openvibers/openvibe.contracts Commits
openvibe-contracts 0.421.0: every AI call measured everywhere (#475)
Changes
@@@ -1,5 +1,31 @@# Changelog++## 0.421.0 — 2026-11-12++++**Every AI call, measured everywhere** (ai-metrics.md).++++- **`ai.call.recorded@1` 1.1.0** adds, all optional:++ - `operation` (chat, completion, embedding, image, image edit, speech, transcription, translation, rerank,++ moderation, decision, realtime, batch, tool);++ - `streamed`, and `tps` (the decode speed after the first token);++ - `queue_ms`;++ - `task`, `task_id` and `task_ms`, so cost and time add up per task;++ - `harness`, and `place` (provider, the person's machine, community, a plan, OpenVibe's hosts);++ - `error_class`, `fallbacks` and `cache_hit` (an exact-cache answer);++ - `tool_calls` and `region`.++- **`ai.call-report@1`:** up to 100 calls a product made without OpenVibe.AI (Actor, Codes harness turns, Link's local++ models through Bot, Vibe). They go to AI's `POST /api/v1/usage/calls`. AI prices any that bring no price, records++ each once (by system + run or turn id) and publishes `ai.call.recorded@1`. The capability is `ai.usage.report`.++- **`report.ai-performance@1`:** how calls performed for one group (model, provider, operation, system, task, place,++ harness):++ - success, fallback, streamed and cache-hit rates;++ - TTFT, latency and tokens per second at p50, p90 and p95;++ - tokens, charged and list cost, and cache savings;++ - cost and time per task;++ - the top errors.++++ Public answers group by model, provider or operation, with at least 20 calls.++## 0.420.0 — 2026-11-12**One agent system, measured.** These contracts carry the decisions in `one-system-v2.md`, which come from reading 24nnew file mode 100644@@@ -0,0 +1,359 @@++{++ "$schema": "https://json-schema.org/draft/2020-12/schema",++ "$id": "https://openvibe.network/contracts/ai/call-report.v1.json",++ "title": "AiCallReport",++ "description": "ai.call-report@1 (ai-metrics.md): up to 100 AI calls a product made without OpenVibe.AI (Actor’s own model calls, a Codes harness turn, a local model on a person’s machine through Bot, Vibe), sent to AI’s POST /api/v1/usage/calls with the capability ai.usage.report. Each call is ai.call.recorded@1’s shape; the price is optional (AI prices from its rate cards: the charged amount first, then the list price) and SYSTEM + RUN_ID or TURN_ID is the idempotency key (a call sent twice is recorded once). AI publishes each as ai.call.recorded@1.",++ "type": "object",++ "additionalProperties": false,++ "required": [++ "calls"++ ],++ "properties": {++ "calls": {++ "type": "array",++ "minItems": 1,++ "maxItems": 100,++ "items": {++ "type": "object",++ "required": [++ "system",++ "provider",++ "model",++ "outcome",++ "at"++ ],++ "additionalProperties": false,++ "properties": {++ "subject": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 128,++ "description": "The person the call was made for, or null when the call was anonymous."++ },++ "attribution": {++ "type": "string",++ "maxLength": 200,++ "description": "The site or app the call came from, as '<type>:<id>' (for example 'site:design'), empty when nothing is known."++ },++ "surface": {++ "type": "string",++ "maxLength": 200,++ "description": "The product surface: 'design.generate', 'codes.turn', 'ai.generate'. Free text, so a new surface needs no new contract."++ },++ "system": {++ "type": "string",++ "maxLength": 100,++ "description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."++ },++ "provider": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 128++ },++ "model": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 200++ },++ "effort": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 64,++ "description": "The reasoning effort the call asked for, when it asked for one."++ },++ "paid_by": {++ "type": "string",++ "enum": [++ "own_key",++ "openvibe_key",++ "plan",++ "own_machine",++ "free_tier",++ "network_allowance",++ "org_key"++ ]++ },++ "paid_by_detail": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 200,++ "description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."++ },++ "input": {++ "type": "integer",++ "minimum": 0,++ "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields."++ },++ "output": {++ "type": "integer",++ "minimum": 0++ },++ "reasoning": {++ "type": "integer",++ "minimum": 0++ },++ "cache_read": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write_ttl": {++ "type": [++ "string",++ "null"++ ],++ "enum": [++ "5m",++ "1h",++ null++ ],++ "description": "How long the written cache entry lives, when the provider says."