From PR #18's own review — the FIRST run with consensus consolidation live (it
posted one ranked consensus comment across 7 models instead of 7 walls).
- Anchor inline comments to ADDED lines only (parseDiffNewLines no longer
records context lines): Gitea reliably accepts comments on added lines, so the
all-or-nothing review POST won't be rejected for an off-change anchor.
- Span-scan anchoring (anchorLine): a cluster whose min line is just outside the
diff still anchors if any line in its [line,maxLine] span is an added line.
- Path normalization (normPath) on both diff and finding paths, so "./pkg/x.go"
vs "pkg/x.go" vs a "b/"-prefixed diff path all match (and the comment Path is
the normalized repo-relative one).
- deletePriorReviews: paginate (cap 10 pages) and bail on a non-2xx GET, so a
stale marked review past page 1 is still removed and the "replace not stack"
guarantee holds better under failure.
- mergeIntoCluster backfills an empty title/detail from any report (not only a
strictly-higher-severity one).
- Rename inlineReviewHTTPTime -> inlineReviewHTTPTimeout (emit.go convention).
Graded the run's 36 findings in gadfly-reports (notably a 7/7-consensus
deletePriorReviews error-handling finding — the consensus signal working as
intended). XSS-framed findings marked false (Gitea sanitizes review markdown);
trusted-input and gofmt-clean ones likewise. Tests updated for added-only
anchoring + span scan. gofmt/vet/bash -n clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Phase 3. Alongside the consensus comment, the consolidator now posts ONE Gitea
pull review (state COMMENT — advisory, never request-changes/approve, so it can
never block a merge) whose inline comments anchor each consensus finding to the
exact changed line. The "reviewer integrated with Gitea" the project wanted,
without the blocking.
- review.go: a unified-diff parser (parseDiffNewLines — hunk-length-bounded, so a
content line that looks like "+++ "/"@@" isn't mistaken for a header), inline
comment building filtered to lines actually in the diff, and the Gitea reviews
API client (raw new_position/event=COMMENT fields). Re-runs delete the prior
gadfly review (body marker) instead of stacking.
- consensus.go: cluster.detail restored (now consumed by the inline comment body);
renderConsensus takes precomputed clusters; runConsolidate clusters once and
drives both the consensus comment and the inline review.
- entrypoint.sh: fetch the PR diff and pass GADFLY_DIFF_FILE to the consolidator
(GITEA_API/TOKEN/PR already in its env).
- README + reusable workflow (`inline_review` input) + entrypoint docs.
Best-effort throughout: no diff / API creds, or any post error → the consensus
comment still stands; the review is never required and never blocks. Validated
the Gitea reviews API + line anchoring live before building. Tests: diff parser
(incl. header-like content + multi-file), inline filtering. gofmt/vet/bash -n clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Phase 2: gadfly's own multi-model reviews now post ONE cross-model consensus
comment instead of N per-model comments. External consumers re-pin separately.
[skip ci]
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Makes the Phase 1 gadfly-findings contract live for gadfly's own dogfood
reviews (the local-ref reusable). External consumers re-pin separately.
[skip ci]
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Centralizes the consumer stub into a reusable Gitea workflow
(.gitea/workflows/review-reusable.yml, workflow_call + defaulted inputs +
secrets: inherit); gadfly's own dogfood is now a thin caller of it, which
proved end-to-end that github.event context propagates into the reusable
on this act_runner. Adds the slim examples/reusable.yml stub + docs.
Folded in the swarm's findings: timeout_minutes default 30->45, map
GADFLY_API_KEY, explicit permissions block, drop the dead specialist_suite
input, and harden the example's actor gate. ~70 findings graded.
Completes the gadfly-games build (Phases 1-4 + quality fixes).
