Merge remote-tracking branch 'origin/master' into dshw/pr-deepseek-harness-deepseek-harness-2781

snapshots/acp/acp.snapshot.ts

@@ -23,7 +23,11 @@ function snapshotMode(value: string | undefined): SnapshotSuiteOptions['mode'] {
   }
 }
 
-const controllerCases = [
+const controllerCases: readonly {
+  readonly name: string
+  readonly hasModelTurn: boolean
+  readonly configPath?: string
+}[] = [
   { name: 'handshake', hasModelTurn: false },
   { name: 'reject-extra-dirs', hasModelTurn: false },
   { name: 'cancel', hasModelTurn: true },
@@ -31,14 +35,25 @@ const controllerCases = [
   { name: 'escalation-approved', hasModelTurn: true },
   { name: 'escalation-rejected', hasModelTurn: true },
   { name: 'fs-escalation-approved', hasModelTurn: true },
+  {
+    name: 'image-compaction',
+    hasModelTurn: true,
+    configPath: join(corpusDir, 'image-compaction', 'cordis.yml'),
+  },
 ] as const
 
+function localScenarioSource(source: string | undefined): string | undefined {
+  return source?.includes('/') === false ? source : undefined
+}
+
 const scenarios: Scenario[] = controllerCases.map((controller) => {
   const manifestPath = join(corpusDir, controller.name, 'snapshot.yml')
   const manifest = parseSnapshotManifest(readFileSync(manifestPath, 'utf8'), manifestPath)
   if (manifest.recording === undefined || manifest.header === undefined) {
     throw new Error(`${controller.name}: ACP snapshot manifest lacks recording or header metadata`)
   }
+  const systemPromptSource = localScenarioSource(manifest.header.systemPromptSource)
+  const toolSchemasSource = localScenarioSource(manifest.header.toolSchemasSource)
   return {
     ...controller,
     recorded: manifest.recording === 'live',
@@ -46,8 +61,11 @@ const scenarios: Scenario[] = controllerCases.map((controller) => {
     ...(manifest.header.pin === true ? { pinsHeader: true } : {}),
     ...(manifest.header.changes === undefined ? {} : { expectedHeaderChanges: manifest.header.changes }),
     headerClass: manifest.header.class,
+    ...(systemPromptSource === undefined ? {} : { systemPromptSource }),
+    ...(toolSchemasSource === undefined ? {} : { toolSchemasSource }),
     ...(manifest.platform === 'posix' ? { posixOnly: true } : {}),
     ...(manifest.platform === 'pwsh' ? { pwshOnly: true } : {}),
+    ...(controller.configPath === undefined ? {} : { configPath: controller.configPath }),
     ...manifest.permission === undefined && manifest.environment === undefined
       ? {}
       : {

snapshots/acp/image-compaction/cordis.snapshot.yml

@@ -0,0 +1,64 @@
+# Keyless replay for the image-compaction scenario. This profile patch swaps
+# the adapter and re-pins the recorded vision model. The replay catalog declares image input,
+# so the strict read_image gate accepts the route and the tool result carries
+# the durable image block.
+- id: llm-deepseek
+  name: '@deepseek-ai/dsh-llm-deepseek'
+  disabled: true
+
+- id: acp
+  name: '@deepseek-ai/dsh-acp'
+  config:
+    provider: deepseek-official
+    model: deepseek-v4-flash-vision-exp
+
+- id: session-persistence-jsonl
+  name: '@deepseek-ai/dsh-session-persistence-jsonl'
+  config:
+    root: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+    compression: none
+
+- id: agent-instructions
+  name: '@deepseek-ai/dsh-agent-instructions'
+  config:
+    maxBytes: 65536
+
+- id: system-prompt
+  name: '@deepseek-ai/dsh-system-prompt'
+  config:
+    persona: |
+      You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
+
+      Verify your work by running the code or tests. Keep answers brief and factual.
+
+- insert:
+    - id: llm-replay
+      name: '@deepseek-ai/dsh-llm-replay'
+      config:
+        providers:
+          - id: deepseek-official
+            name: DeepSeek
+            models:
+              - id: deepseek-v4-flash
+                inputModalities: [text]
+              - id: deepseek-v4-pro
+                inputModalities: [text]
+              - id: deepseek-v4-flash-vision-exp
+                inputModalities: [text, image]
+                # Route-priced request images at the provider cap; the small
+                # context window turns that visual pressure into an automatic
+                # compaction the text-only heuristic would not trigger.
+                contextWindow: 11600
+                imageRequestTokens: 384
+
+- id: attachment-local
+  name: '@deepseek-ai/dsh-attachment-local'
+
+# Tight automatic compaction budget sized to the route-priced visual tokens of
+# the scenario's inline images: the text-only history stays under the
+# threshold, so a triggered compaction proves the routed model's image pricing
+# drove the pressure decision.
+- id: compaction-basic
+  name: '@deepseek-ai/dsh-compaction-basic'
+  config:
+    retainTokens: 100

