xixu-me/deepseek-harness
1
0 Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

test: refresh terminology snapshots

Browse Source
This commit is contained in:
Turtle committed 2026-08-11 15:23:05 +08:00
1 parent 0c708cb10d
commit c6f3870b51
2 files changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
+1 -1
View File
@@ -15,7 +15,7 @@
{"type":"assistant/chunk","seq":13,"time":1785730459883,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":14,"time":1785730459883,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"6b62bed7-113a-4d2e-a6aa-b935a1063ee2"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12,13],"surfaceOp":"append"}
{"type":"tool/call","seq":15,"time":1785730459883,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}}
{"type":"tool/result","seq":16,"time":1785730459904,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Present the calling scope's tools in `mode` instead of the deployment\n * default. Nearest scope on the chain wins, so a preset's standing\n * declaration covers every agent joined under it.\n *\n * Scoped only, and one declaration per scope: this is how an agent preset\n * composes Code Mode agents beside native ones in the same process, and a\n * process-global override would be the `mode` config field instead.\n * @param mode - the presentation the covered agents' models see.\n * @returns the exact disposer that restores the deployment default.\n */\n presentAs(mode: ToolPresentationMode): () => void\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly inbox: Inbox;\n readonly status: AgentStatus;\n readLine truncated
{"type":"tool/result","seq":16,"time":1785730459904,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Present the calling scope's tools in `mode` instead of the deployment\n * default. Nearest scope on the chain wins, so a preset's standing\n * declaration covers every agent joined under it.\n *\n * Scoped only, and one declaration per scope: this is how an agent preset\n * composes Code Mode agents beside native ones in the same process, and a\n * process-global override would be the `mode` config field instead.\n * @param mode - the presentation the covered agents' models see.\n * @returns the exact disposer that restores the deployment default.\n */\n presentAs(mode: ToolPresentationMode): () => void\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-tool mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly inbox: Inbox;\n readonly status: AgentStatus;\n readonlLine truncated
{"type":"step/end","seq":17,"time":1785730459904,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":18,"time":1785730459916,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":19,"time":1784449176734,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
scripts/snapshots/translation-prompt-v4/request-response.expected.json
+1 -1
View File
@@ -4,7 +4,7 @@
"messages": [
{
"role": "system",
"content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the complete source document from English to Chinese, producing natural, professional technical prose.\n\nRead each complete semantic unit, understand it, and restate it as a native technical author would write it in the target language. Do not mechanically preserve source-language syntax. Then verify the translation against the source clause by clause: preserve every proposition and add none. Fluency never justifies losing or altering meaning, and completeness never justifies unnatural word-for-word prose.\n\n## Priority\n\nApply these authorities in order:\n\n1. Preserve the source meaning and the required document structure, protected content, and formatting.\n2. Follow the injected terminology table exactly.\n3. Use the injected whole-document gold pairs to calibrate target-language voice and phrasing.\n4. Apply the general writing guidance and illustrative examples in this prompt.\n\nA lower-priority rule may refine but never override a higher-priority requirement. Gold pairs calibrate voice; they are not a translation memory. No style preference, gold-pair phrasing, or embedded example may override source meaning, required structure, protected content, or the terminology table.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains the same document frame as the source: heading hierarchy and order, list kinds and item counts, ordered-list starts, table rows and columns, link targets, and code blocks.\n- Paragraph boundaries may change within the same structural unit when the target language needs different semantic grouping. Do not merge or move content across headings, list items, table cells, or other independent structural units.\n- Keep each prose paragraph on one physical line. Use paragraph breaks, not hard-wrapped lines inside a paragraph.\n- Fenced code blocks must be byte-identical to the source, including info strings, whitespace, and ALL comments inside them. Do NOT translate or reformat any content inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans must be kept verbatim. This includes commands, flags, paths, identifiers, API and event names, config keys, protocol values, version numbers, and other machine-readable tokens. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Translate link text; do not change link targets.\n- Language switcher line: when an English source contains `English | [中文](source-filename.zh.md)`, write `[English](source-filename.md) | 中文`. When a Chinese source contains `[English](source-filename.md) | 中文`, write `English | [中文](source-filename.zh.md)`. Do NOT copy the source switcher unchanged. If the source has no switcher, do not invent a filename or switcher; the pipeline inserts the canonical target switcher after parsing `<final>`.\n- Preserve emphasis marker types and the semantic spans they cover. Do not add, remove, move, or change bold and italic markers.\n\n### Faithfulness\n- Preserve every proposition in the source and add none. Every sentence, list item, note, FIXME, warning, example, caveat, prerequisite, and guarantee must have an equivalent in the translation. Count list items on both sides.