mirror of
https://github.com/RooVetGit/Roo-Code.git
synced 2026-08-28 05:27:24 +00:00
fix: respect condensation percentage threshold when saving settings
- Fixed issue where context condensation was triggered on every action after saving settings - Condensation now only triggers when the percentage threshold is actually met - If tokens exceed hard limit but percentage is below threshold, sliding window truncation is used instead - Added detailed logging to help debug condensation triggers - Updated tests to reflect the new behavior This prevents unnecessary condensation operations that were happening even when the configured percentage threshold had not been reached.
This commit is contained in:
Roo Code
parent
ad0e33e2d9
commit
6df165da1c
2 changed files with 92 additions and 82 deletions
|
|
@ -544,86 +544,13 @@ describe("Sliding Window", () => {
|
|||
})
|
||||
})
|
||||
|
||||
it("should use summarizeConversation when autoCondenseContext is true and tokens exceed threshold", async () => {
|
||||
// Mock the summarizeConversation function
|
||||
const mockSummary = "This is a summary of the conversation"
|
||||
const mockCost = 0.05
|
||||
const mockSummarizeResponse: condenseModule.SummarizeResponse = {
|
||||
messages: [
|
||||
{ role: "user", content: "First message" },
|
||||
{ role: "assistant", content: mockSummary, isSummary: true },
|
||||
{ role: "user", content: "Last message" },
|
||||
],
|
||||
summary: mockSummary,
|
||||
cost: mockCost,
|
||||
newContextTokens: 100,
|
||||
}
|
||||
|
||||
const summarizeSpy = vi
|
||||
.spyOn(condenseModule, "summarizeConversation")
|
||||
.mockResolvedValue(mockSummarizeResponse)
|
||||
it("should NOT use summarizeConversation when tokens exceed hard limit but percentage is below threshold", async () => {
|
||||
// Reset any previous mock calls
|
||||
vi.clearAllMocks()
|
||||
const summarizeSpy = vi.spyOn(condenseModule, "summarizeConversation")
|
||||
|
||||
const modelInfo = createModelInfo(100000, 30000)
|
||||
const totalTokens = 70001 // Above threshold
|
||||
const messagesWithSmallContent = [
|
||||
...messages.slice(0, -1),
|
||||
{ ...messages[messages.length - 1], content: "" },
|
||||
]
|
||||
|
||||
const result = await truncateConversationIfNeeded({
|
||||
messages: messagesWithSmallContent,
|
||||
totalTokens,
|
||||
contextWindow: modelInfo.contextWindow,
|
||||
maxTokens: modelInfo.maxTokens,
|
||||
apiHandler: mockApiHandler,
|
||||
autoCondenseContext: true,
|
||||
autoCondenseContextPercent: 100,
|
||||
systemPrompt: "System prompt",
|
||||
taskId,
|
||||
profileThresholds: {},
|
||||
currentProfileId: "default",
|
||||
})
|
||||
|
||||
// Verify summarizeConversation was called with the right parameters
|
||||
expect(summarizeSpy).toHaveBeenCalledWith(
|
||||
messagesWithSmallContent,
|
||||
mockApiHandler,
|
||||
"System prompt",
|
||||
taskId,
|
||||
70001,
|
||||
true,
|
||||
undefined, // customCondensingPrompt
|
||||
undefined, // condensingApiHandler
|
||||
)
|
||||
|
||||
// Verify the result contains the summary information
|
||||
expect(result).toMatchObject({
|
||||
messages: mockSummarizeResponse.messages,
|
||||
summary: mockSummary,
|
||||
cost: mockCost,
|
||||
prevContextTokens: totalTokens,
|
||||
})
|
||||
// newContextTokens might be present, but we don't need to verify its exact value
|
||||
|
||||
// Clean up
|
||||
summarizeSpy.mockRestore()
|
||||
})
|
||||
|
||||
it("should fall back to truncateConversation when autoCondenseContext is true but summarization fails", async () => {
|
||||
// Mock the summarizeConversation function to return an error
|
||||
const mockSummarizeResponse: condenseModule.SummarizeResponse = {
|
||||
messages: messages, // Original messages unchanged
|
||||
summary: "", // Empty summary
|
||||
cost: 0.01,
|
||||
error: "Summarization failed", // Error indicates failure
|
||||
}
|
||||
|
||||
const summarizeSpy = vi
|
||||
.spyOn(condenseModule, "summarizeConversation")
|
||||
.mockResolvedValue(mockSummarizeResponse)
|
||||
|
||||
const modelInfo = createModelInfo(100000, 30000)
|
||||
const totalTokens = 70001 // Above threshold
|
||||
const totalTokens = 70001 // Above hard limit but only 70% of context window
|
||||
const messagesWithSmallContent = [
|
||||
...messages.slice(0, -1),
|
||||
{ ...messages[messages.length - 1], content: "" },
|
||||
|
|
@ -644,17 +571,75 @@ describe("Sliding Window", () => {
|
|||
maxTokens: modelInfo.maxTokens,
|
||||
apiHandler: mockApiHandler,
|
||||
autoCondenseContext: true,
|
||||
autoCondenseContextPercent: 100,
|
||||
autoCondenseContextPercent: 100, // 100% threshold, but tokens are only at 70%
|
||||
systemPrompt: "System prompt",
|
||||
taskId,
|
||||
profileThresholds: {},
|
||||
currentProfileId: "default",
|
||||
})
|
||||
|
||||
// Verify summarizeConversation was called
|
||||
// Verify summarizeConversation was NOT called (percentage threshold not met)
|
||||
expect(summarizeSpy).not.toHaveBeenCalled()
|
||||
|
||||
// Verify it used sliding window truncation instead
|
||||