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Co-authored-by: Steve Dudenhoeffer <[email protected]>
Co-committed-by: Steve Dudenhoeffer <[email protected]>
Bump majordomo to the latest build and accept every llama-swap spelling
(llama-swap/llama-swaps + un-hyphenated llamaswap/llamaswaps) in gadfly's
endpoint switches; the LLM_* llama-swap(s):// DSN path already worked via
majordomo.Parse. README + error messages + endpointProvider alias tests.
Swarm review: 8/9 clean; qwen3-coder's "Blocking" was a false positive
(claimed llamaswap was untested — it has dedicated test cases). Folded in
its one fair nit (README now lists the un-hyphenated aliases).
gofmt clean, go vet quiet, go test -race green.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Co-authored-by: Steve Dudenhoeffer <[email protected]>
Co-committed-by: Steve Dudenhoeffer <[email protected]>
Adds claude-code/opus:max to the dogfood swarm and pins to :sha-c342bdb
(which has the :thinking parse). Claude Code lineup is now sonnet + opus +
opus:max. All three ran end-to-end on this PR's own review; 0 findings
(clean PR + the telemetry fix suppressing phantom clean-verification
findings — working as intended).
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Co-authored-by: Steve Dudenhoeffer <[email protected]>
Co-committed-by: Steve Dudenhoeffer <[email protected]>
Adds claude-code/opus to gadfly's dogfood swarm (both sonnet and opus run
end-to-end), bumps the image pin to :sha-80d8f53 so the clean-lens
telemetry fix is live, and adds engine support for a
"claude-code/<model>:max" extended-thinking spec (MAX_THINKING_TOKENS,
best-effort). Validated: only 13 findings on this clean PR vs 43 on the
comparable #4 — the telemetry fix works.
Folded in the swarm's two real findings: a runPass env-injection test and
keeping MAX_THINKING_TOKENS in claudeEnv. Follow-up enables
claude-code/opus:max once this image builds.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Co-authored-by: Steve Dudenhoeffer <[email protected]>
Co-committed-by: Steve Dudenhoeffer <[email protected]>
emit() now skips findings extraction for a "No material issues found"
lens (its path:line refs are verification notes, not problems), fixing
the FP inflation that penalized thorough clean-pass reviewers. Also trims
the dogfood swarm to the strong reviewers: drops m5/qwen3.6 (last local
lane), gemma4, gpt-oss:120b, and kimi-k2.7-code — leaving 6 cloud +
claude-code/sonnet.
Fittingly, PR #4's own 11-model review produced 43 findings that were ALL
clean-verification bullets (zero real) — a live demonstration of the bug
this fixes. gofmt clean, go vet quiet, go test -race green.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Co-authored-by: Steve Dudenhoeffer <[email protected]>
Co-committed-by: Steve Dudenhoeffer <[email protected]>
Phase 2: bump majordomo to latest and wire its new llamaswap provider
into gadfly's endpoint switches; add claude-code/sonnet to gadfly's own
dogfood swarm (pin :sha-86f12c1, map CLAUDE_CODE_OAUTH_TOKEN) so the
Phase-1 engine runs as a live competitor; document the Ollama-through-CC
ANTHROPIC_BASE_URL proxy path as example-only.
The 11-model swarm (incl. claude-code/sonnet) reviewed it; 52 findings
graded via the MCP. Folded in the two real ones: a llamaswap
endpointProvider test (caught by claude-code/sonnet, citing CLAUDE.md)
and adding "openai-compatible" to the provider error messages (gpt-oss).
gofmt clean, go vet quiet, go build + go test -race green.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Co-authored-by: Steve Dudenhoeffer <[email protected]>
Co-committed-by: Steve Dudenhoeffer <[email protected]>
Phase 1: a second review engine alongside the majordomo agent loop. For
each lens, shell out to the Claude Code CLI (`claude -p --output-format
json`) inside the checked-out repo so it verifies findings with its own
read tools, then reuse gadfly's verdict-parse + recheck + consolidate +
emit pipeline. Select via GADFLY_MODELS `claude-code`/`claude-code/<model>`;
auth via CLAUDE_CODE_OAUTH_TOKEN (no --bare) else ANTHROPIC_API_KEY;
read-only by default; GADFLY_CLAUDE_* knobs. Dockerfile bundles Node +
@anthropic-ai/claude-code. Also bumped the dogfood pin to the status-board
image (PR #2 was the first dogfood with the live board + full fleet).
