Folds in the real findings the dogfood swarm raised on PR #20 (21 graded
real, 1 false positive):
- tools.go: anchor get_diff `path` matching to whole path tokens (foo.go no
longer pulls in barfoo.go; a trailing "/" still scopes a directory); split
the diff once + cache it; drop the spurious trailing blank line; fix the
"truncated after line N" off-by-one wording. Share one tool-list source
(allTools) between toolbox() and the executus registry.
- executus.go: drop the dead Config.Defaults caps (per-run RunnableAgent always
overrides them); shared envBool/reviewTimeout helpers; resolveContextTokens
logs a failed lookup and uses a 5s timeout (was 15s); note the budget guard
is pass-granular (the wall-clock backstop covers mid-pass).
- main.go/recheck.go: shared envBool; fix package-doc drift (the removed
finalization fallback, the paginated get_diff).
- entrypoint.sh/run.sh: export GADFLY_MAX_DIFF_CHARS directly (run.sh prefers
it); guard the watchdog's delayed SIGKILL on a .disarmed marker so it can't
catch the consolidation pass.
- tests: anchoring test; corrected obsolete env var + truncation-wording asserts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fixes the large-PR token burn: a ~250K-token diff was re-sent every agent
step across models × lenses × passes, draining a metered usage block in
minutes. Small PRs are untouched (every mitigation is size-gated / no-op
under threshold).
- Re-platform the in-process review path onto executus run.Executor: context
compaction (executus/compact, threshold from the model's real context window
via executus/model), run-bounding, a per-PR budget gate (Ports.Budget), and
the wrap-up nudge re-expressed as a run.Critic. Lens fan-out now uses
executus/fanout. gadfly keeps its own model.go, so GADFLY_ENDPOINT_<NAME>
aliases and the claude-code engine are unaffected. No majordomo bump; the
binary stays static (executus core is majordomo+stdlib only).
- Paginate get_diff (per-file `path` + start_line/limit) instead of dumping the
whole diff; trim the recheck diff embed (60k -> 20k chars).
- entrypoint.sh: downshift the fleet above GADFLY_HUGE_DIFF_BYTES (one cheap
model, fewer lenses/steps, no recheck) + a swarm-wide GADFLY_PR_BUDGET_SECS
wall-clock backstop (adds procps for pkill). All advisory; CI never fails.
- README + CLAUDE.md + tests updated.
Note: run.Result exposes no transcript, so the old transcript-based forced-
finalization fallback is dropped; the wrap-up critic nudge is the remaining
"always emit something" mechanism.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
steve