opensource/kilocode
3
0
Fork 0
mirror of https://github.com/Kilo-Org/kilocode.git synced 2026-08-30 17:14:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(cli): defer threshold compaction during tool loops (#12792)

Browse Source 
* fix(cli): preserve Kilo prompt cache keys

* fix(cli): defer threshold compaction during tool loops
This commit is contained in:
Marius
2026-08-03 12:22:39 +02:00
committed by GitHub
parent 46715c3053
commit 7d3f50c2e8
3 changed files with 16 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.changeset/compaction-threshold-boundary.md
+5
View File
@@ -0,0 +1,5 @@
---
"@kilocode/cli": patch
---
Prevent configured compaction thresholds from interrupting active tool sequences.
packages/opencode/src/session/overflow.ts
+2 -3
View File
@@ -30,8 +30,7 @@ export function isOverflow(input: {
if (input.model.limit.context === 0) return false
const count = KiloSessionOverflow.count(input.tokens) // kilocode_change
// kilocode_change start
const cap = KiloSessionOverflow.limit({ cfg: input.cfg, model: input.model, usable: usable(input) })
return count >= cap
// kilocode_change start - post-step checks are safety-only; economic thresholds run in preflight
return count >= usable(input)
// kilocode_change end
}
packages/opencode/test/kilocode/session-overflow.test.ts
+9 -8
View File
@@ -47,16 +47,17 @@ function tokens(count: number): MessageV2.Assistant["tokens"] {
return { input: count, output: 0, reasoning: 0, cache: { read: 0, write: 0 } }
}
describe("Kilo auto-compaction threshold", () => {
test("triggers at the configured context percentage", () => {
describe("Kilo post-step compaction safety", () => {
test("ignores the configured threshold after a provider step", () => {
const conf = cfg({ threshold_percent: 75 })
const mdl = model({ context: 200_000, output: 32_000 })
expect(isOverflow({ cfg: conf, model: mdl, tokens: tokens(149_999) })).toBe(false)
expect(isOverflow({ cfg: conf, model: mdl, tokens: tokens(150_000) })).toBe(true)
expect(isOverflow({ cfg: conf, model: mdl, tokens: tokens(167_999) })).toBe(false)
expect(isOverflow({ cfg: conf, model: mdl, tokens: tokens(168_000) })).toBe(true)
})
test("keeps the reserved safety trigger when it is lower", () => {
test("uses the usable context limit when the threshold is high", () => {
const conf = cfg({ threshold_percent: 95 })
const mdl = model({ context: 200_000, output: 32_000 })
@@ -68,8 +69,8 @@ describe("Kilo auto-compaction threshold", () => {
const conf = cfg({ threshold_percent: 75 })
const mdl = model({ context: 400_000, input: 200_000, output: 32_000 })
expect(isOverflow({ cfg: conf, model: mdl, tokens: tokens(149_999) })).toBe(false)
expect(isOverflow({ cfg: conf, model: mdl, tokens: tokens(150_000) })).toBe(true)
expect(isOverflow({ cfg: conf, model: mdl, tokens: tokens(179_999) })).toBe(false)
expect(isOverflow({ cfg: conf, model: mdl, tokens: tokens(180_000) })).toBe(true)
})
test("ignores a cleared threshold", () => {
@@ -114,14 +115,14 @@ describe("Kilo auto-compaction threshold", () => {
const conf = cfg({ threshold_percent: 75 })
const mdl = model({ context: 200_000, output: 32_000 })
expect(isOverflow({ cfg: conf, model: mdl, tokens: { ...tokens(149_999), reasoning: 1 } })).toBe(true)
expect(isOverflow({ cfg: conf, model: mdl, tokens: { ...tokens(167_999), reasoning: 1 } })).toBe(true)
})
test("falls back to provider total when normalized usage is unavailable", () => {
const conf = cfg({ threshold_percent: 75 })
const mdl = model({ context: 200_000, output: 32_000 })
expect(isOverflow({ cfg: conf, model: mdl, tokens: { ...tokens(0), total: 150_000 } })).toBe(true)
expect(isOverflow({ cfg: conf, model: mdl, tokens: { ...tokens(0), total: 168_000 } })).toBe(true)
})
test("uses the output cap as the reserve for single-window gateway models", () => {