Folded in the swarm's own review findings: minimal subprocess env (no
GITEA_TOKEN leak to the CLI), runPass robustness (ctx/empty-result/runErr),
process-group cleanup on timeout, rune-safe error truncation, and
engine-neutral prompts (also de-mort-ified the recheck prompt). 66 findings
graded via the gadfly MCP.
gofmt clean, go vet quiet, go build + go test -race green.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Co-authored-by: Steve Dudenhoeffer <[email protected]>
Co-committed-by: Steve Dudenhoeffer <[email protected]>
Phase 3: one consolidated, live-updating PR comment aggregating every
model's per-lens progress (queued -> running -> finished + verdict), so
the swarm's progress is visible at a glance and a watcher can tell when
it's done. Opt-in statusWriter in the binary (atomic writes) + a
background status-board.sh renderer wired through entrypoint.sh; default
on, GADFLY_STATUS_BOARD=0 to disable.
Also restores gadfly's dogfood swarm to the full cloud fleet (9 cloud +
M5; M1 dropped as too slow) matching mort, and folds in the 3 real bugs
the swarm found on its own PR (skip-binary stuck-waiting, panic-stuck
lens, busy-loop on bad poll interval). All 36 findings graded via the
gadfly MCP (18 real / 18 false-positive).
gofmt clean, go vet quiet, go build + go test -race green.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Co-authored-by: Steve Dudenhoeffer <[email protected]>
Co-committed-by: Steve Dudenhoeffer <[email protected]>
Adds the adversarial-review workflow to gadfly itself (copied from mort: 3 cloud + m1/m5 via foreman, findings telemetry, sha-d7f364d). Future gadfly PRs get reviewed by the swarm.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
After each review the binary POSTs the run + its heuristically-extracted findings to GADFLY_FINDINGS_URL (off unless set). Advisory: any error only goes to stderr — never touches stdout, the exit code, or the review. stdlib net/http only (no new deps). entrypoint.sh derives GADFLY_REPO/GADFLY_PR and passes through GADFLY_FINDINGS_URL/GADFLY_FINDINGS_TOKEN. Also renames store references from the old 'docket' name to 'gadfly-reports'.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Specialist lenses ran strictly sequentially within a model. Add a
GADFLY_LENS_CONCURRENCY knob (default 1 = unchanged) that overlaps the
independent per-lens review+recheck passes, so a model posts its
consolidated comment as soon as its lenses finish.
Per-provider configurable, mirroring GADFLY_PROVIDER_CONCURRENCY:
GADFLY_PROVIDER_LENS_CONCURRENCY takes a "provider=N,..." map keyed by
the same provider lanes (modelProvider() mirrors entrypoint's provider_of;
providerOverride() mirrors provider_cap). The override wins for the model's
lane, else the scalar default.
runSpecialists fans out via a bounded worker pool, order-preserving
(results written by index) and keeping each lens's own timeout/recheck.
repoFS is immutable + fresh-toolbox-per-pass, so lenses share no mutable
state (verified under -race). Docs/examples updated; dropped a duplicate
GADFLY_TIMEOUT_SECS README row.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Accept "foreman" in both resolveModel (GADFLY_BASE_URL) and endpointProvider
(GADFLY_ENDPOINT_*) switches, mapping to majordomo's ollama.Foreman() preset
(handles foreman's non-streaming/long-poll quirks). Unlike the HTTPS-only
LLM_* foreman:// DSN, the base URL is verbatim, so a plaintext http:// foreman
queue works. Tests + README provider table + endpoint-aliases example updated.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
steveandClaude Opus 4.8