expect(result).toEqual({
|
||||
messages: expectedMessages,
|
||||
summary: "",
|
||||
cost: 0,
|
||||
prevContextTokens: totalTokens,
|
||||
})
|
||||
|
||||
// Clean up
|
||||
summarizeSpy.mockRestore()
|
||||
})
|
||||
|
||||
it("should fall back to truncateConversation when autoCondenseContext is true, percentage threshold is met, but summarization fails", async () => {
|
||||
// Mock the summarizeConversation function to return an error
|
||||
const mockSummarizeResponse: condenseModule.SummarizeResponse = {
|
||||
messages: messages, // Original messages unchanged
|
||||
summary: "", // Empty summary
|
||||
cost: 0.01,
|
||||
error: "Summarization failed", // Error indicates failure
|
||||
}
|
||||
|
||||
const summarizeSpy = vi
|
||||
.spyOn(condenseModule, "summarizeConversation")
|
||||
.mockResolvedValue(mockSummarizeResponse)
|
||||
|
||||
const modelInfo = createModelInfo(100000, 30000)
|
||||
// Set tokens to meet percentage threshold (100% of context)
|
||||
const totalTokens = 100001 // Above 100% threshold
|
||||
const messagesWithSmallContent = [
|
||||
...messages.slice(0, -1),
|
||||
{ ...messages[messages.length - 1], content: "" },
|
||||
]
|
||||
|
||||
// When truncating, always uses 0.5 fraction
|
||||
// With 4 messages after the first, 0.5 fraction means remove 2 messages
|
||||
const expectedMessages = [
|
||||
messagesWithSmallContent[0],
|
||||
messagesWithSmallContent[3],
|
||||
messagesWithSmallContent[4],
|
||||
]
|
||||
|
||||
const result = await truncateConversationIfNeeded({
|
||||
messages: messagesWithSmallContent,
|
||||
totalTokens,
|
||||
contextWindow: modelInfo.contextWindow,
|
||||
maxTokens: modelInfo.maxTokens,
|
||||
apiHandler: mockApiHandler,
|
||||
autoCondenseContext: true,
|
||||
autoCondenseContextPercent: 100, // 100% threshold, tokens are at 100%+
|
||||
systemPrompt: "System prompt",
|
||||
taskId,
|
||||
profileThresholds: {},
|
||||
currentProfileId: "default",
|
||||
})
|
||||
|
||||
// Verify summarizeConversation was called (percentage threshold was met)
|
||||
expect(summarizeSpy).toHaveBeenCalled()
|
||||
|
||||
// Verify it fell back to truncation
|
||||
// Verify it fell back to truncation after summarization failed
|
||||
expect(result.messages).toEqual(expectedMessages)
|
||||
expect(result.summary).toBe("")
|
||||
expect(result.prevContextTokens).toBe(totalTokens)
|
||||
|
|
|
|||
|
|
@ -144,7 +144,17 @@ export async function truncateConversationIfNeeded({
|
|||
|
||||
if (autoCondenseContext) {
|
||||
const contextPercent = (100 * prevContextTokens) / contextWindow
|
||||
if (contextPercent >= effectiveThreshold || prevContextTokens > allowedTokens) {
|
||||
// Check if we should trigger condensation based on percentage threshold
|
||||
const shouldCondenseByPercentage = contextPercent >= effectiveThreshold
|
||||
// Check if we're over the hard token limit
|
||||
const isOverHardLimit = prevContextTokens > allowedTokens
|
||||
|
||||
// Only trigger automatic condensation when the percentage threshold is met
|
||||
// If we're over the hard limit but below percentage, we'll use sliding window instead
|
||||
if (shouldCondenseByPercentage) {
|
||||
console.log(
|
||||
`[Condensation] Triggering automatic condensation: ${contextPercent.toFixed(1)}% >= ${effectiveThreshold}% threshold`,
|
||||
)
|
||||
// Attempt to intelligently condense the context
|
||||
const result = await summarizeConversation(
|
||||
messages,
|
||||
|
|
@ -159,14 +169,29 @@ export async function truncateConversationIfNeeded({
|
|||
if (result.error) {
|
||||
error = result.error
|
||||
cost = result.cost
|
||||
console.log(`[Condensation] Condensation failed: ${result.error}`)
|
||||
// If condensation fails and we're over the hard limit, fall through to sliding window
|
||||
} else {
|
||||
console.log(
|
||||
`[Condensation] Successfully condensed context from ${prevContextTokens} to ${result.newContextTokens} tokens`,
|
||||
)
|
||||
return { ...result, prevContextTokens }
|
||||
}
|
||||
} else if (isOverHardLimit) {
|
||||
// If we're over the hard limit but haven't reached the percentage threshold,
|
||||
// log this condition - we'll use sliding window truncation below
|
||||
console.log(
|
||||
`[Condensation] Context tokens (${prevContextTokens}) exceed allowed (${allowedTokens}), but percentage (${contextPercent.toFixed(1)}%) < threshold (${effectiveThreshold}%). Will use sliding window truncation.`,
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
// Fall back to sliding window truncation if needed
|
||||
// This happens when we're over the hard token limit regardless of percentage
|
||||
if (prevContextTokens > allowedTokens) {
|
||||
console.log(
|
||||
`[Condensation] Using sliding window truncation: ${prevContextTokens} tokens > ${allowedTokens} allowed`,
|
||||
)
|
||||
const truncatedMessages = truncateConversation(messages, 0.5, taskId)
|
||||
return { messages: truncatedMessages, prevContextTokens, summary: "", cost, error }
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue