GiorgioAresu/home-ops
Watch
0
0
Fork
You've already forked home-ops
 0
Code Issues 1 Pull requests 40 Projects Releases Packages Wiki Activity Actions

ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.3.0) - autoclosed #2258

Closed
renovate-bot wants to merge 1 commit from renovate/https-github.com-misospace-pr-reviewer-action-3.x into main
pull from: renovate/https-github.com-misospace-pr-reviewer-action-3.x
merge into: GiorgioAresu:main
Conversation 1 Commits 1 Files changed 1 +1 -1
renovate-bot commented 2026-10-01 01:02:23 +02:00
Collaborator

This PR contains the following updates:

Package Type Update Change
https://github.com/misospace/pr-reviewer-action action major v2.5.0 → v3.3.0

⚠️ Warning

Some dependencies could not be looked up. Check the Dependency Dashboard for more information.

Release Notes

misospace/pr-reviewer-action (https://github.com/misospace/pr-reviewer-action)

v3.3.0

Compare Source

Features
Bug Fixes
Chores

v3.2.0

Compare Source

The native tool loop has always rationed its own evidence gathering against a fixed assumption: about 50 KB of corpus on the first turn and 12 KB captured per tool result, no matter which model was listening on the other end. Declaring a model window already sized the review corpus, diff and file budgets to it — but the tool loop kept living hand-to-mouth under defaults tuned for the smallest plausible setup.

3.2.0 makes the window you declare the source of truth for the whole evidence pipeline, front to back. It is a steady minor release: no breaking changes, no renames, nothing you must reconfigure — though if you run large-window models, your reviewer is about to read a lot more of the PR per turn.

primary-model-context-tokens: ${{ vars.PRIMARY_CONTEXT_TOKENS }}
smart-model-context-tokens: ${{ vars.SMART_CONTEXT_TOKENS }}
fallback-model-context-tokens: ${{ vars.FALLBACK_CONTEXT_TOKENS }}

Context that actually fits the model

  • Declaring a tier's window already sized the review corpus, diff and file budgets; the native-loop budgets were the holdout. tool-corpus-max-bytes and tool-max-response-bytes now derive from the declared window too (#​923): the first-turn corpus normally lands near 15% of the window (capped at 600 KB) and each tool result near 2% (capped at 64 KB), with envelope guards so the loop's conversation can never overflow the window you declared.
  • New fallback-model-context-tokens (#​922, #​942): the fallback reuses the primary's review corpus, so declaring the fallback window sizes the shared corpus to the smaller of the two capacities. A compact fallback model stops receiving a corpus sized for a large primary.
  • No window declared? Nothing changes: the derived values resolve to exactly the previous defaults (50000 and 12000).
  • The honest flip side: if you already declare large windows, expect materially larger review and tool context, and the token spend that comes with it. Explicit tool-corpus-max-bytes / tool-max-response-bytes values still win — keep them set if you want the old ceiling.

Better evidence, less harness friction

A cluster of fixes with one theme: the reviewer spends its context on evidence instead of fighting its own harness.

  • gh_api decodes Contents API file reads instead of handing the model truncated base64 (#​926). The model was being shown encoded bytes and asked to review code it couldn't read.
  • Changed files whose complete diff is already in the review corpus are credited as read (#​930) — no redundant tool calls re-reading what the corpus already carried, and no honest review made to look partial.
  • Repository-content files are masked before truncation rather than after (#​943), so a size cut can no longer land inside what the redaction needed to see.
  • Direct smart routes actually run on the selected model (#​933) — the smarter model you configured is the one that shows up.
  • The availability-fallback corpus is bounded by the fallback model's declared capacity (#​942).

Operator-mode foundations

#​946 lands the typed groundwork for the self-hosted Operator — the Renovate-style, multi-repository reviewer: a strictly validated, fail-closed operator instance config; named model/executor/evidence profiles that carry credential references, never inline secrets; a deterministic adoption policy; and an ecfg-v1 effective-config fingerprint that future review jobs will hash for identity. Repository-referenced instruction files are read from the trusted base side — byte-capped, symlink-refusing, resolved from the base ref, never the PR head.

None of this is wired into the normal Action runtime yet. It is scaffolding, exercised by tests and consumed by the controller work ahead; Action users should notice exactly nothing today.

Small things that make operating it nicer

  • Skipped reviews now say why, in the log and a step-summary line (#​944, #​903). Silent skips were a support-ticket generator.
  • Published reviews carry the action version in both the engine line and the managed metadata marker (#​941), so "which build wrote this review" stops being an archaeology question. action_version is an additive key in the marker (the schema stays version 1) — custom parsers should tolerate it. For the same reason, note that the verdict-source output may now read enforcement when a fail-closed layer forced the verdict.
  • Claim extraction got sharper: whole-sentence claim units, body claims outranking titles, enumerated items handled (#​939).
  • Requirement tracing is scoped to the requirements actually relevant to the change (#​937).
  • Image-digest-only manifest refreshes — the pin bumps that change nothing but digests — now classify correctly (#​925, #​909).
  • The README split into focused pages with a generated inputs reference (#​917), and the Marketplace listing metadata is refreshed (#​918).

Toward Tangled

Another read-side step for the Tangled platform (#​854, #​584): a Bobbin/XRPC read client and a canonical pull resolver, with pulls addressed by AT-URI/CID and resolution that fails closed on ambiguity. This is groundwork — Tangled review support is not complete yet.

Upgrading

  • No declared model-context windows? You should see no context-budget behavior change from #​923 — the derived values resolve to the previous defaults.
  • Declaring large windows? Expect larger review and tool context, and the token spend that comes with it.
  • Running primary + fallback models? Consider setting fallback-model-context-tokens so the shared corpus fits the smaller window.
  • Existing explicit tool-corpus-max-bytes / tool-max-response-bytes remain authoritative. Remove them only if you want window-derived budgets.
  • @v3 follows the newly released v3.2.0 build. Immutable-version and SHA pins must bump deliberately.
  • No input renames, removals, or other major-version migration. Every input's current contract lives in docs/inputs.md.

Full changelog: https://github.com/misospace/pr-reviewer-action/compare/v3.1.0...v3.2.0

Generated changelog (release-please)
Features
  • build: stamp action version into the engine line and marker (#​941) (c0721cf)
  • config: define the operator instance/repo config and adoption contract (#​946) (1529026)
  • context: derive context budgets from each tier's declared window (#​923) (3ef1fd2)
  • v3: add Tangled Bobbin read client and canonical pull resolver (#​584) (#​854) (4899ece)
Bug Fixes
  • action: log the precheck skip reason and write a step summary line (#​944) (69a91d7), closes #​903
  • claims: whole-sentence claim units, body-claim priority, item enumeration (#​939) (a625193), closes #​898
  • classification: classify image-digest-only manifest refreshes (#​909) (#​925) (7f6ab64)
  • deps: update dependency @​types/node (24.19.0 → 24.19.1) (#​936) (0562534)
  • eval: carry env-only stage knobs so blind replays really skip human reviews (#​928) (#​929) (14900d9)
  • requirement-trace: scope the trace to relevant requirements (#​937) (b0a3d6e)
  • review: bound the availability-fallback corpus by the declared fallback capacity (#​942) (0162197)
  • review: use selected model for direct smart routes (#​933) (d5923ee)
  • test: stop the semantic fixture racing git's background gc (#​920) (#​945) (19f0f6b)
  • tools: credit changed files whose full diff is already in the review corpus (#​930) (0a5c700)
  • tools: gh_api decodes Contents API files instead of returning truncated base64 (#​926) (d1fdbd4)
  • tools: mask repo_contents files before truncating (#​943) (861a326)
Chores
  • action: refresh the Marketplace listing metadata (#​918) (554500d)
Documentation
  • split the README into focused pages and generate the inputs reference (#​917) (93118c6)

v3.1.0

Compare Source

Features
  • tools: raise the native-loop budget and report a real cache hit ratio (#​911) (bf937d0)

v3.0.1

Compare Source

Bug Fixes
  • release: track a source-vX.Y.Z anchor so release-please finds the last release (#​907) (443bf19)
  • v3: read system-prompt-file from the base ref, not the run artifact dir (#​905) (de5c628)

