Repository navigation
feat: arm decide-local in the shipped binary (default feature, runtime opt-in) - #1097
Merged
Merged
Conversation
The rc.80 gate measurement (PR #1088) caught the stock release binary arming nothing for --decide-mode local: release.yml builds xerj-server with default features, and the decide-local feature was off, so tier 2 of the decide ladder existed only in from-source builds that enabled it by hand. Anyone following the published rc.80 eval card got a silent fallback to the history vote. Root cause: feature gating drifted from the batteries-included rule the binary already follows for neural. Fix: add decide-local to xerj-server's default feature set. - No new dependency: the candle/tokenizers crates it names are already in the default build via neural; xerj-ai is already a direct dep of xerj-server (Cargo.toml:22). - No egress change: decide-local pulls no hf-hub; the published network inventory is unchanged (PR #1083's label tests stay green). - Runtime stays OPT-IN: --decide-mode local --decide-model-dir <path> (or XERJ_DECIDE_MODE/XERJ_DECIDE_MODEL_DIR). Without it a node boots on the history vote exactly as before. --no-default-features still drops the tier, same as neural. Verified: cargo build --release -p xerj-server (12m55s, clean) and cargo test --release -p xerj-api decide — 3 passed, 0 failed. Refs #1057, gate evidence in PR #1088.
neoneye
pushed a commit
to agent-memory-atlas-archive/xerj-org--xerj
that referenced
this pull request
Oct 1, 2026
The rc.80 release PR, docs-only on top of main (all engine code rides the merged window PRs; nothing here touches engine/crates or xerj-ux). rc.79 was folded into this cut by direction; no rc.79 tag exists. - CHANGELOG: [Unreleased] cut over to ## [1.0.0-rc.80] - 2026-09-30 with the measured-gates theme (three gates passed outright, three failed and ship opt-in/behind a flag with numbers published, one split); xerj-org#1095's own entry moves from [Unreleased] into the section unchanged; adds the citations the coverage gate was missing (xerj-org#1078 tool inventory, xerj-org#1079 ask-plan latency arm 1.129 ms, xerj-org#1083 egress-inventory classification, xerj-org#1089 console UX review) plus xerj-org#1097 (merged with no entry of its own). - ROADMAP: review line bumped to 2026-09-30 against rc.80; the ten-item program (xerj-org#1054, xerj-org#1055-xerj-org#1064) recorded as executed with every verdict; the semantic-detections row rewritten (the 'no alerting' text was false since xerj-org#1082); Next release -> v1.0.0 GA with the rc.80 cut record and a live-verified five-defect shortlist (xerj-org#1091-xerj-org#1094, xerj-org#1100) — xerj-org#1098/xerj-org#1099 were fixed and closed by xerj-org#1095 inside this release. - landing: all 53 V1.0.0-RC.78 stamps -> RC.80 (landing-constants-guard matches the tree version); data-latest-tag rc.78 -> rc.80. - llms.txt + llms-full.txt: the watcher caveat rewritten to the rc.80 reality (one real watch shape, everything else 501) with the earlier-version note kept in the open. - content/answers/does-xerj-support-s3-alerting-plugins.md: the alerting half rewritten (PARTIAL since xerj-org#1082) and the packs half corrected (record packs real since rc.78); updated bumped to 2026-09-30. - release-notes-gate.sh: an empty open-defects shortlist is a real state (tracker emptied 2026-09-29) — distinguish 'section moved' from 'section lists none'; verified against the live tracker. - engine/Cargo.toml 1.0.0-rc.78 -> 1.0.0-rc.80; Cargo.lock version strings only (no dependency moves — xerj-org#1095/xerj-org#1097 added none). docs_capability_lists: 15 passed, 0 failed. landing-constants-guard: all checks passed. release-notes-gate: PASS, all window PRs cited.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
One feature line:
xerj-server'sdefaultset now includesdecide-local, alongsideneural.Why — the rc.80 gate caught a silent no-op
PR #1088's gate measurement found that the stock release binary arms nothing for
--decide-mode local:.github/workflows/release.ymlbuildsxerj-serverwith default features, anddecide-localwas off — so tier 2 of the decide ladder (issue #1057) existed only in from-source builds that enabled the feature by hand. Anyone following the published rc.80 eval card (--decide-mode local --decide-model-dir ...) got a silent fallback to the history vote.Constraints checked
decide-localnames are already in the default build vianeural;xerj-aiis already a direct dependency ofxerj-server.decide-localpulls no hf-hub; the published network-egress inventory is unchanged (PR rerank: classify #1062's label test stubs in the egress inventory (fix main) #1083's label tests stay green).--decide-mode local --decide-model-dir <path>(orXERJ_DECIDE_MODE/XERJ_DECIDE_MODEL_DIR). Without it a node boots on the history vote exactly as before.--no-default-featuresstill drops the tier, same asneural.Verification
cargo build --release -p xerj-server— clean (12m55s, /tmp/xtarget-decidedefault).cargo test --release -p xerj-api decide— 3 passed, 0 failed.Gate evidence: PR #1088 (SMS 0.9193 / ECE 0.287 / AG News 0.2599 / Banking77 0.1185 / latency p50 8.4 ms — tier ships opt-in with the numbers published, per the plan's own rule).
Refs #1057, #1088.