Files
oh-my-pi/packages/coding-agent/test
roboomp b74f7bb720 fix(compaction): trigger goal-mode threshold on billed context, not post-prune estimate
Pruning frees bytes for the NEXT prompt — it does not change the size of
the prompt the LLM just billed for. Subtracting the per-turn
`#pruneStaleToolResults` / `#pruneToolOutputs` savings from the
threshold input let a long-running `/goal` session sit above
`compaction.thresholdTokens` indefinitely: the visible context
(anchored to the same provider billing) showed >threshold, but
`shouldCompact` no-op'd because the subtraction dropped the input below
the trigger. The `compactionContextTokens` floor against the post-prune
local estimate is still applied, so a payload-compression hook still
can't deflate the trigger.

Regression test seeds one large `useless` tool result whose suffix sits
inside the 8k cache-warm window so `#pruneStaleToolResults` actually
returns ≥20k savings, then asserts compaction fires when the final turn
bills 91k tokens against the reporter's `thresholdTokens: 76384`.

Fixes #3174
2026-06-21 07:21:22 +00:00
..
2026-06-11 21:03:49 +02:00
2026-05-30 18:08:51 +02:00
2026-05-30 18:08:51 +02:00
2026-06-12 11:24:26 +02:00
2026-05-30 18:08:51 +02:00