Repository navigation
Limit egm-bootstrap workers and scouts - #359
Conversation
The root spawned every Sub-Orchestrator "without artificial concurrency limits", and each worker spawned one scout per ~1,500-line chunk with no limit. Cap workers at 5, which the partitioning already yields at most, and run at most 5 chunk scouts at a time per worker. The >15-directory gate now says how many workers and scouts the run uses. Update the bootstrap design doc, add a unit test and a scenario assertion, and regenerate distributions/claude. Refs google#262
|
Hi @n3wth , A note on overlap: #350 (opened 2026-11-07) also caps |
…lelism-caps # Conflicts: # skills/egm-bootstrap/TEST.md
egm-triage-bot
left a comment
There was a problem hiding this comment.
Automated first-pass review found zero blocking or major issues. Routing to @google/egm-maintainers for maintainer review.
…lelism-caps # Conflicts: # distributions/claude/skills/egm-bootstrap/SKILL.md
After merging main, google#409's .NET detection put the skill body at 24,109 bytes, over the 24,000-byte limit. Restore Execution Constraint 5, shorten the gate question and scout cap, and drop the worker cap's repeat of the partition limit, which the partitioning steps state.
egm-triage-bot
left a comment
There was a problem hiding this comment.
Automated first-pass review found zero blocking or major issues. Routing to @google/egm-maintainers for maintainer review.
|
LGTM - approval pending a decision on merging this or #350 |
|
I had Gemini Neon do an analysis of #359 and #350, the tl;dr is we're merging 359 with a couple of flags for possible future work. Evaluation and Comparison: PR #350 versus PR #359Comparison of [PR #350][pr-350] ( RecommendationPR #359 addresses one item in issue #262 cleanly. It merges with PR #350 has merge conflicts and would exceed the 24,000-byte limit on PR #350 does raise two valid concerns that PR #359 does not cover: host Side-by-Side Comparison
Evaluation of PR #359PR #359 focuses strictly on Strengths
Risks and Caveats
Evaluation of PR #350PR #350 combines Blockers
Ideas Worth Salvaging as Separate Follow-Ups
|
Summary of Key Changes
Refs #262 (bootstrap parallelism item: add a cap and show an estimated cost at the existing >15-directory gate).
egm-bootstraptold the root to spawn all Sub-Orchestrators "without artificial concurrency limits", and each worker spawned onegoldfish-explorerscout per ~1,500-line chunk of a directory, all in parallel, with no limit. The >15-directory gate asked for approval without saying what the run would start.skills/egm-bootstrap/SKILL.md:docs/designs/bootstrap.md(Status: Current): replaced "unbounded" parallelism with the caps in the overview, goals, user journey, swarm architecture, both "Spawning upon Approval" bullets, the rate-limit risk, and thebootstrap_parallel_treetest description, and added the estimate to the Safety Gate step.tests/unit/test_harnesses.py:test_bootstrap_caps_parallel_workers_and_scoutschecks the worker cap, the scout cap, the gate estimate, and that "artificial concurrency limits" is gone. All four checks fail on the skill text inmain.skills/egm-bootstrap/test_scenarios.yaml:bootstrap_safety_gatenow also requires the gate to state the worker cap ("up to", "at most", or "no more than" 5 workers or Sub-Orchestrators). Replies such as "I will spawn 20 workers" or "trees with 5 or fewer subdirectories run without workers" do not match.skills/egm-bootstrap/TEST.md: the manual safety gate scenario now checks the estimate.The caps are prompt instructions, not limits a host enforces. On a host with no subagent tool, the skill already runs the scout steps inline, so the caps do not apply there. I chose 5 for both because it is the partitioning's existing maximum, so the worker cap does not change how a run that follows the algorithm partitions the tree.
Counts: the non-test diff is 22 lines in
skills/egm-bootstrap/SKILL.mdand 38 indocs/designs/bootstrap.md, in 1 core file.Out of scope: the other #262 items. #347 fixed the marketplace source, the development dependencies item is still open, and the persona and standard paths are recorded as accepted on #262; #291 covers the docs-accuracy item.
docs/designs/bootstrap.mdstill says in places that approval is requested when the directory count is above 5, while the skill and the design's own Warning Gate ask above 15; I left those sentences as they were.Suggested label:
docs(for thedocs/designs/bootstrap.mdupdate).Contribution Type
Track: Bug Fix / Minor Patch
Verification
Unit tests: passed, after merging
mainagain at70406c4. #394 removed the committeddistributions/claudefolder, so this PR no longer changes it. With #409's .NET detection, the merged skill body came to 24,109 bytes, over the 24,000-byte limit, so I trimmed this PR's own wording: Execution Constraint 5 is back to itsmaintext, the gate question says "scout" instead of "scout subagent", the scout cap says "queue the rest" instead of "start the next when one returns", and the worker cap no longer repeats that the partitioning yields at most 5 partitions, which the partitioning steps already state.pytest tests/uniton Python 3.14.0 (viauv run --no-project --with pytest==9.0.3 --with pyyaml==6.0.3, thetestgroup pins inpyproject.toml): 388 passed, 2 skipped (the Copilot and Cursor native probes, which needEGM_COPILOT_OFFLINEandEGM_CURSOR_BUNDLE). The four checks in the new test fail on the skill text inmain.Scenario pattern: the new
bootstrap_safety_gatepattern matches the skill's gate question and does not match the two wrong replies above or the old question. Not run: a live scenario evaluation.Other checks and limits: passed:
git diff --check; the skill body is 23,973 bytes, under the 24,000-byte limit. Not run: a live bootstrap on any host.Human Accountability Affirmation