++ },++ "images": {++ "type": "integer",++ "minimum": 0++ },++ "audio_seconds": {++ "type": "number",++ "minimum": 0++ },++ "video_seconds": {++ "type": "number",++ "minimum": 0++ },++ "list_cost_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the tokens cost at the human-typed list prices. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "charged_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the payer was actually charged. A person's own key is never charged here: 0. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "fee_usd": {++ "type": "number",++ "minimum": 0,++ "description": "The network's fee on top of the cost, when the OpenVibe key paid. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "cache_saved_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the cached tokens saved against the plain input price. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "price_source": {++ "type": "string",++ "maxLength": 64,++ "description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price). Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "price_date": {++ "type": [++ "string",++ "null"++ ],++ "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",++ "description": "The day the price was checked, when it was. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "latency_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0++ },++ "ttft_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Time to the first token, when the call streamed and it was measured."++ },++ "attempts": {++ "type": "integer",++ "minimum": 0++ },++ "outcome": {++ "type": "string",++ "enum": [++ "succeeded",++ "failed",++ "cancelled",++ "cached"++ ]++ },++ "run_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 100++ },++ "turn_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 100++ },++ "at": {++ "type": "string",++ "format": "date-time"++ },++ "operation": {++ "enum": [++ "chat",++ "completion",++ "embedding",++ "image",++ "image_edit",++ "speech",++ "transcription",++ "translation",++ "rerank",++ "moderation",++ "decision",++ "realtime",++ "batch",++ "tool",++ "other",++ null++ ],++ "description": "Since 1.1.0: what kind of call it was."++ },++ "streamed": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."++ },++ "tps": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."++ },++ "queue_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."++ },++ "task": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."++ },++ "task_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."++ },++ "task_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."++ },++ "harness": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."++ },++ "place": {++ "enum": [++ "provider",++ "machine",++ "community",++ "plan",++ "host",++ null++ ],++ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."++ },++ "error_class": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."++ },++ "fallbacks": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "maximum": 50,++ "description": "Since 1.1.0: how many offers failed before the one that answered."++ },++ "cache_hit": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."++ },++ "tool_calls": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: tool calls the model asked for in this call."++ },++ "region": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 40,++ "description": "Since 1.1.0: the provider region or data centre, when known."++ }++ },++ "anyOf": [++ {++ "required": [++ "run_id"++ ]++ },++ {++ "required": [++ "turn_id"++ ]++ }++ ]++ }++ }++ }++}@@@ -1643,7 +1643,7 @@},{"id": "ai.call.recorded",-- "version": "1.0.0",++ "version": "1.1.0","owner": "ai","schema": "events/payloads/ai.call.recorded.v1.json","visibility": "first-party",@@@ -1651,6 +1651,24 @@"status": "active","adr": "ADR-033"},++ {++ "id": "ai.call-report",++ "version": "1.0.0",++ "owner": "ai",++ "schema": "ai/call-report.v1.json",++ "visibility": "internal",++ "compatibility": "backward",++ "status": "active"++ },++ {++ "id": "report.ai-performance",++ "version": "1.0.0",++ "owner": "report",++ "schema": "report/ai-performance.v1.json",++ "visibility": "internal",++ "compatibility": "backward",++ "status": "active"++ },{"id": "ai.run.queued","version": "1.0.0",@@@ -2,7 +2,7 @@"$schema": "https://json-schema.org/draft/2020-12/schema","$id": "https://openvibe.network/contracts/events/payloads/ai.call.recorded.v1.json","title": "AiCallRecordedPayload",-- "description": "ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai.",++ "description": "ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai. Since 1.1.0 (ai-metrics.md): OPERATION, STREAMED, TPS, QUEUE_MS, TASK, TASK_ID, TASK_MS, HARNESS, PLACE, ERROR_CLASS, FALLBACKS, CACHE_HIT, TOOL_CALLS and REGION, all optional. Products other than AI send their calls to POST /api/v1/usage/calls (ai.call-report@1); AI prices and publishes them.","type": "object","required": ["system",@@@ -32,7 +32,10 @@"additionalProperties": false,"properties": {"subject": {-- "type": ["string", "null"],++ "type": [++ "string",++ "null"++ ],"maxLength": 128,"description": "The person the call was made for, or null when the call was anonymous."},@@@ -51,50 +54,298 @@"maxLength": 100,"description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."},-- "provider": { "type": ["string", "null"], "maxLength": 128 },-- "model": { "type": ["string", "null"], "maxLength": 200 },-- "effort": { "type": ["string", "null"], "maxLength": 64, "description": "The reasoning effort the call asked for, when it asked for one." },++ "provider": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 128++ },++ "model": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 200++ },++ "effort": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 64,++ "description": "The reasoning effort the call asked for, when it asked for one."++ },"paid_by": {"type": "string",-- "enum": ["own_key", "openvibe_key", "plan", "own_machine", "free_tier", "network_allowance", "org_key"]++ "enum": [++ "own_key",++ "openvibe_key",++ "plan",++ "own_machine",++ "free_tier",++ "network_allowance",++ "org_key"++ ]},"paid_by_detail": {-- "type": ["string", "null"],++ "type": [++ "string",++ "null"++ ],"maxLength": 200,"description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."},-- "input": { "type": "integer", "minimum": 0, "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields." },-- "output": { "type": "integer", "minimum": 0 },-- "reasoning": { "type": "integer", "minimum": 0 },-- "cache_read": { "type": "integer", "minimum": 0 },-- "cache_write": { "type": "integer", "minimum": 0 },++ "input": {++ "type": "integer",++ "minimum": 0,++ "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields."++ },++ "output": {++ "type": "integer",++ "minimum": 0++ },++ "reasoning": {++ "type": "integer",++ "minimum": 0++ },++ "cache_read": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write": {++ "type": "integer",++ "minimum": 0++ },"cache_write_ttl": {-- "type": ["string", "null"],-- "enum": ["5m", "1h", null],++ "type": [++ "string",++ "null"++ ],++ "enum": [++ "5m",++ "1h",++ null++ ],"description": "How long the written cache entry lives, when the provider says."},-- "images": { "type": "integer", "minimum": 0 },-- "audio_seconds": { "type": "number", "minimum": 0 },-- "video_seconds": { "type": "number", "minimum": 0 },-- "list_cost_usd": { "type": "number", "minimum": 0, "description": "What the tokens cost at the human-typed list prices." },-- "charged_usd": { "type": "number", "minimum": 0, "description": "What the payer was actually charged. A person's own key is never charged here: 0." },-- "fee_usd": { "type": "number", "minimum": 0, "description": "The network's fee on top of the cost, when the OpenVibe key paid." },-- "cache_saved_usd": { "type": "number", "minimum": 0, "description": "What the cached tokens saved against the plain input price." },++ "images": {++ "type": "integer",++ "minimum": 0++ },++ "audio_seconds": {++ "type": "number",++ "minimum": 0++ },++ "video_seconds": {++ "type": "number",++ "minimum": 0++ },++ "list_cost_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the tokens cost at the human-typed list prices."++ },++ "charged_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the payer was actually charged. A person's own key is never charged here: 0."++ },++ "fee_usd": {++ "type": "number",++ "minimum": 0,++ "description": "The network's fee on top of the cost, when the OpenVibe key paid."++ },++ "cache_saved_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the cached tokens saved against the plain input price."