snapshots/acp/image-compaction/cordis.yml

@@ -0,0 +1,42 @@
+# Image-compaction overlay: the image scenario plus a compaction budget the
+# scenario's inline images exceed only under route-priced visual tokens.
+# Adds the durable attachment store the read_image tool
+# commits through. The store resolves its root from $DSH_HOME, which the
+# snapshot harness scopes per run, so the patch itself carries no attachment
+# path. The ACP row selects the shipped vision model.
+- id: acp
+  name: '@deepseek-ai/dsh-acp'
+  config:
+    provider: deepseek-official
+    model: deepseek-v4-flash-vision-exp
+
+- id: session-persistence-jsonl
+  name: '@deepseek-ai/dsh-session-persistence-jsonl'
+  config:
+    root: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
+    compression: none
+
+- id: agent-instructions
+  name: '@deepseek-ai/dsh-agent-instructions'
+  config:
+    maxBytes: 65536
+
+- id: system-prompt
+  name: '@deepseek-ai/dsh-system-prompt'
+  config:
+    persona: |
+      You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
+
+      Verify your work by running the code or tests. Keep answers brief and factual.
+
+- id: attachment-local
+  name: '@deepseek-ai/dsh-attachment-local'
+
+# Tight automatic compaction budget sized to the route-priced visual tokens of
+# the scenario's inline images: the text-only history stays under the
+# threshold, so a triggered compaction proves the routed model's image pricing
+# drove the pressure decision.
+- id: compaction-basic
+  name: '@deepseek-ai/dsh-compaction-basic'
+  config:
+    retainTokens: 100

snapshots/acp/image-compaction/input.json

@@ -0,0 +1,86 @@
+{
+  "steps": [
+    {
+      "op": "initialize"
+    },
+    {
+      "op": "newSession"
+    },
+    {
+      "op": "promptContent",
+      "content": [
+        {
+          "type": "text",
+          "text": "Here are six reference screenshots of the dashboard: "
+        },
+        {
+          "type": "image",
+          "data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGP4z8AAAAMBAQDJ/pLvAAAAAElFTkSuQmCC",
+          "mimeType": "image/png"
+        },
+        {
+          "type": "text",
+          "text": " (frame 1) "
+        },
+        {
+          "type": "image",
+          "data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGP4z8AAAAMBAQDJ/pLvAAAAAElFTkSuQmCC",
+          "mimeType": "image/png"
+        },
+        {
+          "type": "text",
+          "text": " (frame 2) "
+        },
+        {
+          "type": "image",
+          "data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGP4z8AAAAMBAQDJ/pLvAAAAAElFTkSuQmCC",
+          "mimeType": "image/png"
+        },
+        {
+          "type": "text",
+          "text": " (frame 3) "
+        },
+        {
+          "type": "image",
+          "data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGP4z8AAAAMBAQDJ/pLvAAAAAElFTkSuQmCC",
+          "mimeType": "image/png"
+        },
+        {
+          "type": "text",
+          "text": " (frame 4) "
+        },
+        {
+          "type": "image",
+          "data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGP4z8AAAAMBAQDJ/pLvAAAAAElFTkSuQmCC",
+          "mimeType": "image/png"
+        },
+        {
+          "type": "text",
+          "text": " (frame 5) "
+        },
+        {
+          "type": "image",
+          "data": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGP4z8AAAAMBAQDJ/pLvAAAAAElFTkSuQmCC",
+          "mimeType": "image/png"
+        },
+        {
+          "type": "text",
+          "text": " (frame 6) "
+        },
+        {
+          "type": "text",
+          "text": "Acknowledge receipt briefly; we will discuss them next."
+        }
+      ]
+    },
+    {
+      "op": "promptContent",
+      "content": [
+        {
+          "type": "text",
+          "text": "Now reply with exactly the single word DONE."
+        }
+      ]
+    }
+  ]
+}

