fix(coding-agent): suppress rlm_child_update emits with an unchanged snapshot - #1944
Merged
Conversation
…snapshot Child streaming re-emits the parent's child snapshot on every assistant delta; once the answer preview caps and activity is steady, the repeats are byte-identical and only add wire and render noise for every attached client. Emit only when the serialized snapshot actually changed.
kernelStderr accumulated for the kernel's lifetime while every reader takes at most the last 1 KiB; keep only an 8 KiB tail.
snimu
changed the title
xeophon
approved these changes
Sep 1, 2026
olety
added a commit
to oneiron-dev/prime-agent
that referenced
this pull request
Sep 1, 2026
Takes upstream's event-driven supervisor roster ledger + push (PrimeIntellect-ai#1897, PrimeIntellect-ai#1900), direct TUI<->worker transport (ENG-5817), daemon startup/recovery hardening (PrimeIntellect-ai#1929, PrimeIntellect-ai#1909), single-dump kernel snapshots (PrimeIntellect-ai#1945), empty-draft eviction (PrimeIntellect-ai#1946), rlm_child_update suppression (PrimeIntellect-ai#1944), bash-skill preview (PrimeIntellect-ai#1911). Fork laws re-expressed on the roster architecture: - stable-target follow-up honesty kept (capability proof via worker hello, target_unavailable never not_found when ownership unproven) - schema revision 26 (union of fork rev-24 stable-target + upstream rev-24/25 roster+transport); digest minted by the repo's own algorithm - summary freshness reuse + single-flight + staleness + root-omission rejection restored on upstream's refresh pull - adoption/recovery never fails a live worker on a slow or root-omitting catalog: get_state root seed + stale mark + bounded background rehydration - repl.py keeps fork prune-on-aggregate-overflow - delete handlers keep fork persistence reporting; eviction fence test keeps the stronger two-worker contention variant Known test debt (deferred to post-Wave cleanup per owner): roster-era fixture migrations in daemon-supervisor-monitor (2), plus un-triaged failures in package-command-paths, agent-session-recursion, daemon-runtime-stress, 4600-supervisor-singleton, 4603-worker-recovery, 4606-update-restart- coordinator, agents-view-roster. Production laws preserved; failures are fixture-era artifacts or mechanism assertions to rewrite.
ketema
added a commit
to ketema/prime-agent
that referenced
this pull request
Sep 1, 2026
- Direct session transport between TUI and worker (ENG-5817, PrimeIntellect-ai#1926) - Event-driven supervisor agent roster with push subscriptions (PrimeIntellect-ai#1897, PrimeIntellect-ai#1900, PrimeIntellect-ai#1895) - Hardened daemon startup, recovery ownership, and worker launch diagnostics (PrimeIntellect-ai#1929, PrimeIntellect-ai#1918) - Python REPL runtime single-dump snapshots and bash preview tool (PrimeIntellect-ai#1945, PrimeIntellect-ai#1911) - Non-blocking RLM subagent deletion and snapshot update suppression (PrimeIntellect-ai#1954, PrimeIntellect-ai#1944) - Saved catalog loading on Agents View open (PrimeIntellect-ai#1960) - Advanced Anthropic prompt caching marker across tool results (PrimeIntellect-ai#1927) - TUI process replacement on update and empty draft eviction (PrimeIntellect-ai#1631, PrimeIntellect-ai#1946, PrimeIntellect-ai#1920)
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
2 participants
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.
Fixes ENG-5830 (https://linear.app/primeintellect/issue/ENG-5830/suppress-duplicate-rlm-child-update-emits).
A session running child agents emits an
rlm_child_updatesnapshot for every streaming event a child produces — every token delta, every tool start/stop — and each ancestor re-emits its descendants' updates. The snapshot only carries coarse fields (status, activity, a 160-character answer preview, token count from the last completed message), so while a child is thinking, and once its answer preview hits the cap, consecutive snapshots are byte-for-byte identical. Every attached client still received and re-rendered each one, and in daemon mode each one was serialized to every attached socket and scheduled a roster flush.emitChildUpdatenow compares the serialized snapshot against the last one it emitted and skips exact repeats, the same way_emitQueueUpdatealready deduplicates queue snapshots. Status transitions, preview growth, recap changes, and terminal updates still emit; removal signals bypass the closure entirely and are unaffected.One test pins the behavior: repeated emits with an unchanged snapshot produce no event, and a real change produces exactly one.
Validated with the daemon/roster suites and root
npm run check.