{"type":"agent/inbox/spliced","seq":0,"time":1785498803392,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Inspect the exact tools service API and tools/pre-execute event with cordis_inspect, then reply with exactly CORDIS_INSPECT_JSDOC_OK."}],"source":{"kind":"user"},"role":"user","id":"3a6e7222-9340-429e-bec7-c30fcd063c70"}]}}
{"type":"user/message","seq":4,"time":1785498803419,"data":{"content":[{"type":"text","text":"Inspect the exact tools service API and tools/pre-execute event with cordis_inspect, then reply with exactly CORDIS_INSPECT_JSDOC_OK."}],"source":{"kind":"user"},"role":"user","id":"3a6e7222-9340-429e-bec7-c30fcd063c70"},"surfaceOp":"append"}
{"type":"user/message","seq":5,"time":1785730459873,"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":"f9a387d6-bd6f-4613-9c11-5768017feb5c"},"surfaceOp":"append"}
{"type":"session/title","seq":6,"time":1785730459873,"data":{"title":"Inspect the exact tools service","messageSeqs":[4],"source":{"kind":"fallback"}}}
{"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 * 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 i
{"type":"tool/result","seq":26,"time":1785730459929,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"inspect-tools-event"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-event","content":[{"type":"text","text":"## events\n- tools/pre-execute [waterfall] — Allow, deny, or ask before dispatch.\n /**\n * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing\n * approval support turns `ask` into denial. Async gates must observe\n * `exec.signal`; the registry rechecks cancellation after they settle but\n * never abandons their promise.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.\n * @param exec - the pending call (name, parsed arguments, caller agent).\n * @mode waterfall\n */\n 'tools/pre-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>\nwaterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() short-circuits the chain."}],"isError":false}],"role":"user","id":"c187306a-d73c-4bcd-b76c-8607ddbc0974"}},"sourceEventSeqs":[25],"surfaceOp":"append"}
