant

Notifications

Subscribe

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

pdurlej/platform!524

No description provided.