\n- Preserve actors, objects, conditions, exceptions, negation, modality, causal relationships, and distinctions between concepts.\n- Preserve the exact strength and orientation of contracts. Completion and lifecycle conditions, failure behavior, directions and data flow, normal and exceptional result channels, ownership changes, and quantitative bounds must not be weakened, strengthened, reversed, or merged.\n- Translate ideas rather than source-language idioms, but never use fluency as a reason to omit or alter meaning.\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native technical author. If an expression sounds like a word-for-word rendering from the source language, rephrase it.\n- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.\n- Name an actor when the target language would otherwise obscure an actor that the source states or unambiguously implies. Never invent responsibility merely to avoid a passive construction.\n- Prefer established target-language engineering terms over literal renderings. Replace metaphors with direct descriptions that preserve the source meaning.\n- Use polite imperative forms where the text instructs the reader to do something. In Chinese, address the reader as `你`, not `您`.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences where the target language needs a pause. Avoid run-on sentences.\n- UseLine truncated
"content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the complete source document from English to Chinese, producing natural, professional technical prose.\n\nRead each complete semantic unit, understand it, and restate it as a native technical author would write it in the target language. Do not mechanically preserve source-language syntax. Then verify the translation against the source clause by clause: preserve every proposition and add none. Fluency never justifies losing or altering meaning, and completeness never justifies unnatural word-for-word prose.\n\n## Priority\n\nApply these authorities in order:\n\n1. Preserve the source meaning and the required document structure, protected content, and formatting.\n2. Follow the injected terminology table exactly.\n3. Use the injected whole-document gold pairs to calibrate target-language voice and phrasing.\n4. Apply the general writing guidance and illustrative examples in this prompt.\n\nA lower-priority rule may refine but never override a higher-priority requirement. Gold pairs calibrate voice; they are not a translation memory. No style preference, gold-pair phrasing, or embedded example may override source meaning, required structure, protected content, or the terminology table.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains the same document frame as the source: heading hierarchy and order, list kinds and item counts, ordered-list starts, table rows and columns, link targets, and code blocks.\n- Paragraph boundaries may change within the same structural unit when the target language needs different semantic grouping. Do not merge or move content across headings, list items, table cells, or other independent structural units.\n- Keep each prose paragraph on one physical line. Use paragraph breaks, not hard-wrapped lines inside a paragraph.\n- Fenced code blocks must be byte-identical to the source, including info strings, whitespace, and ALL comments inside them. Do NOT translate or reformat any content inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans must be kept verbatim. This includes commands, flags, paths, identifiers, API and event names, config keys, protocol values, version numbers, and other machine-readable tokens. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Translate link text; do not change link targets.\n- Language switcher line: when an English source contains `English | [中文](source-filename.zh.md)`, write `[English](source-filename.md) | 中文`. When a Chinese source contains `[English](source-filename.md) | 中文`, write `English | [中文](source-filename.zh.md)`. Do NOT copy the source switcher unchanged. If the source has no switcher, do not invent a filename or switcher; the pipeline inserts the canonical target switcher after parsing `<final>`.\n- Preserve emphasis marker types and the semantic spans they cover. Do not add, remove, move, or change bold and italic markers.\n\n### Faithfulness\n- Preserve every proposition in the source and add none. Every sentence, list item, note, FIXME, warning, example, caveat, prerequisite, and guarantee must have an equivalent in the translation. Count list items on both sides.\n- Preserve actors, objects, conditions, exceptions, negation, modality, causal relationships, and distinctions between concepts.\n- Preserve the exact strength and orientation of contracts. Completion and lifecycle conditions, failure behavior, directions and data flow, normal and exceptional result channels, ownership changes, and quantitative bounds must not be weakened, strengthened, reversed, or merged.\n- Translate ideas rather than source-language idioms, but never use fluency as a reason to omit or alter meaning.\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native technical author. If an expression sounds like a word-for-word rendering from the source language, rephrase it.\n- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.\n- Name an actor when the target language would otherwise obscure an actor that the source states or unambiguously implies. Never invent responsibility merely to avoid a passive construction.\n- Prefer established target-language engineering terms over literal renderings. Replace metaphors with direct descriptions that preserve the source meaning.\n- Use polite imperative forms where the text instructs the reader to do something. In Chinese, address the reader as `你`, not `您`.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences where the target language needs a pause. Avoid run-on sentences.\n- UseLine truncated
},
{
"role": "user",