snapshots/acp/image-compaction/session.jsonl

@@ -0,0 +1,37 @@
+{"type":"session","version":0,"id":"{{session:1}}","createdAt":1783952000000,"cwd":"{{cwd}}","delegationDepth":0}
+{"type":"permission/preset","data":{"preset":"danger-full-access"}}
+{"type":"sandbox/mode","data":{"mode":"danger-full-access"}}
+{"type":"approval/policy","data":{"policy":"never"}}
+{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Here are six reference screenshots of the dashboard: "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 1) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 2) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 3) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 4) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 5) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 6) Acknowledge receipt briefly; we will discuss them next."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"}]}}
+{"type":"turn/start","data":{"turn":1}}
+{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
+{"type":"step/start","data":{"turn":1,"step":1}}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Here are six reference screenshots of the dashboard: "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 1) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 2) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 3) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 4) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 5) "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":" (frame 6) Acknowledge receipt briefly; we will discuss them next."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:2}}"},"surfaceOp":"append"}
+{"type":"session/title","data":{"title":"Here are six reference screenshots","messageSeqs":[7],"source":{"kind":"fallback"}}}
+{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp","contextWindow":11600}}
+{"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"Received six dashboard frames; ready to discuss."}}}}
+{"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
+{"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"Received six dashboard frames; ready to discuss."}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"{{message:3}}"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[12,13,14,15],"surfaceOp":"append"}
+{"type":"step/end","data":{"turn":1,"step":1}}
+{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
+{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Now reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"{{message:4}}"}]}}
+{"type":"turn/start","data":{"turn":2}}
+{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
+{"type":"compaction/start","data":{"compactionId":"{{id:1}}","turn":2}}
+{"type":"compaction/summary","data":{"compactionId":"{{id:1}}","summary":[{"type":"text","text":"Six identical 1x1 dashboard reference screenshots were shared and acknowledged."}],"rawOutput":[{"type":"text","text":"Six identical 1x1 dashboard reference screenshots were shared and acknowledged."}],"llmStreamCall":true,"shadowedRange":{"start":7,"end":7},"shadowedSeqs":[7],"shadowedTokenCount":366,"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp","maxTokens":8192,"usage":{"inputTokens":20,"outputTokens":16}}}
+{"type":"user/message","data":{"content":[{"type":"text","text":"This is an automatically generated checkpoint condensing an earlier span of the conversation to free up context. Treat the captured context as established background and build on it without restating it. Continue the task directly from the messages that follow, without acknowledging this checkpoint.\n\n<compacted-summary>"},{"type":"text","text":"Six identical 1x1 dashboard reference screenshots were shared and acknowledged."},{"type":"text","text":"</compacted-summary>"}],"source":{"kind":"plugin","plugin":"compact","compactionId":"{{id:1}}"},"role":"user","id":"{{message:5}}"},"sourceEventSeqs":[22,23,7],"surfaceOp":{"op":"replace","start":7,"end":7}}
+{"type":"compaction/end","data":{"compactionId":"{{id:1}}","turn":2}}
+{"type":"step/start","data":{"turn":2,"step":1}}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Now reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"{{message:4}}"},"surfaceOp":"append"}
+{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"system":"{{system}}","tools":"{{tools}}"},"reason":"series"}}
+{"type":"assistant/chunk","data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
+{"type":"assistant/chunk","data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
+{"type":"assistant/chunk","data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"{{message:6}}"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[29,30,31,32],"surfaceOp":"append"}
+{"type":"step/end","data":{"turn":2,"step":1}}
+{"type":"turn/end","data":{"turn":2,"reason":{"kind":"completed"}}}

snapshots/acp/image-compaction/snapshot.yml

@@ -0,0 +1,16 @@
+version: 1
+scenario: image-compaction
+profile: acp
+composition: image-compaction
+recording: authored
+header:
+  class: image-compaction
+  pin: true
+  systemPromptSource: session/read-image
+  toolSchemasSource: escalation-approved
+permission: danger-full-access
+input:
+  attachments:
+    - id: sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640
+      mediaType: image/png
+      data: iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElFTkSuQmCC

snapshots/acp/image-compaction/stdout.expected.jsonl

@@ -0,0 +1,8 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"mcpCapabilities":{"http":true},"promptCapabilities":{"image":true,"audio":false,"embeddedContext":false},"sessionCapabilities":{"close":{},"list":{},"resume":{}}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","category":"model","type":"select","currentValue":"[\"deepseek-official\",\"deepseek-v4-flash-vision-exp\"]","options":[{"group":"deepseek-official","name":"DeepSeek","options":[{"value":"[\"deepseek-official\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek-official\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"},{"value":"[\"deepseek-official\",\"deepseek-v4-flash-vision-exp\"]","name":"deepseek-v4-flash-vision-exp"}]}]}]}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","messageId":"{{messageId}}","content":{"type":"text","text":"Received six dashboard frames; ready to discuss."}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"usage_update","used":"{{usedTokens}}","size":11600}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","messageId":"{{messageId}}","content":{"type":"text","text":"DONE"}}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"usage_update","used":"{{usedTokens}}","size":11600}}}
+{"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}}

snapshots/acp/image-compaction/system-prompt.expected.md

@@ -0,0 +1 @@
+../../session/read-image/system-prompt.expected.md