Skip to content

chore(deps): protoagent 0.108.0 base + pr-reviewer v0.16.0#14

Merged
mabry1985 merged 1 commit into
mainfrom
chore/base-0.108.0-plugin-0.16.0
Jul 23, 2026
Merged

chore(deps): protoagent 0.108.0 base + pr-reviewer v0.16.0#14
mabry1985 merged 1 commit into
mainfrom
chore/base-0.108.0-plugin-0.16.0

Conversation

@mabry1985

Copy link
Copy Markdown
Member

The base bump is the point of this one.

The fan-out fix finally takes effect

protoAgent#2168 — recipe-declared fan-out width + per-step timings — landed after the v0.107.0 tag. So max_concurrency: 5 in the review recipe has been inert since v0.12.0: the five finders kept running as 4+1 under the host's default cap of 4, paying the slowest finder's cost twice while the second wave ran a single step alone and saved nothing.

Measured over 60 reviews before the fix:

code-review-structural (5 finders)  n=53  p50 458s      F + T = 322
code-review            (4 finders)  n=7   p50 322s  →  2F + T = 458
                                              →  F ≈ 136s,  T ≈ 186s

Expected saving: ~136s per structural review, about 30%.

And step_s starts flowing

Every review so far recorded step_s: null and slowest_step: null, because the timings come from the engine change in the same PR. The split above is an estimate inferred from two recipe populations; after this it is measured.

That matters for what comes next: the sequential tail (synthesize → verify → report, ~186s) is now the larger half, and synthesize is close to a no-op when there's one finding. But optimising it before the numbers exist is how you make something slower while believing otherwise.

Plugin v0.14.1 → v0.16.0

version what
v0.14.2 Grounding no longer mistakes prose for a code quote — it downgraded a true finding on projectBoard-plugin#94 within an hour of deploying
v0.15.0 @vera review — on-demand panel, admin-gated, permission resolved server-side (#28 slice 1)
v0.16.0 Every guard reports its decision, not only when it fires; and a finding with line: 0 no longer silently blocks convergence forever

The observability one is worth calling out: four rules now sit between the panel's findings and the merge gate, and three of them were only visible when they acted — so "ran and correctly declined" was indistinguishable from "never ran". Twice that meant verifying a guard by hand-fetching blobs from GitHub.

Verification

Base and verified_against moved together (they must stay in step). Upstream main green at 260 tests; v0.16.0 tagged.

Merging deploys — GHCR rebuild then watchtower rolls Vera in ~60s.

🤖 Generated with Claude Code

The base bump is the point of this one: protoAgent#2168 (recipe-declared
fan-out width + per-step timings) landed AFTER the v0.107.0 tag, so
`max_concurrency: 5` in the review recipe has been inert since v0.12.0 — the
five finders kept running as 4+1 under the host's default cap of 4, paying the
slowest finder's cost twice.

Measured over 60 reviews before the fix: the five-finder recipe's p50 was 458s
against 322s for the otherwise-identical four-finder one, which solves to ~136s
per finder and ~186s for the sequential synthesize -> verify -> report tail.
Expected saving ~136s per structural review, about 30%.

It also starts `step_s` / `slowest_step` flowing. Every review so far has
recorded them as null, so the split above is an estimate inferred from two
recipe populations; after this it is measured. The sequential tail is the larger
half and is the next thing worth attacking — but not before the numbers exist.

Plugin v0.14.1 -> v0.16.0 brings:
  v0.14.2  grounding no longer mistakes prose for a code quote (it downgraded a
           TRUE finding on projectBoard-plugin#94 within an hour of deploying)
  v0.15.0  `@vera review` — on-demand panel, admin-gated, server-side permission
  v0.16.0  every guard reports its DECISION, not only when it fires; and a
           finding with `line: 0` no longer silently blocks convergence forever

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@mabry1985
mabry1985 merged commit c85928e into main Jul 23, 2026
1 check passed
@mabry1985
mabry1985 deleted the chore/base-0.108.0-plugin-0.16.0 branch July 23, 2026 09:29
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant