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

Merge branch 'codex/simp-session-log-representation' into codex/simp-snapshot-fixture-inventory

Browse Source 
# Conflicts:
#	packages/support/acp-snapshot/README.md
#	packages/support/acp-snapshot/src/suite.ts
#	packages/support/acp-snapshot/tests/suite.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-15 16:03:33 +08:00
parent 17693d20c4 d0cf9cd411
commit dc00509910
305 changed files with 8786 additions and 2049 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/session.jsonl
Vendored
+1 -1
View File
@@ -1,2 +1,2 @@
{"type":"session","id":"ccdc749f-56f3-4267-9750-598b5c60b7b2","createdAt":600,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-nOQ4Gy"}
{"type":"request/header","seq":0,"time":4,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
{"type":"request/header","seq":0,"time":4,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/tool-schemas.golden.json
Vendored
+12
View File
@@ -0,0 +1,12 @@
{
"initial": [
{
"name": "t1",
"description": "D1",
"parameters": {
"type": "object"
}
}
],
"changes": []
}
packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/session.jsonl
Vendored
+2 -2
View File
@@ -1,4 +1,4 @@
{"type":"session","id":"12121212-3434-4545-8686-787878787878","createdAt":7,"cwd":"/rec/pin-cwd"}
{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
{"type":"request/header","seq":1,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"change"}}
{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/header","seq":1,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
{"type":"turn/start","seq":2,"time":7,"data":{"turn":1}}
packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/tool-schemas.golden.json
Vendored
+22
View File
@@ -0,0 +1,22 @@
{
"initial": [
{
"name": "t1",
"description": "D1",
"parameters": {
"type": "object"
}
}
],
"changes": [
[
{
"name": "t1",
"description": "D1",
"parameters": {
"type": "object"
}
}
]
]
}
packages/support/acp-snapshot/tests/normalize.spec.ts
+43
View File
@@ -5,6 +5,7 @@ import {
normalizeStdout,
scrubRequestHeaders,
scrubSystemPrompts,
scrubToolSchemas,
} from '../src/normalize.ts'
/**
@@ -238,3 +239,45 @@ describe('scrubSystemPrompts', () => {
expect(scrubSystemPrompts(out)).toBe(out)
})
})
describe('scrubToolSchemas', () => {
it('scrubs only tool-schema payloads while keeping prompts and prefixes verbatim', () => {
const header = JSON.stringify({
type: 'request/header', seq: 1, time: 2,
data: {
header: {
system: 'full prompt',
tools: [{ name: 'read', description: 'full schema', parameters: { type: 'object' } }],
messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'full prefix' }] }],
},
reason: 'initial',
},
})
const changed = JSON.stringify({
type: 'request/header', seq: 2, time: 3,
data: {
header: {
system: 'new prompt',
tools: [{ name: 'grep', description: 'new schema' }],
messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'changed prefix' }] }],
},
reason: 'change',
},
})
const systemOnly = JSON.stringify({
type: 'request/header', seq: 3, time: 4,
data: { header: { system: 'prompt only' }, reason: 'resume' },
})
const out = scrubToolSchemas(`${header}\n${changed}\n${systemOnly}\n`)
expect(out.match(/"tools":"{{tools}}"/g)).toHaveLength(2)
expect(out).not.toContain('full schema')
expect(out).not.toContain('new schema')
expect(out).toContain('full prompt')
expect(out).toContain('new prompt')
expect(out).toContain('full prefix')
expect(out).toContain('changed prefix')
expect(out.split('\n')[2]).toBe(systemOnly)
expect(scrubToolSchemas(out)).toBe(out)
})
})
packages/support/acp-snapshot/tests/suite.spec.ts
+81
View File
@@ -9,11 +9,16 @@ import {
fixtureContext,
formatSystemPromptSnapshot,
headerChangeCount,
formatToolSchemasSnapshot,
normalizedHeaders,
normalizedSystemPrompts,
normalizedToolSchemas,
parseToolSchemasSnapshot,
refreshFixtureReplacements,
sessionFixtureNames,
restorePinnedToolSchemas,
stabilizeRefreshLog,
unknownToolCallIds,
} from '../src/suite.ts'
/**
@@ -75,6 +80,7 @@ afterAll(async () => {
function staleRefreshFixtures(dir: string): void {
writeFileSync(join(dir, 'plain-turn', 'stdout.golden.jsonl'), 'stale stdout\n')
writeFileSync(join(dir, 'pin-turn', 'system-prompt.golden.md'), 'STALE PROMPT\n')
writeFileSync(join(dir, 'pin-turn', 'tool-schemas.golden.json'), '{"initial":[{"name":"stale"}],"changes":[]}\n')
const plainBehaviorFile = join(dir, 'plain-turn', 'behavior.json')
const plainBehavior = JSON.parse(readFileSync(plainBehaviorFile, 'utf8')) as Record<string, unknown>
@@ -132,6 +138,9 @@ describe('defineAcpSnapshotSuite: refresh write-back', () => {
'NEW PROMPT LINE',
'',
].join('\n'))
const schemas = readFileSync(join(refreshDir, 'pin-turn', 'tool-schemas.golden.json'), 'utf8')
expect(schemas).toContain('"description": "D1"')
expect(schemas).not.toContain('"name":"stale"')
})
})
@@ -277,6 +286,23 @@ describe('normalizedSystemPrompts', () => {
})
})
describe('normalizedToolSchemas', () => {
it('extracts normalized schema arrays and omits absent or non-array fields', () => {
const log = [
'{"type":"session","id":"a","createdAt":5,"cwd":"/w"}',
'{"type":"request/header","seq":0,"time":9,"data":{"header":{"tools":[{"name":"read","description":"work in /w"}]}}}',
'{"type":"request/header","seq":1,"time":9,"data":{"header":{}}}',
'{"type":"request/header","seq":2,"time":9,"data":{"header":{"tools":null}}}',
'{"type":"request/header","seq":3,"time":9,"data":{"header":null}}',
'{"type":"request/header","seq":4,"time":9,"data":{"header":"invalid"}}',
'',
].join('\n')
expect(normalizedToolSchemas(log, { sessionIds: [], cwd: '/w' })).toEqual([
[{ name: 'read', description: 'work in {{cwd}}' }],
])
})
})
describe('formatSystemPromptSnapshot', () => {
it('adds a missing terminal newline without changing an existing one', () => {
expect(formatSystemPromptSnapshot('prompt')).toBe('prompt\n')
@@ -304,6 +330,61 @@ describe('headerChangeCount', () => {
})
})
describe('tool-schema snapshots', () => {
const snapshot = {
initial: [{ name: 'read', description: 'Read a file.' }],
changes: [[{ name: 'grep', description: 'Search files.' }]],
}
it('formats and parses canonical structured JSON', () => {
const formatted = formatToolSchemasSnapshot(snapshot.initial, snapshot.changes)
expect(formatted).toBe(`${JSON.stringify(snapshot, null, 2)}\n`)
expect(parseToolSchemasSnapshot(formatted)).toEqual(snapshot)
})
it('rejects invalid top-level and field shapes', () => {
expect(() => parseToolSchemasSnapshot('null')).toThrow(/must be an object/)
expect(() => parseToolSchemasSnapshot('"invalid"')).toThrow(/must be an object/)
expect(() => parseToolSchemasSnapshot('[]')).toThrow(/must be an object/)
expect(() => parseToolSchemasSnapshot('{"initial":{},"changes":[]}')).toThrow(/array-valued/)
expect(() => parseToolSchemasSnapshot('{"initial":[],"changes":{}}')).toThrow(/array-valued/)
expect(() => parseToolSchemasSnapshot('{"initial":[],"changes":[{}]}')).toThrow(/array-valued/)
})
it('restores initial schemas into the pinned header token', () => {
expect(restorePinnedToolSchemas({ system: '{{system}}', tools: '{{tools}}' }, snapshot.initial))
.toEqual({ system: '{{system}}', tools: snapshot.initial })
})
it('rejects invalid headers and a missing tool token', () => {
expect(() => restorePinnedToolSchemas(null, snapshot.initial)).toThrow(/must be an object/)
expect(() => restorePinnedToolSchemas('invalid', snapshot.initial)).toThrow(/must be an object/)
expect(() => restorePinnedToolSchemas([], snapshot.initial)).toThrow(/must be an object/)
expect(() => restorePinnedToolSchemas({ tools: [] }, snapshot.initial)).toThrow(/must equal/)
})
})
describe('unknownToolCallIds', () => {
it('returns structured UNKNOWN_TOOL call ids and ignores other results', () => {
const log = [
'{"type":"tool/result","data":{"callId":"missing","error":{"code":"UNKNOWN_TOOL"}}}',
'{"type":"tool/result","data":{"callId":"failed","error":{"code":"EXECUTION_FAILED"}}}',
'{"type":"tool/result","data":null}',
'{"type":"tool/result","data":"invalid"}',
'{"type":"tool/result","data":{"error":null}}',
'{"type":"tool/result","data":{"error":"invalid"}}',
'{"type":"assistant/message","data":{"error":{"code":"UNKNOWN_TOOL"}}}',
'{"type":"tool/result","data":{"error":{"code":"UNKNOWN_TOOL"}}}',
'',
].join('\n')
expect(unknownToolCallIds(log)).toEqual(['missing', '<missing callId>'])
})
it('returns no failures for ordinary tool results', () => {
expect(unknownToolCallIds('{"type":"tool/result","data":{"callId":"ok"}}\n')).toEqual([])
})
})
describe('refreshFixtureReplacements', () => {
it('maps fresh ids and cwd values to the existing fixture values, skipping non-replacements', () => {
const log = (content: string): HarvestedLog => ({ id: 'diagnostic', createdAt: 1, content })