Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into codex/simp-session-log-representation

Browse Source 
# Conflicts:
#	docs/cordis-catalog/services.md
#	docs/rfc/INDEX.md
#	docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md
#	docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md
#	packages/support/acp-snapshot/README.md
#	packages/support/acp-snapshot/src/normalize.ts
#	packages/support/acp-snapshot/src/suite.ts
#	packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/session.jsonl
#	packages/support/acp-snapshot/tests/suite.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-15 15:53:56 +08:00
parent 649865043d 9cd31c7259
commit 281eed3e57
290 changed files with 5428 additions and 2039 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
packages/support/acp-snapshot/src/normalize.ts
View File

@@ -1,8 +1,8 @@
/**
* Pure ACP transcript and session-log normalizers. They scrub session ids, temp cwd, RPC ids,
* timestamps, and hook duration while preserving deterministic event sequence numbers.
* Request-header scrubbers stay separate so one scenario per header class can pin tools and a
* readable prompt while other fixtures omit duplicated header bulk.
* Request-header scrubbers stay composable so one scenario per header class can pin prompt and
* tool-schema sidecars while retaining any model-visible prefix in the session log.
* @module @deepseek-ai/dsh-acp-snapshot/normalize
*/
@@ -123,7 +123,21 @@ export function normalizeSessionLog(rawLog: string, ctx: NormalizeContext): stri
* @returns The JSONL with system-prompt content tokenized.
*/
export function scrubSystemPrompts(rawLog: string): string {
return scrubHeaderContent(rawLog, false)
return scrubHeaderContent(rawLog, { system: true })
}
/**
* Replace tool schemas in full request-header snapshots with `{{tools}}`
* tokens while retaining field presence. System prompts and session-prefix
* messages stay verbatim so pinning fixtures can move only schema bulk into
* their dedicated JSON sidecar. Lines without a tool payload pass through
* byte-for-byte; the transform is idempotent.
*
* @param rawLog The raw session `.jsonl` content.
* @returns The JSONL with tool-schema content tokenized.
*/
export function scrubToolSchemas(rawLog: string): string {
return scrubHeaderContent(rawLog, { tools: true })
}
/**
@@ -138,11 +152,18 @@ export function scrubSystemPrompts(rawLog: string): string {
* @returns The JSONL with all header bulk tokenized, other lines byte-identical.
*/
export function scrubRequestHeaders(rawLog: string): string {
return scrubHeaderContent(rawLog, true)
return scrubHeaderContent(rawLog, { system: true, tools: true, prefix: true })
}
/** Transform header content, optionally including tool schemas and the session prefix. */
function scrubHeaderContent(rawLog: string, scrubToolsAndPrefix: boolean): string {
/** Which independent request-header payloads a scrubber replaces. */
interface HeaderScrubOptions {
system?: boolean
tools?: boolean
prefix?: boolean
}
/** Transform the selected request-header payloads. */
function scrubHeaderContent(rawLog: string, options: HeaderScrubOptions): string {
const lines = rawLog.split('\n')
const out = lines.map((line) => {
if (line.trim().length === 0) return line
@@ -153,9 +174,9 @@ function scrubHeaderContent(rawLog: string, scrubToolsAndPrefix: boolean): strin
const header = data.header as Record<string, unknown> | null | undefined
if (header === null || typeof header !== 'object') return line
let touched = false
if ('system' in header) { header.system = SYSTEM; touched = true }
if (scrubToolsAndPrefix && 'tools' in header) { header.tools = TOOLS; touched = true }
if (scrubToolsAndPrefix && Array.isArray(header.messagePrefix)) {
if (options.system === true && 'system' in header) { header.system = SYSTEM; touched = true }
if (options.tools === true && 'tools' in header) { header.tools = TOOLS; touched = true }
if (options.prefix === true && Array.isArray(header.messagePrefix)) {
header.messagePrefix = header.messagePrefix.map(() => MESSAGE_PREFIX)
touched = true
}