v3.0.0

Compare Source

⚠ BREAKING CHANGES
  • review: remove incremental-only escalation and review metadata state (#​618) (#​645)
  • review: remove carried findings and cross-run incremental evidence state (#​617) (#​644)
  • review: review_scope, escalate_on_dirty_baseline, effective_review_scope, previous_head_sha, and baseline_clean are removed; there is no replacement.
Features
Bug Fixes
  • ci: wall-bound GitHub gh api polling attempts (#​688) (d6889b4)
  • classifier: require a real untrusted-path surface for path handling (#​756) (a3abef6)
  • classifier: stop misclassifying module imports as path handling (#​720) (9931ac6)
  • dogfood: exercise all specialist roles (#​667) (702675e)
  • dogfood: make the v3 shadow actually run (#​819) (91df3a0)
  • enforcement: run thread settlement and carry original severity (#​812) (7a7a35b)
  • eval: fail closed on an unusable pinned file manifest (#​833) (ed873b2)
  • eval: fixtures are same-repo PRs; configurable review timeout (#​771) (645feb6)
  • eval: key adjudication scenarios by corpus entry id (#​893) (#​894) (c5c1024)
  • eval: real-PR runs-per-mode, longer review timeout, bad corpus pin (#​860) (062c498)
  • eval: seed pinned replays' file list from the pinned diff (6cc1113)
  • eval: seed pinned replays' file list from the pinned diff (#​833) (c3db3c0)
  • evals: fail eval-harness when every run errors (#​714) (05aaafe)
  • evals: harvester review follow-ups (#​801) (88b94fc)
  • evals: retain diffs for specialists fixtures (#​713) (fd4d8cd)
  • evals: triage the 13 anchor-check flags from #​861 (#​877) (60dbe1a)
  • eval: weekly summary reads per-mode rates from mode_summary (#​715) (#​744) (4b17206)
  • image: validate registry repository paths (#​724) (864ffc1)
  • keep reviewed checkout off python sys.path (#​788) (4c630a5)
  • model: guarantee at least one call attempt per tier (#​887) (55eeaf8)
  • native-loop: consume recoverable verdict retry, no duplicate synthesis (#​637) (#​651) (345351c)
  • platform: body-edit cutoff via GraphQL lastEditedAt; reapply #​812 rule post-CI (7a19eaf)
  • platform: one atomic body snapshot per metadata pass (#​812 review) (ac09f43)
  • platform: valid PR-thread comment order (#​631) (#​649) (d45a273)
  • precheck: link issues referenced by PR title and non-closing body forms (#​879) (e481bd6), closes #​872
  • precheck: pin config reads to one fd (#​723) (2ab2a3a)
  • publish: keep the endpoint URL out of published reviews (#​836) (7a788da)
  • redact: use a non-alphanumeric marker for known-secret masking (#​888) (939e0fc)
  • repo-map: avoid auth filename backtracking (#​722) (d70bc95)
  • restore the reviewer's evidence gathering (v2 + v3) (#​759) (339d998)
  • reviewer: keep sanitizer redaction from garbling committed source (#​880) (791c85f)
  • run: streamed tool calls, tool cwd and specialist artifact root (#​820) (515943e)
  • standards: resolve the standards file from the base ref, not PR head (#​890) (59d93f2)
  • tests: clear .test-build and make git operations hermetic (#​858) (27d4b95)
  • tool-loop: honour an empty ai_temperature on native_loop planning turns (#​747) (8f3c0a6)
  • tooling: refuse redirects on token-bearing HTTP calls (#​859) (860b56d)
  • tools: keep tool-harness.json valid under redaction and fail closed when unreadable (#​899) (#​900) (97f0b0d)
  • tools: scale loop round cap with the tool budget (#​895) (#​897) (a98bdf5)
  • transport: surface HTTP status and body detail on model-call errors (#​862) (ec25b3f)
  • v3: mask secrets in model errors carried by a 200 reply (#​868) (#​869) (ae72527)
  • v3: normalize labeled-event shape so ai-review forces a re-review (#​896) (241dd2d)
  • v3: publish the model-failure notice as request_changes (#​863) (#​866) (fb49242)
  • v3: run never reads artifacts from the PR checkout (#​838) (#​870) (6080648)
  • verdict: make non-blocking finding categories opt-in (#​775) (1b83be8)
  • verdict: repair invalid escapes before accepting a partial candidate (#​767) (d9b1a12)
Chores
Documentation
Refactors

Configuration

📅 Schedule: (in timezone Europe/Rome)

  • Branch creation
    • At any time (no schedule defined)
  • Automerge
    • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

  • If you want to rebase/retry this PR, check this box

This PR has been generated by Mend Renovate CLI.

This PR contains the following updates: | Package | Type | Update | Change | |---|---|---|---| | [https://github.com/misospace/pr-reviewer-action](https://github.com/misospace/pr-reviewer-action) | action | major | `v2.5.0` → `v3.3.0` | --- > ⚠️ **Warning** > > Some dependencies could not be looked up. Check the [Dependency Dashboard](issues/6) for more information. --- ### Release Notes <details> <summary>misospace/pr-reviewer-action (https://github.com/misospace/pr-reviewer-action)</summary> ### [`v3.3.0`](https://github.com/misospace/pr-reviewer-action/releases/tag/v3.3.0) [Compare Source](https://github.com/misospace/pr-reviewer-action/compare/v3.2.0...v3.3.0) ##### Features - **rereview:** /ai-review comment command to force a re-review ([#&#8203;914](https://github.com/misospace/pr-reviewer-action/issues/914)) ([#&#8203;952](https://github.com/misospace/pr-reviewer-action/issues/952)) ([9e7519b](https://github.com/misospace/pr-reviewer-action/commit/9e7519b877c80b9b1b51ddcc14100f95b37efb33)) ##### Bug Fixes - **precheck:** recognize Addresses and scope past-tense closing keywords ([#&#8203;953](https://github.com/misospace/pr-reviewer-action/issues/953)) ([#&#8203;956](https://github.com/misospace/pr-reviewer-action/issues/956)) ([5a659f7](https://github.com/misospace/pr-reviewer-action/commit/5a659f7b9578a80a671325d782ca400eee8e5e92)) - **requirement-trace:** require strong subject evidence for scope ([#&#8203;957](https://github.com/misospace/pr-reviewer-action/issues/957)) ([#&#8203;958](https://github.com/misospace/pr-reviewer-action/issues/958)) ([bcae3d3](https://github.com/misospace/pr-reviewer-action/commit/bcae3d3d68f245c7ad9206936c7a079a19412448)) - **test:** list the dogfood context-window inputs as overrides ([#&#8203;951](https://github.com/misospace/pr-reviewer-action/issues/951)) ([f32389b](https://github.com/misospace/pr-reviewer-action/commit/f32389b899ca0a9970e45a7efda42b122a68ec10)) - **v3:** split trace gap from execution gap ([#&#8203;954](https://github.com/misospace/pr-reviewer-action/issues/954)) ([#&#8203;955](https://github.com/misospace/pr-reviewer-action/issues/955)) ([f891b14](https://github.com/misospace/pr-reviewer-action/commit/f891b14d2529f15fcbb0c69f38b8e8ae6a06327b)) ##### Chores - **ai-review:** declare dogfood context windows ([#&#8203;949](https://github.com/misospace/pr-reviewer-action/issues/949)) ([69788e1](https://github.com/misospace/pr-reviewer-action/commit/69788e1337a09b0c6b2e988d9d46a5501ac8b1c8)) ### [`v3.2.0`](https://github.com/misospace/pr-reviewer-action/releases/tag/v3.2.0) [Compare Source](https://github.com/misospace/pr-reviewer-action/compare/v3.1.0...v3.2.0) The native tool loop has always rationed its own evidence gathering against a fixed assumption: about 50 KB of corpus on the first turn and 12 KB captured per tool result, no matter which model was listening on the other end. Declaring a model window already sized the review corpus, diff and file budgets to it — but the tool loop kept living hand-to-mouth under defaults tuned for the smallest plausible setup. 3.2.0 makes the window you declare the source of truth for the whole evidence pipeline, front to back. It is a steady minor release: no breaking changes, no renames, nothing you must reconfigure — though if you run large-window models, your reviewer is about to read a lot more of the PR per turn. ```yaml primary-model-context-tokens: ${{ vars.PRIMARY_CONTEXT_TOKENS }} smart-model-context-tokens: ${{ vars.SMART_CONTEXT_TOKENS }} fallback-model-context-tokens: ${{ vars.FALLBACK_CONTEXT_TOKENS }} ``` #### Context that actually fits the model - Declaring a tier's window already sized the review corpus, diff and file budgets; the native-loop budgets were the holdout. `tool-corpus-max-bytes` and `tool-max-response-bytes` now derive from the declared window too ([#&#8203;923](https://github.com/misospace/pr-reviewer-action/issues/923)): the first-turn corpus normally lands near 15% of the window (capped at 600 KB) and each tool result near 2% (capped at 64 KB), with envelope guards so the loop's conversation can never overflow the window you declared. - New `fallback-model-context-tokens` ([#&#8203;922](https://github.com/misospace/pr-reviewer-action/issues/922), [#&#8203;942](https://github.com/misospace/pr-reviewer-action/issues/942)): the fallback reuses the primary's review corpus, so declaring the fallback window sizes the shared corpus to the smaller of the two capacities. A compact fallback model stops receiving a corpus sized for a large primary. - No window declared? Nothing changes: the derived values resolve to exactly the previous defaults (50000 and 12000). - The honest flip side: if you already declare large windows, expect materially larger review and tool context, and the token spend that comes with it. Explicit `tool-corpus-max-bytes` / `tool-max-response-bytes` values still win — keep them set if you want the old ceiling. #### Better evidence, less harness friction A cluster of fixes with one theme: the reviewer spends its context on evidence instead of fighting its own harness. - `gh_api` decodes Contents API file reads instead of handing the model truncated base64 ([#&#8203;926](https://github.com/misospace/pr-reviewer-action/issues/926)). The model was being shown encoded bytes and asked to review code it couldn't read. - Changed files whose complete diff is already in the review corpus are credited as read ([#&#8203;930](https://github.com/misospace/pr-reviewer-action/issues/930)) — no redundant tool calls re-reading what the corpus already carried, and no honest review made to look partial. - Repository-content files are masked before truncation rather than after ([#&#8203;943](https://github.com/misospace/pr-reviewer-action/issues/943)), so a size cut can no longer land inside what the redaction needed to see. - Direct smart routes actually run on the selected model ([#&#8203;933](https://github.com/misospace/pr-reviewer-action/issues/933)) — the smarter model you configured is the one that shows up. - The availability-fallback corpus is bounded by the fallback model's declared capacity ([#&#8203;942](https://github.com/misospace/pr-reviewer-action/issues/942)). #### Operator-mode foundations [#&#8203;946](https://github.com/misospace/pr-reviewer-action/issues/946) lands the typed groundwork for the self-hosted Operator — the Renovate-style, multi-repository reviewer: a strictly validated, fail-closed operator instance config; named model/executor/evidence profiles that carry credential *references*, never inline secrets; a deterministic adoption policy; and an `ecfg-v1` effective-config fingerprint that future review jobs will hash for identity. Repository-referenced instruction files are read from the trusted base side — byte-capped, symlink-refusing, resolved from the base ref, never the PR head. None of this is wired into the normal Action runtime yet. It is scaffolding, exercised by tests and consumed by the controller work ahead; Action users should notice exactly nothing today. #### Small things that make operating it nicer - Skipped reviews now say why, in the log and a step-summary line ([#&#8203;944](https://github.com/misospace/pr-reviewer-action/issues/944), [#&#8203;903](https://github.com/misospace/pr-reviewer-action/issues/903)). Silent skips were a support-ticket generator. - Published reviews carry the action version in both the engine line and the managed metadata marker ([#&#8203;941](https://github.com/misospace/pr-reviewer-action/issues/941)), so "which build wrote this review" stops being an archaeology question. `action_version` is an additive key in the marker (the schema stays version 1) — custom parsers should tolerate it. For the same reason, note that the `verdict-source` output may now read `enforcement` when a fail-closed layer forced the verdict. - Claim extraction got sharper: whole-sentence claim units, body claims outranking titles, enumerated items handled ([#&#8203;939](https://github.com/misospace/pr-reviewer-action/issues/939)). - Requirement tracing is scoped to the requirements actually relevant to the change ([#&#8203;937](https://github.com/misospace/pr-reviewer-action/issues/937)). - Image-digest-only manifest refreshes — the pin bumps that change nothing but digests — now classify correctly ([#&#8203;925](https://github.com/misospace/pr-reviewer-action/issues/925), [#&#8203;909](https://github.com/misospace/pr-reviewer-action/issues/909)). - The README split into focused pages with a generated inputs reference ([#&#8203;917](https://github.com/misospace/pr-reviewer-action/issues/917)), and the Marketplace listing metadata is refreshed ([#&#8203;918](https://github.com/misospace/pr-reviewer-action/issues/918)). #### Toward Tangled Another read-side step for the Tangled platform ([#&#8203;854](https://github.com/misospace/pr-reviewer-action/issues/854), [#&#8203;584](https://github.com/misospace/pr-reviewer-action/issues/584)): a Bobbin/XRPC read client and a canonical pull resolver, with pulls addressed by AT-URI/CID and resolution that fails closed on ambiguity. This is groundwork — Tangled review support is not complete yet. #### Upgrading - No declared model-context windows? You should see no context-budget behavior change from [#&#8203;923](https://github.com/misospace/pr-reviewer-action/issues/923) — the derived values resolve to the previous defaults. - Declaring large windows? Expect larger review and tool context, and the token spend that comes with it. - Running primary + fallback models? Consider setting `fallback-model-context-tokens` so the shared corpus fits the smaller window. - Existing explicit `tool-corpus-max-bytes` / `tool-max-response-bytes` remain authoritative. Remove them only if you *want* window-derived budgets. - `@v3` follows the newly released v3.2.0 build. Immutable-version and SHA pins must bump deliberately. - No input renames, removals, or other major-version migration. Every input's current contract lives in [docs/inputs.md](https://github.com/misospace/pr-reviewer-action/blob/v3.2.0/docs/inputs.md). **Full changelog:** <https://github.com/misospace/pr-reviewer-action/compare/v3.1.0...v3.2.0> <details> <summary>Generated changelog (release-please)</summary> ##### Features - **build:** stamp action version into the engine line and marker ([#&#8203;941](https://github.com/misospace/pr-reviewer-action/issues/941)) ([c0721cf](https://github.com/misospace/pr-reviewer-action/commit/c0721cf7af5d838f99ab0d16a8a7d4de788fe6b9)) - **config:** define the operator instance/repo config and adoption contract ([#&#8203;946](https://github.com/misospace/pr-reviewer-action/issues/946)) ([1529026](https://github.com/misospace/pr-reviewer-action/commit/1529026b19fde60b70402a43dc8998b8f7f43bba)) - **context:** derive context budgets from each tier's declared window ([#&#8203;923](https://github.com/misospace/pr-reviewer-action/issues/923)) ([3ef1fd2](https://github.com/misospace/pr-reviewer-action/commit/3ef1fd2c87c817047fc79b1df7679bd3df80ae34)) - **v3:** add Tangled Bobbin read client and canonical pull resolver ([#&#8203;584](https://github.com/misospace/pr-reviewer-action/issues/584)) ([#&#8203;854](https://github.com/misospace/pr-reviewer-action/issues/854)) ([4899ece](https://github.com/misospace/pr-reviewer-action/commit/4899ece12cc6c345edccf45e379cc068cac7f3f2)) ##### Bug Fixes - **action:** log the precheck skip reason and write a step summary line ([#&#8203;944](https://github.com/misospace/pr-reviewer-action/issues/944)) ([69a91d7](https://github.com/misospace/pr-reviewer-action/commit/69a91d7139573bf5d61778ac2e9d6ad1236cc802)), closes [#&#8203;903](https://github.com/misospace/pr-reviewer-action/issues/903) - **claims:** whole-sentence claim units, body-claim priority, item enumeration ([#&#8203;939](https://github.com/misospace/pr-reviewer-action/issues/939)) ([a625193](https://github.com/misospace/pr-reviewer-action/commit/a625193be1c2ced7f8b4783fdff6d1de97179951)), closes [#&#8203;898](https://github.com/misospace/pr-reviewer-action/issues/898) - **classification:** classify image-digest-only manifest refreshes ([#&#8203;909](https://github.com/misospace/pr-reviewer-action/issues/909)) ([#&#8203;925](https://github.com/misospace/pr-reviewer-action/issues/925)) ([7f6ab64](https://github.com/misospace/pr-reviewer-action/commit/7f6ab644a3ebcced52fccf252ede51ec6976f462)) - **deps:** update dependency [@&#8203;types/node](https://github.com/types/node) (24.19.0 → 24.19.1) ([#&#8203;936](https://github.com/misospace/pr-reviewer-action/issues/936)) ([0562534](https://github.com/misospace/pr-reviewer-action/commit/0562534f861fc5178f47e37700ae6d802c766f0f)) - **eval:** carry env-only stage knobs so blind replays really skip human reviews ([#&#8203;928](https://github.com/misospace/pr-reviewer-action/issues/928)) ([#&#8203;929](https://github.com/misospace/pr-reviewer-action/issues/929)) ([14900d9](https://github.com/misospace/pr-reviewer-action/commit/14900d9fcfee89382df2d84ac146b5555d7d8d1a)) - **requirement-trace:** scope the trace to relevant requirements ([#&#8203;937](https://github.com/misospace/pr-reviewer-action/issues/937)) ([b0a3d6e](https://github.com/misospace/pr-reviewer-action/commit/b0a3d6ed0b59b2eb931774a8717ffc535e9339d6)) - **review:** bound the availability-fallback corpus by the declared fallback capacity ([#&#8203;942](https://github.com/misospace/pr-reviewer-action/issues/942)) ([0162197](https://github.com/misospace/pr-reviewer-action/commit/0162197f463a9f03d4826c4e8e0fec95c7080b5c)) - **review:** use selected model for direct smart routes ([#&#8203;933](https://github.com/misospace/pr-reviewer-action/issues/933)) ([d5923ee](https://github.com/misospace/pr-reviewer-action/commit/d5923ee63dd161953b48a4e68e69f2a1abbdf2e4)) - **test:** stop the semantic fixture racing git's background gc ([#&#8203;920](https://github.com/misospace/pr-reviewer-action/issues/920)) ([#&#8203;945](https://github.com/misospace/pr-reviewer-action/issues/945)) ([19f0f6b](https://github.com/misospace/pr-reviewer-action/commit/19f0f6b4dd554851a1899f5d1a6a4a9d8f513b4c)) - **tools:** credit changed files whose full diff is already in the review corpus ([#&#8203;930](https://github.com/misospace/pr-reviewer-action/issues/930)) ([0a5c700](https://github.com/misospace/pr-reviewer-action/commit/0a5c7002d31dee14fc923a11086d447f824449b0)) - **tools:** gh\_api decodes Contents API files instead of returning truncated base64 ([#&#8203;926](https://github.com/misospace/pr-reviewer-action/issues/926)) ([d1fdbd4](https://github.com/misospace/pr-reviewer-action/commit/d1fdbd4fc6e0d6579000ab615538d9b2b4fd613c)) - **tools:** mask repo\_contents files before truncating ([#&#8203;943](https://github.com/misospace/pr-reviewer-action/issues/943)) ([861a326](https://github.com/misospace/pr-reviewer-action/commit/861a3262aada2b3573c2f475455cfc5d9fff89fa)) ##### Chores - **action:** refresh the Marketplace listing metadata ([#&#8203;918](https://github.com/misospace/pr-reviewer-action/issues/918)) ([554500d](https://github.com/misospace/pr-reviewer-action/commit/554500d6ab81e9c8f01981693cbce8fb8cef59de)) ##### Documentation - split the README into focused pages and generate the inputs reference ([#&#8203;917](https://github.com/misospace/pr-reviewer-action/issues/917)) ([93118c6](https://github.com/misospace/pr-reviewer-action/commit/93118c6f2ac2d7096f930833f25cdc69beb91513)) </details> ### [`v3.1.0`](https://github.com/misospace/pr-reviewer-action/releases/tag/v3.1.0) [Compare Source](https://github.com/misospace/pr-reviewer-action/compare/v3.0.1...v3.1.0) ##### Features - **tools:** raise the native-loop budget and report a real cache hit ratio ([#&#8203;911](https://github.com/misospace/pr-reviewer-action/issues/911)) ([bf937d0](https://github.com/misospace/pr-reviewer-action/commit/bf937d011786fc9c45a5be56220ed17489bd6648)) ### [`v3.0.1`](https://github.com/misospace/pr-reviewer-action/releases/tag/v3.0.1) [Compare Source](https://github.com/misospace/pr-reviewer-action/compare/v3.0.0...v3.0.1) ##### Bug Fixes - **release:** track a source-vX.Y.Z anchor so release-please finds the last release ([#&#8203;907](https://github.com/misospace/pr-reviewer-action/issues/907)) ([443bf19](https://github.com/misospace/pr-reviewer-action/commit/443bf1998d61b87c47070103ccd84bee4582af5e)) - **v3:** read system-prompt-file from the base ref, not the run artifact dir ([#&#8203;905](https://github.com/misospace/pr-reviewer-action/issues/905)) ([de5c628](https://github.com/misospace/pr-reviewer-action/commit/de5c628a9a73ce9cf27a5999e8f62be76364d33d)) ### [`v3.0.0`](https://github.com/misospace/pr-reviewer-action/blob/HEAD/CHANGELOG.md#300-2026-09-30) [Compare Source](https://github.com/misospace/pr-reviewer-action/compare/v2.5.0...v3.0.0) ##### ⚠ BREAKING CHANGES - **review:** remove incremental-only escalation and review metadata state ([#&#8203;618](https://github.com/misospace/pr-reviewer-action/issues/618)) ([#&#8203;645](https://github.com/misospace/pr-reviewer-action/issues/645)) - **review:** remove carried findings and cross-run incremental evidence state ([#&#8203;617](https://github.com/misospace/pr-reviewer-action/issues/617)) ([#&#8203;644](https://github.com/misospace/pr-reviewer-action/issues/644)) - **review:** `review_scope`, `escalate_on_dirty_baseline`, `effective_review_scope`, `previous_head_sha`, and `baseline_clean` are removed; there is no replacement. ##### Features - **ci:** privilege-separated AI review for fork PRs ([#&#8203;748](https://github.com/misospace/pr-reviewer-action/issues/748)) ([76d9baf](https://github.com/misospace/pr-reviewer-action/commit/76d9baf66fb266a8703893983b4efe11c072f410)) - **context:** anchor edits to their enclosing function ([#&#8203;790](https://github.com/misospace/pr-reviewer-action/issues/790)) ([14a7cff](https://github.com/misospace/pr-reviewer-action/commit/14a7cffb45fc35aba3736ef6fcbce6523c1530bb)) - **context:** consumers of changed keys and referenced counterparts ([#&#8203;795](https://github.com/misospace/pr-reviewer-action/issues/795)) ([6376583](https://github.com/misospace/pr-reviewer-action/commit/63765835070a1093318f5df608d4809d956a105a)) - **context:** current PR metadata outranks earlier discussion ([#&#8203;812](https://github.com/misospace/pr-reviewer-action/issues/812)) ([f52f196](https://github.com/misospace/pr-reviewer-action/commit/f52f1966c39882bc3ab6d797a3bdeaaabf2c5353)) - **deep-review:** classifier-driven auto role selection ([#&#8203;633](https://github.com/misospace/pr-reviewer-action/issues/633)) ([#&#8203;655](https://github.com/misospace/pr-reviewer-action/issues/655)) ([3a1ea6f](https://github.com/misospace/pr-reviewer-action/commit/3a1ea6fdc9d7ff4a73b050393c635bb79ab37bdd)) - **deps:** update dependency [@&#8203;types/node](https://github.com/types/node) (24.13.6 → 24.19.0) ([#&#8203;760](https://github.com/misospace/pr-reviewer-action/issues/760)) ([77203aa](https://github.com/misospace/pr-reviewer-action/commit/77203aa9f27c64c990b02cf9e0ced5ed2c5b167a)) - **deps:** update dependency esbuild (0.25.5 → 0.28.2) ([#&#8203;693](https://github.com/misospace/pr-reviewer-action/issues/693)) ([3f6bfbf](https://github.com/misospace/pr-reviewer-action/commit/3f6bfbfd8e75fadd46c82e08a0362241b1d1c196)) - **deps:** update dependency typescript (5.8.3 → 7.0.2) ([#&#8203;696](https://github.com/misospace/pr-reviewer-action/issues/696)) ([1327d75](https://github.com/misospace/pr-reviewer-action/commit/1327d753cb46f8b91ec8da57294458c5a044248f)) - **eval:** blind adjudication tool for real-PR recall ([#&#8203;841](https://github.com/misospace/pr-reviewer-action/issues/841)) ([#&#8203;864](https://github.com/misospace/pr-reviewer-action/issues/864)) ([7dd6fcb](https://github.com/misospace/pr-reviewer-action/commit/7dd6fcbcfeaafc1d82139463304d481a35e1167b)) - **eval:** counterexample-falsification scoring and fixtures ([#&#8203;757](https://github.com/misospace/pr-reviewer-action/issues/757)) ([#&#8203;758](https://github.com/misospace/pr-reviewer-action/issues/758)) ([aaeac1f](https://github.com/misospace/pr-reviewer-action/commit/aaeac1fc70bd9275411b2aed264c5feb936842d3)) - **evals:** A/B specialist execution shapes ([#&#8203;635](https://github.com/misospace/pr-reviewer-action/issues/635)) ([#&#8203;691](https://github.com/misospace/pr-reviewer-action/issues/691)) ([ae8bb25](https://github.com/misospace/pr-reviewer-action/commit/ae8bb258026d878e0e30a7d12bb4a206c62a27a9)) - **evals:** add historical semantic regression corpus ([#&#8203;627](https://github.com/misospace/pr-reviewer-action/issues/627)) ([#&#8203;646](https://github.com/misospace/pr-reviewer-action/issues/646)) ([f86bf2c](https://github.com/misospace/pr-reviewer-action/commit/f86bf2cfb06fb9346d30aae575200cc1a017310a)) - **evals:** add PR [#&#8203;654](https://github.com/misospace/pr-reviewer-action/issues/654) execution-boundary fixtures ([#&#8203;659](https://github.com/misospace/pr-reviewer-action/issues/659)) ([#&#8203;664](https://github.com/misospace/pr-reviewer-action/issues/664)) ([894f092](https://github.com/misospace/pr-reviewer-action/commit/894f092f2d4c5df00af68abbb153e720c1015299)) - **evals:** harvest maintainer findings into the human-findings corpus ([#&#8203;798](https://github.com/misospace/pr-reviewer-action/issues/798)) ([#&#8203;800](https://github.com/misospace/pr-reviewer-action/issues/800)) ([4ad14e8](https://github.com/misospace/pr-reviewer-action/commit/4ad14e86a7a455b0ae9ae4e382400ce003119279)) - **evals:** real-PR recall corpus ([#&#8203;782](https://github.com/misospace/pr-reviewer-action/issues/782)) ([ea7649d](https://github.com/misospace/pr-reviewer-action/commit/ea7649dbc848754f6e8d25e75319acc0eff995f0)) - **platform:** resolve tangled platform and normalize Spindle runtime context ([#&#8203;793](https://github.com/misospace/pr-reviewer-action/issues/793)) ([b8b1aa8](https://github.com/misospace/pr-reviewer-action/commit/b8b1aa85823f41548115549c049c930e09c75dc3)) - **publish:** resolve review threads of superseded managed reviews ([#&#8203;769](https://github.com/misospace/pr-reviewer-action/issues/769)) ([6f5813a](https://github.com/misospace/pr-reviewer-action/commit/6f5813a42b0f418110abeaeb85f561218c8edcd6)) - **requirements:** harness-authored verification obligations in the ledger ([#&#8203;796](https://github.com/misospace/pr-reviewer-action/issues/796)) ([#&#8203;818](https://github.com/misospace/pr-reviewer-action/issues/818)) ([2a0d088](https://github.com/misospace/pr-reviewer-action/commit/2a0d08894bbf37d8ba61caf601bb7bf5490b2360)) - **review:** add failure-path contract auditing to the correctness pass ([#&#8203;648](https://github.com/misospace/pr-reviewer-action/issues/648)) ([ad79a2b](https://github.com/misospace/pr-reviewer-action/commit/ad79a2b101b225fa5a275574269051061dbe0376)) - **review:** budget and shape requests per tier ([#&#8203;668](https://github.com/misospace/pr-reviewer-action/issues/668)) ([08a05b3](https://github.com/misospace/pr-reviewer-action/commit/08a05b3b440de81d302fe4b612731e06bb8d608b)) - **review:** gate unknown requirements ([#&#8203;647](https://github.com/misospace/pr-reviewer-action/issues/647)) ([49190cb](https://github.com/misospace/pr-reviewer-action/commit/49190cb300518881935e8b2b1eb218f15ab71292)) - **review:** give smart escalation native tools ([#&#8203;665](https://github.com/misospace/pr-reviewer-action/issues/665)) ([9334f02](https://github.com/misospace/pr-reviewer-action/commit/9334f02473d4cfa4745fff139be0a9707b3cd650)) - **review:** independent specialist corpus and output budget ([#&#8203;632](https://github.com/misospace/pr-reviewer-action/issues/632)) ([#&#8203;652](https://github.com/misospace/pr-reviewer-action/issues/652)) ([082cf92](https://github.com/misospace/pr-reviewer-action/commit/082cf920bed81c6f1467592d8545829cb8bbca70)) - **review:** make must\_check a typed review obligation ([#&#8203;750](https://github.com/misospace/pr-reviewer-action/issues/750)) ([#&#8203;755](https://github.com/misospace/pr-reviewer-action/issues/755)) ([5900cfc](https://github.com/misospace/pr-reviewer-action/commit/5900cfc0b5f39f17e39901ae9b002672c11e3550)) - **review:** overlap specialist passes with CI gating ([#&#8203;634](https://github.com/misospace/pr-reviewer-action/issues/634)) ([#&#8203;654](https://github.com/misospace/pr-reviewer-action/issues/654)) ([38b79bb](https://github.com/misospace/pr-reviewer-action/commit/38b79bb3c927ddb608b1cc4b66f4cb733c1ae8ff)) - **review:** state outstanding human change requests in every review ([#&#8203;774](https://github.com/misospace/pr-reviewer-action/issues/774)) ([73246dd](https://github.com/misospace/pr-reviewer-action/commit/73246ddffa1ca100ce69b836c4f54ca5f2f05d94)) - **review:** unresolved review threads as review context with dispositions ([#&#8203;770](https://github.com/misospace/pr-reviewer-action/issues/770)) ([1591146](https://github.com/misospace/pr-reviewer-action/commit/15911464c1e32b23b093a6cb9974264f59a072ab)) - **routing:** make post-primary smart escalation reviewer-requested only ([#&#8203;721](https://github.com/misospace/pr-reviewer-action/issues/721)) ([#&#8203;743](https://github.com/misospace/pr-reviewer-action/issues/743)) ([9c13356](https://github.com/misospace/pr-reviewer-action/commit/9c133568e7bb6a62b6b8c19820bda367211c21cc)) - **tools:** per-tier request budget inputs ([#&#8203;768](https://github.com/misospace/pr-reviewer-action/issues/768)) ([3da29c5](https://github.com/misospace/pr-reviewer-action/commit/3da29c551b8ac17ee300c8c77a2c67024d3978f0)) - **tools:** stop rationing tool-loop evidence gathering ([#&#8203;794](https://github.com/misospace/pr-reviewer-action/issues/794)) ([#&#8203;797](https://github.com/misospace/pr-reviewer-action/issues/797)) ([373529e](https://github.com/misospace/pr-reviewer-action/commit/373529e455fa9047f3cd14b6fa6fc61b7e52002c)) - **tools:** structured budget telemetry for the native loop ([#&#8203;709](https://github.com/misospace/pr-reviewer-action/issues/709)) ([7c26e6d](https://github.com/misospace/pr-reviewer-action/commit/7c26e6da2b1908268e2fb544c0ac4731059fcccf)) - **tools:** tier-aware, exhaustion-aware native-loop request budgets ([#&#8203;707](https://github.com/misospace/pr-reviewer-action/issues/707)) ([e2ca972](https://github.com/misospace/pr-reviewer-action/commit/e2ca972cc764fc8715518169acc5bf5bf4aa5be7)) - **transport:** bound v3 model response buffering ([#&#8203;745](https://github.com/misospace/pr-reviewer-action/issues/745)) ([#&#8203;754](https://github.com/misospace/pr-reviewer-action/issues/754)) ([55b5762](https://github.com/misospace/pr-reviewer-action/commit/55b5762d8fca63dc3274bc64a9cc9df6067dc12d)) - **v3:** CI and specialists gate workloads ([#&#8203;807](https://github.com/misospace/pr-reviewer-action/issues/807)) ([c504e51](https://github.com/misospace/pr-reviewer-action/commit/c504e51c4f19afca2ff3069b23a1e7b8017ae976)) - **v3:** clamp max\_tokens to the provider's stated cap and retry once ([#&#8203;825](https://github.com/misospace/pr-reviewer-action/issues/825)) ([7ba3463](https://github.com/misospace/pr-reviewer-action/commit/7ba34634b6f3522dff828f1935007356ea09b3d5)) - **v3:** consistent re-reviews: CI-aware skip and resolved-blocker gate ([#&#8203;812](https://github.com/misospace/pr-reviewer-action/issues/812)) ([#&#8203;817](https://github.com/misospace/pr-reviewer-action/issues/817)) ([6fcbe1e](https://github.com/misospace/pr-reviewer-action/commit/6fcbe1e04e5a1b1e587349dd59d613f83532f85d)) - **v3:** define kebab-case action contract ([#&#8203;687](https://github.com/misospace/pr-reviewer-action/issues/687)) ([95c4039](https://github.com/misospace/pr-reviewer-action/commit/95c4039501bb01333543c00e67f9799929d62013)) - **v3:** deterministic context producers ([#&#8203;805](https://github.com/misospace/pr-reviewer-action/issues/805)) ([eea90ba](https://github.com/misospace/pr-reviewer-action/commit/eea90ba9c0ebbc3effb1877d5700c4453edf08d6)) - **v3:** end-to-end TypeScript orchestrator and v2 shadow comparison ([#&#8203;809](https://github.com/misospace/pr-reviewer-action/issues/809)) ([#&#8203;814](https://github.com/misospace/pr-reviewer-action/issues/814)) ([d48b4f2](https://github.com/misospace/pr-reviewer-action/commit/d48b4f2f39246253bffb093cd57ede6dbed4fcb0)) - **v3:** evidence providers, SARIF, image transport ([#&#8203;806](https://github.com/misospace/pr-reviewer-action/issues/806)) ([4777297](https://github.com/misospace/pr-reviewer-action/commit/47772971a30b8e4cc31651de399f23710ff6f588)) - **v3:** make harness obligations opt-in ([#&#8203;796](https://github.com/misospace/pr-reviewer-action/issues/796)) ([#&#8203;831](https://github.com/misospace/pr-reviewer-action/issues/831)) ([b7a6db4](https://github.com/misospace/pr-reviewer-action/commit/b7a6db46d72b13c193d8fc639588ac8eb2e344f7)) - **v3:** migrate classification, role selection, and requirement ledger to TypeScript ([#&#8203;675](https://github.com/misospace/pr-reviewer-action/issues/675)) ([#&#8203;708](https://github.com/misospace/pr-reviewer-action/issues/708)) ([39aa503](https://github.com/misospace/pr-reviewer-action/commit/39aa503cc736d45bfae9caeee22769d675ba558e)) - **v3:** migrate enforcement, managed metadata, publishing, and outputs ([#&#8203;680](https://github.com/misospace/pr-reviewer-action/issues/680)) ([#&#8203;778](https://github.com/misospace/pr-reviewer-action/issues/778)) ([db45c7e](https://github.com/misospace/pr-reviewer-action/commit/db45c7eeb5e4ad700bbeadf923aa82ece42ad872)) - **v3:** migrate platform adapters and precheck path to TypeScript ([#&#8203;674](https://github.com/misospace/pr-reviewer-action/issues/674)) ([#&#8203;705](https://github.com/misospace/pr-reviewer-action/issues/705)) ([567977e](https://github.com/misospace/pr-reviewer-action/commit/567977e0452b63222c09a740bf6fc5694b8e6a49)) - **v3:** migrate remaining [#&#8203;675](https://github.com/misospace/pr-reviewer-action/issues/675) context scope to TypeScript ([#&#8203;716](https://github.com/misospace/pr-reviewer-action/issues/716)) ([ff47ef3](https://github.com/misospace/pr-reviewer-action/commit/ff47ef36c68a4dd71a263a959e729bca5aa5c873)) - **v3:** opt-in claim falsification pass ([#&#8203;785](https://github.com/misospace/pr-reviewer-action/issues/785)) ([#&#8203;786](https://github.com/misospace/pr-reviewer-action/issues/786)) ([e95fbe6](https://github.com/misospace/pr-reviewer-action/commit/e95fbe614b59afc01d3f3f8883289fbf926e5ab6)) - **v3:** platform read seams ([#&#8203;803](https://github.com/misospace/pr-reviewer-action/issues/803)) ([1e9dd0c](https://github.com/misospace/pr-reviewer-action/commit/1e9dd0c6f58abeb57b94fed0fac824a28f454e4b)) - **v3:** port change\_anchors ([#&#8203;802](https://github.com/misospace/pr-reviewer-action/issues/802)) ([7236aa4](https://github.com/misospace/pr-reviewer-action/commit/7236aa4b278f91646247583155ea188f55b8ac2d)) - **v3:** port corpus assembly to TypeScript ([#&#8203;676](https://github.com/misospace/pr-reviewer-action/issues/676)) ([#&#8203;746](https://github.com/misospace/pr-reviewer-action/issues/746)) ([37242e2](https://github.com/misospace/pr-reviewer-action/commit/37242e2721bee599e018da2d29969b9f9278268b)) - **v3:** port routing, escalation, conversation, and native tool loop ([#&#8203;678](https://github.com/misospace/pr-reviewer-action/issues/678)) ([#&#8203;761](https://github.com/misospace/pr-reviewer-action/issues/761)) ([7137b88](https://github.com/misospace/pr-reviewer-action/commit/7137b88e0e5874ba474d18936107ed52b70667ed)) - **v3:** port the deep-review specialists logic ([#&#8203;776](https://github.com/misospace/pr-reviewer-action/issues/776)) ([#&#8203;780](https://github.com/misospace/pr-reviewer-action/issues/780)) ([08bd1d1](https://github.com/misospace/pr-reviewer-action/commit/08bd1d10e14a658055a268d89ba9ca09283f9a57)) - **v3:** port the model call layer to typescript ([#&#8203;703](https://github.com/misospace/pr-reviewer-action/issues/703)) ([309aabf](https://github.com/misospace/pr-reviewer-action/commit/309aabfd6fec55b226908094fcc534116c5e6d83)) - **v3:** production cutover to the TypeScript runtime ([#&#8203;706](https://github.com/misospace/pr-reviewer-action/issues/706)) ([#&#8203;815](https://github.com/misospace/pr-reviewer-action/issues/815)) ([f94bef8](https://github.com/misospace/pr-reviewer-action/commit/f94bef828391c9662da39a473d487e87576939b7)) - **v3:** prompt and message layer ([#&#8203;804](https://github.com/misospace/pr-reviewer-action/issues/804)) ([ebb231a](https://github.com/misospace/pr-reviewer-action/commit/ebb231a206dfaa16d0e17db81ea57d22a24acdfc)) - **v3:** record tool-budget provenance in telemetry and the review marker ([#&#8203;847](https://github.com/misospace/pr-reviewer-action/issues/847)) ([#&#8203;865](https://github.com/misospace/pr-reviewer-action/issues/865)) ([c794392](https://github.com/misospace/pr-reviewer-action/commit/c794392e6062d8c92fc9b0a212ebefe407f4887a)) - **v3:** repository config, trim dead inputs ([#&#8203;784](https://github.com/misospace/pr-reviewer-action/issues/784)) ([3cbfe6b](https://github.com/misospace/pr-reviewer-action/commit/3cbfe6b386500bc808108f98df7df2c8dbbbc66f)) - **v3:** scaffold typed runtime ([#&#8203;689](https://github.com/misospace/pr-reviewer-action/issues/689)) ([77736bf](https://github.com/misospace/pr-reviewer-action/commit/77736bfb50636d9ec27b9278800db7f685968567)) - **v3:** size-scaled tool budget and honest partial coverage ([#&#8203;810](https://github.com/misospace/pr-reviewer-action/issues/810)) ([#&#8203;813](https://github.com/misospace/pr-reviewer-action/issues/813)) ([eec5bc7](https://github.com/misospace/pr-reviewer-action/commit/eec5bc72250ec8c1f488241d0254f54376b644e2)) - **v3:** SSRF-safe linked-source fetch and render ([#&#8203;808](https://github.com/misospace/pr-reviewer-action/issues/808)) ([5ca8d80](https://github.com/misospace/pr-reviewer-action/commit/5ca8d803501c96d70cfe1fea06e7f53b7adf8d06)) - **v3:** strict verdict derived from open findings and coverage ([#&#8203;811](https://github.com/misospace/pr-reviewer-action/issues/811)) ([#&#8203;816](https://github.com/misospace/pr-reviewer-action/issues/816)) ([bf9ec54](https://github.com/misospace/pr-reviewer-action/commit/bf9ec5415c9f07117591e164306115664001c438)) - **v3:** tag findings outside the diff ([#&#8203;781](https://github.com/misospace/pr-reviewer-action/issues/781)) ([9c9b103](https://github.com/misospace/pr-reviewer-action/commit/9c9b103fbda39e32912573bdbb17ba09905a7939)) - **v3:** thread re-emission keeps original severity; current metadata outranks earlier discussion ([#&#8203;812](https://github.com/misospace/pr-reviewer-action/issues/812)) ([d21dc7d](https://github.com/misospace/pr-reviewer-action/commit/d21dc7d315545de7370956454b219947f65cb889)) - **v3:** typed gates, evidence, and lifecycle ([#&#8203;717](https://github.com/misospace/pr-reviewer-action/issues/717)) ([709bb6f](https://github.com/misospace/pr-reviewer-action/commit/709bb6f4217ae26c8fecb016b9e4f03d859cdc5b)) - **verdict:** coverage, docs and style findings cannot block on their own ([#&#8203;772](https://github.com/misospace/pr-reviewer-action/issues/772)) ([66cef8a](https://github.com/misospace/pr-reviewer-action/commit/66cef8a0dd21406810a0b51a9e814ae811a4a452)) - **verdict:** decisive finding first ([#&#8203;773](https://github.com/misospace/pr-reviewer-action/issues/773)) ([6ac94c5](https://github.com/misospace/pr-reviewer-action/commit/6ac94c560c1adfd36090b326bfe0967565d87ecc)) ##### Bug Fixes - **ci:** wall-bound GitHub gh api polling attempts ([#&#8203;688](https://github.com/misospace/pr-reviewer-action/issues/688)) ([d6889b4](https://github.com/misospace/pr-reviewer-action/commit/d6889b42652dfe405454075b1eba8830379d847d)) - **classifier:** require a real untrusted-path surface for path handling ([#&#8203;756](https://github.com/misospace/pr-reviewer-action/issues/756)) ([a3abef6](https://github.com/misospace/pr-reviewer-action/commit/a3abef68e916532643d6c8e8342f7678ad379721)) - **classifier:** stop misclassifying module imports as path handling ([#&#8203;720](https://github.com/misospace/pr-reviewer-action/issues/720)) ([9931ac6](https://github.com/misospace/pr-reviewer-action/commit/9931ac6276db3d654824b051494db91d00ab02ec)) - **dogfood:** exercise all specialist roles ([#&#8203;667](https://github.com/misospace/pr-reviewer-action/issues/667)) ([702675e](https://github.com/misospace/pr-reviewer-action/commit/702675e074abfb7a0c08bcbdf1f8d4a7646bb8e5)) - **dogfood:** make the v3 shadow actually run ([#&#8203;819](https://github.com/misospace/pr-reviewer-action/issues/819)) ([91df3a0](https://github.com/misospace/pr-reviewer-action/commit/91df3a0e1ab01085e3bcfdf26105542ed890948c)) - **enforcement:** run thread settlement and carry original severity ([#&#8203;812](https://github.com/misospace/pr-reviewer-action/issues/812)) ([7a7a35b](https://github.com/misospace/pr-reviewer-action/commit/7a7a35b6de5c2f03e8c9ee0eff433a26938f2385)) - **eval:** fail closed on an unusable pinned file manifest ([#&#8203;833](https://github.com/misospace/pr-reviewer-action/issues/833)) ([ed873b2](https://github.com/misospace/pr-reviewer-action/commit/ed873b2dcfc4557d5424950b88331fe0bc9943d7)) - **eval:** fixtures are same-repo PRs; configurable review timeout ([#&#8203;771](https://github.com/misospace/pr-reviewer-action/issues/771)) ([645feb6](https://github.com/misospace/pr-reviewer-action/commit/645feb60365e8b0545cc0e0d7f12026e0eec0eb0)) - **eval:** key adjudication scenarios by corpus entry id ([#&#8203;893](https://github.com/misospace/pr-reviewer-action/issues/893)) ([#&#8203;894](https://github.com/misospace/pr-reviewer-action/issues/894)) ([c5c1024](https://github.com/misospace/pr-reviewer-action/commit/c5c1024a09eb64c6eaa8d01abca13ee656da8228)) - **eval:** real-PR runs-per-mode, longer review timeout, bad corpus pin ([#&#8203;860](https://github.com/misospace/pr-reviewer-action/issues/860)) ([062c498](https://github.com/misospace/pr-reviewer-action/commit/062c498b9bc8ca14611f833757bc79ccbbd54715)) - **eval:** seed pinned replays' file list from the pinned diff ([6cc1113](https://github.com/misospace/pr-reviewer-action/commit/6cc1113c165432bf9ca40ae41b259f2d8f6ed945)) - **eval:** seed pinned replays' file list from the pinned diff ([#&#8203;833](https://github.com/misospace/pr-reviewer-action/issues/833)) ([c3db3c0](https://github.com/misospace/pr-reviewer-action/commit/c3db3c02ab4d6f7a08d8f101d4e48041f8b17420)) - **evals:** fail eval-harness when every run errors ([#&#8203;714](https://github.com/misospace/pr-reviewer-action/issues/714)) ([05aaafe](https://github.com/misospace/pr-reviewer-action/commit/05aaafee26f714451a4efd9889dab61ffd59adba)) - **evals:** harvester review follow-ups ([#&#8203;801](https://github.com/misospace/pr-reviewer-action/issues/801)) ([88b94fc](https://github.com/misospace/pr-reviewer-action/commit/88b94fc9f47c5cd0a92365eaa8252e52dec0eb03)) - **evals:** retain diffs for specialists fixtures ([#&#8203;713](https://github.com/misospace/pr-reviewer-action/issues/713)) ([fd4d8cd](https://github.com/misospace/pr-reviewer-action/commit/fd4d8cd402dbb2ee4929d9ee707171f388ee9423)) - **evals:** triage the 13 anchor-check flags from [#&#8203;861](https://github.com/misospace/pr-reviewer-action/issues/861) ([#&#8203;877](https://github.com/misospace/pr-reviewer-action/issues/877)) ([60dbe1a](https://github.com/misospace/pr-reviewer-action/commit/60dbe1abd78193d20990c52b3669eb24e44e1b2e)) - **eval:** weekly summary reads per-mode rates from mode\_summary ([#&#8203;715](https://github.com/misospace/pr-reviewer-action/issues/715)) ([#&#8203;744](https://github.com/misospace/pr-reviewer-action/issues/744)) ([4b17206](https://github.com/misospace/pr-reviewer-action/commit/4b17206388a96843cca204cee4d176a4da84f771)) - **image:** validate registry repository paths ([#&#8203;724](https://github.com/misospace/pr-reviewer-action/issues/724)) ([864ffc1](https://github.com/misospace/pr-reviewer-action/commit/864ffc1a1bf8066b38a6cc328deda9422673f23c)) - keep reviewed checkout off python sys.path ([#&#8203;788](https://github.com/misospace/pr-reviewer-action/issues/788)) ([4c630a5](https://github.com/misospace/pr-reviewer-action/commit/4c630a5ba2d385b17f1f7bf9bd7d536ce36ace62)) - **model:** guarantee at least one call attempt per tier ([#&#8203;887](https://github.com/misospace/pr-reviewer-action/issues/887)) ([55eeaf8](https://github.com/misospace/pr-reviewer-action/commit/55eeaf802423cfaeaff1446f659e0d262d76a1ed)) - **native-loop:** consume recoverable verdict retry, no duplicate synthesis ([#&#8203;637](https://github.com/misospace/pr-reviewer-action/issues/637)) ([#&#8203;651](https://github.com/misospace/pr-reviewer-action/issues/651)) ([345351c](https://github.com/misospace/pr-reviewer-action/commit/345351c2bf2074b5480d574aef500ebe69f82163)) - **platform:** body-edit cutoff via GraphQL lastEditedAt; reapply [#&#8203;812](https://github.com/misospace/pr-reviewer-action/issues/812) rule post-CI ([7a19eaf](https://github.com/misospace/pr-reviewer-action/commit/7a19eaf66b061511e53068fa8104c2af650a6d52)) - **platform:** one atomic body snapshot per metadata pass ([#&#8203;812](https://github.com/misospace/pr-reviewer-action/issues/812) review) ([ac09f43](https://github.com/misospace/pr-reviewer-action/commit/ac09f437f50d790af98d706447e76a4fcfb80a3d)) - **platform:** valid PR-thread comment order ([#&#8203;631](https://github.com/misospace/pr-reviewer-action/issues/631)) ([#&#8203;649](https://github.com/misospace/pr-reviewer-action/issues/649)) ([d45a273](https://github.com/misospace/pr-reviewer-action/commit/d45a2737b6098bff3369a46d58c8c6911fd9eb6c)) - **precheck:** link issues referenced by PR title and non-closing body forms ([#&#8203;879](https://github.com/misospace/pr-reviewer-action/issues/879)) ([e481bd6](https://github.com/misospace/pr-reviewer-action/commit/e481bd66de57f8e463a0f3229ca83a8b41175699)), closes [#&#8203;872](https://github.com/misospace/pr-reviewer-action/issues/872) - **precheck:** pin config reads to one fd ([#&#8203;723](https://github.com/misospace/pr-reviewer-action/issues/723)) ([2ab2a3a](https://github.com/misospace/pr-reviewer-action/commit/2ab2a3a5b35ebe5a5e174fdf8399baef195979c8)) - **publish:** keep the endpoint URL out of published reviews ([#&#8203;836](https://github.com/misospace/pr-reviewer-action/issues/836)) ([7a788da](https://github.com/misospace/pr-reviewer-action/commit/7a788da1bd2017774c66ff985a81469ca5a848f9)) - **redact:** use a non-alphanumeric marker for known-secret masking ([#&#8203;888](https://github.com/misospace/pr-reviewer-action/issues/888)) ([939e0fc](https://github.com/misospace/pr-reviewer-action/commit/939e0fc35b480615a65f6a64a457c874dcef5cd6)) - **repo-map:** avoid auth filename backtracking ([#&#8203;722](https://github.com/misospace/pr-reviewer-action/issues/722)) ([d70bc95](https://github.com/misospace/pr-reviewer-action/commit/d70bc952d863de3acd0a2c4216e32468717e4955)) - restore the reviewer's evidence gathering (v2 + v3) ([#&#8203;759](https://github.com/misospace/pr-reviewer-action/issues/759)) ([339d998](https://github.com/misospace/pr-reviewer-action/commit/339d998b6e521776be51b02b08cb8800c574c4ad)) - **reviewer:** keep sanitizer redaction from garbling committed source ([#&#8203;880](https://github.com/misospace/pr-reviewer-action/issues/880)) ([791c85f](https://github.com/misospace/pr-reviewer-action/commit/791c85ffdf4ade6f03707842ff943c6ce821f85d)) - **run:** streamed tool calls, tool cwd and specialist artifact root ([#&#8203;820](https://github.com/misospace/pr-reviewer-action/issues/820)) ([515943e](https://github.com/misospace/pr-reviewer-action/commit/515943e282c2ef893ffaf0a3b7a1bff9abb108bd)) - **standards:** resolve the standards file from the base ref, not PR head ([#&#8203;890](https://github.com/misospace/pr-reviewer-action/issues/890)) ([59d93f2](https://github.com/misospace/pr-reviewer-action/commit/59d93f2cc237313f328fe0a9fa81ebbe6f1f30af)) - **tests:** clear .test-build and make git operations hermetic ([#&#8203;858](https://github.com/misospace/pr-reviewer-action/issues/858)) ([27d4b95](https://github.com/misospace/pr-reviewer-action/commit/27d4b9510596b5baba8457e0ff74299b01032009)) - **tool-loop:** honour an empty ai\_temperature on native\_loop planning turns ([#&#8203;747](https://github.com/misospace/pr-reviewer-action/issues/747)) ([8f3c0a6](https://github.com/misospace/pr-reviewer-action/commit/8f3c0a68fe42c16bb63b92d230df46e3d1854f09)) - **tooling:** refuse redirects on token-bearing HTTP calls ([#&#8203;859](https://github.com/misospace/pr-reviewer-action/issues/859)) ([860b56d](https://github.com/misospace/pr-reviewer-action/commit/860b56d6df7a637f92586a533b1bb1951137db25)) - **tools:** keep tool-harness.json valid under redaction and fail closed when unreadable ([#&#8203;899](https://github.com/misospace/pr-reviewer-action/issues/899)) ([#&#8203;900](https://github.com/misospace/pr-reviewer-action/issues/900)) ([97f0b0d](https://github.com/misospace/pr-reviewer-action/commit/97f0b0dc0e3e391b96cb10ce42a0748bf303778b)) - **tools:** scale loop round cap with the tool budget ([#&#8203;895](https://github.com/misospace/pr-reviewer-action/issues/895)) ([#&#8203;897](https://github.com/misospace/pr-reviewer-action/issues/897)) ([a98bdf5](https://github.com/misospace/pr-reviewer-action/commit/a98bdf5d0925dc9dc43cff85d8e738fe8ad983d2)) - **transport:** surface HTTP status and body detail on model-call errors ([#&#8203;862](https://github.com/misospace/pr-reviewer-action/issues/862)) ([ec25b3f](https://github.com/misospace/pr-reviewer-action/commit/ec25b3fd72ba2cd31574205ef658d53512de49f9)) - **v3:** mask secrets in model errors carried by a 200 reply ([#&#8203;868](https://github.com/misospace/pr-reviewer-action/issues/868)) ([#&#8203;869](https://github.com/misospace/pr-reviewer-action/issues/869)) ([ae72527](https://github.com/misospace/pr-reviewer-action/commit/ae72527ce3f3b5e262b81c06d31de2f3a0cbc82f)) - **v3:** normalize labeled-event shape so ai-review forces a re-review ([#&#8203;896](https://github.com/misospace/pr-reviewer-action/issues/896)) ([241dd2d](https://github.com/misospace/pr-reviewer-action/commit/241dd2d764be4c0db6f61f57f6fd01666c4a6052)) - **v3:** publish the model-failure notice as request\_changes ([#&#8203;863](https://github.com/misospace/pr-reviewer-action/issues/863)) ([#&#8203;866](https://github.com/misospace/pr-reviewer-action/issues/866)) ([fb49242](https://github.com/misospace/pr-reviewer-action/commit/fb4924221dada0cc8fe7dc9a669372a3eb526e34)) - **v3:** run never reads artifacts from the PR checkout ([#&#8203;838](https://github.com/misospace/pr-reviewer-action/issues/838)) ([#&#8203;870](https://github.com/misospace/pr-reviewer-action/issues/870)) ([6080648](https://github.com/misospace/pr-reviewer-action/commit/60806486eb1f6aee684206ed6655fe8ea143d0da)) - **verdict:** make non-blocking finding categories opt-in ([#&#8203;775](https://github.com/misospace/pr-reviewer-action/issues/775)) ([1b83be8](https://github.com/misospace/pr-reviewer-action/commit/1b83be80c4c326f6c9ef00d2daaf97b670065afa)) - **verdict:** repair invalid escapes before accepting a partial candidate ([#&#8203;767](https://github.com/misospace/pr-reviewer-action/issues/767)) ([d9b1a12](https://github.com/misospace/pr-reviewer-action/commit/d9b1a12cbded169dae07a2ebb50646a084879b1d)) ##### Chores - clear code-scanning alerts before v3.0.0 ([#&#8203;891](https://github.com/misospace/pr-reviewer-action/issues/891)) ([6c35674](https://github.com/misospace/pr-reviewer-action/commit/6c35674c53f2dd19065be8ff98e2674f237dece1)) - remove orphaned .candidates.json from repository root ([#&#8203;822](https://github.com/misospace/pr-reviewer-action/issues/822)) ([#&#8203;834](https://github.com/misospace/pr-reviewer-action/issues/834)) ([20fd562](https://github.com/misospace/pr-reviewer-action/commit/20fd5623b3d8070d66ce857bdd41cac0aeace4d3)) - **v3:** wave 2 teardown: freeze parity on v2 goldens, delete the remaining v2 code ([#&#8203;681](https://github.com/misospace/pr-reviewer-action/issues/681)) ([#&#8203;853](https://github.com/misospace/pr-reviewer-action/issues/853)) ([a8c4d14](https://github.com/misospace/pr-reviewer-action/commit/a8c4d1487fd470b36afb1fe174e349fae18f6694)) ##### Documentation - add a v2 to v3 upgrade guide ([#&#8203;857](https://github.com/misospace/pr-reviewer-action/issues/857)) ([7a018e3](https://github.com/misospace/pr-reviewer-action/commit/7a018e391ea49c65bfe9ec066fec9a811ca9f267)) - **agents:** slim AGENTS.md to durable rules, move detail to docs ([#&#8203;751](https://github.com/misospace/pr-reviewer-action/issues/751)) ([#&#8203;753](https://github.com/misospace/pr-reviewer-action/issues/753)) ([85ae3c3](https://github.com/misospace/pr-reviewer-action/commit/85ae3c375cae3ef62bdf77ba139c5f142d8168ab)) - **architecture:** keep three\_call specialist shape on benchmark evidence ([#&#8203;704](https://github.com/misospace/pr-reviewer-action/issues/704)) ([#&#8203;710](https://github.com/misospace/pr-reviewer-action/issues/710)) ([4403d62](https://github.com/misospace/pr-reviewer-action/commit/4403d62708dd0578d73377a570ebcb6081e1efba)) - **runtime:** choose composite Node boundary ([#&#8203;682](https://github.com/misospace/pr-reviewer-action/issues/682)) ([3a362a2](https://github.com/misospace/pr-reviewer-action/commit/3a362a2f19ed61a3db2affc1fa62e0620786604e)) - v3 examples and kebab-case input names ([#&#8203;848](https://github.com/misospace/pr-reviewer-action/issues/848), [#&#8203;850](https://github.com/misospace/pr-reviewer-action/issues/850), [#&#8203;851](https://github.com/misospace/pr-reviewer-action/issues/851)) ([#&#8203;849](https://github.com/misospace/pr-reviewer-action/issues/849)) ([cd0d29c](https://github.com/misospace/pr-reviewer-action/commit/cd0d29ce91d47ed135e3ee619bd3924a5c5ccff6)) - **v3-migration:** record the thread-severity and superseded-discussion change ([04fa6ee](https://github.com/misospace/pr-reviewer-action/commit/04fa6ee8c7eb65a54bc7d254e3cd8dfc06d1d8e6)) - **v3:** plan the v2 teardown file-by-file ([#&#8203;706](https://github.com/misospace/pr-reviewer-action/issues/706)) ([#&#8203;827](https://github.com/misospace/pr-reviewer-action/issues/827)) ([61314cc](https://github.com/misospace/pr-reviewer-action/commit/61314cc57a908675d826cbc5a082c812d10a3cbb)) ##### Refactors - **action:** dedupe step env blocks into a shared $GITHUB\_ENV export ([#&#8203;653](https://github.com/misospace/pr-reviewer-action/issues/653)) ([00e7b01](https://github.com/misospace/pr-reviewer-action/commit/00e7b0172b38308dce3b1259d4151f195607de9c)) - **review:** collapse the review corpus to one full-PR path ([#&#8203;643](https://github.com/misospace/pr-reviewer-action/issues/643)) ([ec9e038](https://github.com/misospace/pr-reviewer-action/commit/ec9e038763e804dca2d8539a868026a31861c852)), closes [#&#8203;616](https://github.com/misospace/pr-reviewer-action/issues/616) - **review:** remove carried findings and cross-run incremental evidence state ([#&#8203;617](https://github.com/misospace/pr-reviewer-action/issues/617)) ([#&#8203;644](https://github.com/misospace/pr-reviewer-action/issues/644)) ([07fb9d4](https://github.com/misospace/pr-reviewer-action/commit/07fb9d4629ff23ee2054e89a80bf87bc72c50bd1)) - **review:** remove incremental-only escalation and review metadata state ([#&#8203;618](https://github.com/misospace/pr-reviewer-action/issues/618)) ([#&#8203;645](https://github.com/misospace/pr-reviewer-action/issues/645)) ([a9dde07](https://github.com/misospace/pr-reviewer-action/commit/a9dde07c84b24e0072afad6a80792eaec0c74d74)) - **review:** remove the review-scope selection seam ([#&#8203;615](https://github.com/misospace/pr-reviewer-action/issues/615)) ([#&#8203;638](https://github.com/misospace/pr-reviewer-action/issues/638)) ([e2d74c2](https://github.com/misospace/pr-reviewer-action/commit/e2d74c2e9c42765d7a1552fb13d999cfc872ffd6)) - **review:** split render\_linked\_sources into single-purpose helpers ([#&#8203;640](https://github.com/misospace/pr-reviewer-action/issues/640)) ([#&#8203;650](https://github.com/misospace/pr-reviewer-action/issues/650)) ([2af34b8](https://github.com/misospace/pr-reviewer-action/commit/2af34b8f7793eeb7f7237246f4a171fb244830ca)) </details> --- ### Configuration 📅 **Schedule**: (in timezone Europe/Rome) - Branch creation - At any time (no schedule defined) - Automerge - At any time (no schedule defined) 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR has been generated by [Mend Renovate CLI](https://github.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0NC4xMTUuMTMiLCJ1cGRhdGVkSW5WZXIiOiI0NC4xMzMuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOlsicmVub3ZhdGUvZ2l0aHViLWFjdGlvbiIsInJlbm92YXRlL2dpdGh1Yi1yZWxlYXNlIiwidHlwZS9tYWpvciJdfQ==-->
ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.0.0)
Some checks failed
Konflate 0 resources changed
Details
Labeler / Labeler (pull_request) Successful in 3s
Details
AI PR Review / AI PR Review (pull_request) Failing after 7s
Details
Lint / actionlint (pull_request) Successful in 8s
Details
Lint / yamllint (pull_request) Successful in 12s
Details
f5c132235b
lab-assistant-bot commented 2026-10-01 01:02:25 +02:00
Collaborator

