You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Child token budgets below one iteration's cost are no longer refused (#736 removed the floor; no replacement or changelog note) #2694
supervise no longer refuses a child token budget that is too small to finish one iteration.
#685 (commit 012762f, 2026-08-01) added this check. #736 (merged 2026-08-04) removed it in the sub-commit "fix(supervise): remove guessed worker token floor":
src/runtime/supervise/budget-floor.ts was deleted;
below-runtime-floor and PI_TOKEN_FLOOR no longer appear on main (checked 2026-11-17 at fc92d9d);
the CHANGELOG does not mention the removal.
Why it matters (the evidence from #685's own commit message)
Parents wrote child budgets of 2,000, 8,000, 12,000 and 20,000 tokens.
Six pi children on tangle-router/glm-5.2 settled between 31,211 and 62,616 input tokens.
In run proof-native-tools-20260801b, a child wrote its artifact correctly, then overran a 12,000-token budget by spending 76,657. The run recorded it as a failure: a false negative.
What main offers instead (checked in the docs, 2026-11-17)
The budget ledger reconciles measured spend after the turn. Overspend returns a BudgetViolation.
preflightSpawn can refuse a spawn before reservation, but:
SpawnRefusalCause is closed to model-route | bridge-full | unmountable-tool | unprovisionable-profile;
SpawnPreflightContext does not carry the child's token budget.
So a caller cannot write a budget-floor check through the supported gate.
Ask
If dropping the floor was intended (one measured pairing should not be a global guess), document the decision in the CHANGELOG.
Say how a caller should catch an unsatisfiable child budget before dispatch. For example, expose the child's budget to SpawnPreflightContext and allow a budget refusal cause.
tangle.tools has a published post (2026-08-09) that still describes below-runtime-floor. That post is being rewritten from this evidence.
Closing. The floor's removal was deliberate and right. #2695 (merged as 53d6ad6) documents what Runtime does today and adds the CHANGELOG line that 0.129.0 lacked. It changes docs only, so there is no release and no consumer bump.
Deliberate.#736 removed the floor in aafd2a1, "remove guessed worker token floor". The same commit rewrote the agent-graphs skill to give the reason: "Do not turn one run's cumulative spend into a universal harness minimum; Runtime enforces the caller's conserved pool, not guessed per-harness floors."
Right.
31,211 was the lowest cumulative settlement of six pi children on one model, each running 1 to 4 iterations. It was not the cost of one iteration.
The table applied that number to every pi child on every model, and every other harness was null.
On catching an undersized budget before dispatch:preflightSpawn still does not see the budget. The documented path is to size perWorker and authored budgets from measured runs of the same profile, and to raise the budget through a same-key continuation when a child runs out. The tangle.tools post that describes below-runtime-floor is queued for a rewrite with these facts.
Activity
drewstone commentedon Nov 17, 2026
Closing. The floor's removal was deliberate and right. #2695 (merged as 53d6ad6) documents what Runtime does today and adds the CHANGELOG line that 0.129.0 lacked. It changes docs only, so there is no release and no consumer bump.
Deliberate. #736 removed the floor in aafd2a1, "remove guessed worker token floor". The same commit rewrote the
agent-graphsskill to give the reason: "Do not turn one run's cumulative spend into a universal harness minimum; Runtime enforces the caller's conserved pool, not guessed per-harness floors."Right.
pichildren on one model, each running 1 to 4 iterations. It was not the cost of one iteration.pichild on every model, and every other harness wasnull.AgentProfiledecides model, prompt, tools and context. Those set the cost of a turn, so a harness-keyed constant refuses lean profiles and admits heavy ones.The false negative from #685 has been recovered since then.
donewith its output and abudgetViolation.tests/kernel/leaf-unavailable-pause.test.tsproves it: a 1-token budget is admitted, the turn settlesdoneover budget, and a larger budget continues in the same box. The test passed in the docs(supervise): Runtime admits a child budget of any size; record the removed floor #2695 gate.On catching an undersized budget before dispatch:
preflightSpawnstill does not see the budget. The documented path is to sizeperWorkerand authored budgets from measured runs of the same profile, and to raise the budget through a same-key continuation when a child runs out. The tangle.tools post that describesbelow-runtime-flooris queued for a rewrite with these facts.