No rendered changes.

konflate 0.6.4 · rendered f6a8c39 · full diff →

<!-- konflate:pr-2258 --> No rendered changes. <sub>konflate 0.6.4 · rendered `f6a8c39` · [full diff →](https://konflate.aresu.eu/#/pr/2258)</sub>
renovate-bot changed title from ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.0.0) to ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.0.1) 2026-10-01 02:01:47 +02:00
renovate-bot force-pushed renovate/https-github.com-misospace-pr-reviewer-action-3.x from f5c132235b
Some checks failed
Konflate 0 resources changed
Details
Labeler / Labeler (pull_request) Successful in 3s
Details
AI PR Review / AI PR Review (pull_request) Failing after 7s
Details
Lint / actionlint (pull_request) Successful in 8s
Details
Lint / yamllint (pull_request) Successful in 12s
Details
to c8237c743c
Some checks failed
Konflate 0 resources changed
Details
Labeler / Labeler (pull_request) Successful in 3s
Details
Lint / actionlint (pull_request) Successful in 9s
Details
AI PR Review / AI PR Review (pull_request) Failing after 7s
Details
Lint / yamllint (pull_request) Successful in 12s
Details
2026-10-01 02:01:47 +02:00 Compare
renovate-bot force-pushed renovate/https-github.com-misospace-pr-reviewer-action-3.x from c8237c743c
Some checks failed
Konflate 0 resources changed
Details
Labeler / Labeler (pull_request) Successful in 3s
Details
Lint / actionlint (pull_request) Successful in 9s
Details
AI PR Review / AI PR Review (pull_request) Failing after 7s
Details
Lint / yamllint (pull_request) Successful in 12s
Details
to b3b1a0bf68
Some checks failed
Labeler / Labeler (pull_request) Successful in 3s
Details
AI PR Review / AI PR Review (pull_request) Failing after 8s
Details
Lint / actionlint (pull_request) Successful in 9s
Details
Lint / yamllint (pull_request) Successful in 12s
Details
Konflate 0 resources changed
Details
2026-10-01 05:01:48 +02:00 Compare
renovate-bot changed title from ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.0.1) to ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.1.0) 2026-10-01 05:01:48 +02:00
renovate-bot force-pushed renovate/https-github.com-misospace-pr-reviewer-action-3.x from b3b1a0bf68
Some checks failed
Labeler / Labeler (pull_request) Successful in 3s
Details
AI PR Review / AI PR Review (pull_request) Failing after 8s
Details
Lint / actionlint (pull_request) Successful in 9s
Details
Lint / yamllint (pull_request) Successful in 12s
Details
Konflate 0 resources changed
Details
to 4fa078e4a9
Some checks failed
Labeler / Labeler (pull_request) Successful in 4s
Details
Lint / actionlint (pull_request) Failing after 6s
Details
AI PR Review / AI PR Review (pull_request) Failing after 7s
Details
Lint / yamllint (pull_request) Failing after 11s
Details
Konflate 0 resources changed
Details
2026-10-03 05:04:06 +02:00 Compare
renovate-bot changed title from ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.1.0) to ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.2.0) 2026-10-03 05:04:06 +02:00
renovate-bot changed title from ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.2.0) to ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.3.0) 2026-10-05 06:03:34 +02:00
renovate-bot force-pushed renovate/https-github.com-misospace-pr-reviewer-action-3.x from 4fa078e4a9
Some checks failed
Labeler / Labeler (pull_request) Successful in 4s
Details
Lint / actionlint (pull_request) Failing after 6s
Details
AI PR Review / AI PR Review (pull_request) Failing after 7s
Details
Lint / yamllint (pull_request) Failing after 11s
Details
Konflate 0 resources changed
Details
to f6a8c394fe
Some checks failed
Labeler / Labeler (pull_request) Successful in 3s
Details
Lint / actionlint (pull_request) Failing after 7s
Details
AI PR Review / AI PR Review (pull_request) Failing after 9s
Details
Lint / yamllint (pull_request) Failing after 13s
Details
Konflate 0 resources changed
Details
2026-10-05 06:03:35 +02:00 Compare
renovate-bot changed title from ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.3.0) to ci(github-action)!: Update action https://github.com/misospace/pr-reviewer-action (v2.5.0 ➔ v3.3.0) - autoclosed 2026-10-05 22:03:52 +02:00
renovate-bot closed this pull request 2026-10-05 22:03:52 +02:00
Some checks failed
Labeler / Labeler (pull_request) Successful in 3s
Details
Lint / actionlint (pull_request) Failing after 7s
Details
AI PR Review / AI PR Review (pull_request) Failing after 9s
Details
Lint / yamllint (pull_request) Failing after 13s
Details
Konflate 0 resources changed
Details

Pull request closed

This pull request cannot be reopened because the branch was deleted.
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels   
area/bootstrap

   
area/ci

   
area/kubernetes

   
bug
Something isn't working

  
documentation
Improvements or additions to documentation

  
duplicate
This issue or pull request already exists

  
enhancement
New feature or request

  
good first issue
Good for newcomers

  
help wanted
Extra attention is needed

  
invalid
This doesn't seem right

  
question
Further information is requested

  
renovate/container

   
renovate/github-action

   
renovate/github-release

   
renovate/grafana-dashboard

   
renovate/helm

   
renovate/terraform

   
type/digest

   
type/major

   
type/minor

   
type/patch

   
wontfix
This will not be worked on

No labels
area/bootstrap
area/ci
area/kubernetes
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
question
renovate/container
renovate/github-action
renovate/github-release
renovate/grafana-dashboard
renovate/helm
renovate/terraform
type/digest
type/major
type/minor
type/patch
wontfix
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
2 participants
Notifications
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
GiorgioAresu/home-ops!2258
No description provided.