++ },"price_source": {"type": "string","maxLength": 64,"description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price)."},-- "price_date": { "type": ["string", "null"], "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$", "description": "The day the price was checked, when it was." },-- "latency_ms": { "type": ["integer", "null"], "minimum": 0 },-- "ttft_ms": { "type": ["integer", "null"], "minimum": 0, "description": "Time to the first token, when the call streamed and it was measured." },-- "attempts": { "type": "integer", "minimum": 0 },++ "price_date": {++ "type": [++ "string",++ "null"++ ],++ "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",++ "description": "The day the price was checked, when it was."++ },++ "latency_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0++ },++ "ttft_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Time to the first token, when the call streamed and it was measured."++ },++ "attempts": {++ "type": "integer",++ "minimum": 0++ },"outcome": {"type": "string",-- "enum": ["succeeded", "failed", "cancelled", "cached"]++ "enum": [++ "succeeded",++ "failed",++ "cancelled",++ "cached"++ ]++ },++ "run_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 100++ },++ "turn_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 100++ },++ "at": {++ "type": "string",++ "format": "date-time"++ },++ "operation": {++ "enum": [++ "chat",++ "completion",++ "embedding",++ "image",++ "image_edit",++ "speech",++ "transcription",++ "translation",++ "rerank",++ "moderation",++ "decision",++ "realtime",++ "batch",++ "tool",++ "other",++ null++ ],++ "description": "Since 1.1.0: what kind of call it was."++ },++ "streamed": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."++ },++ "tps": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."++ },++ "queue_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."++ },++ "task": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."++ },++ "task_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."++ },++ "task_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."++ },++ "harness": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."++ },++ "place": {++ "enum": [++ "provider",++ "machine",++ "community",++ "plan",++ "host",++ null++ ],++ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."++ },++ "error_class": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."++ },++ "fallbacks": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "maximum": 50,++ "description": "Since 1.1.0: how many offers failed before the one that answered."++ },++ "cache_hit": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."++ },++ "tool_calls": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: tool calls the model asked for in this call."},-- "run_id": { "type": ["string", "null"], "maxLength": 100 },-- "turn_id": { "type": ["string", "null"], "maxLength": 100 },-- "at": { "type": "string", "format": "date-time" }++ "region": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 40,++ "description": "Since 1.1.0: the provider region or data centre, when known."++ }}}nnew file mode 100644@@@ -0,0 +1,352 @@++{++ "$schema": "https://json-schema.org/draft/2020-12/schema",++ "$id": "https://openvibe.network/contracts/report/ai-performance.v1.json",++ "title": "ReportAiPerformance",++ "description": "report.ai-performance@1 (ai-metrics.md): how AI calls performed over a range, for one group (a model, a provider, an operation, a system, a task). Percentiles come from log-scale histograms (within one bucket’s width). Public answers group by model, provider or operation only and show a group with at least 20 calls; system and task groups are for staff. Money is USD; tokens per second is the decode speed after the first token; cost per task sums the calls that share a task id.",++ "type": "object",++ "additionalProperties": false,++ "required": [++ "group",++ "key",++ "calls"++ ],++ "properties": {++ "group": {++ "enum": [++ "model",++ "provider",++ "operation",++ "system",++ "task",++ "place",++ "harness"++ ]++ },++ "key": {++ "type": "string",++ "maxLength": 200++ },++ "provider": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120++ },++ "range": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "from": {++ "type": "string",++ "format": "date"++ },++ "to": {++ "type": "string",++ "format": "date"++ }++ }++ },++ "calls": {++ "type": "integer",++ "minimum": 0++ },++ "succeeded": {++ "type": "integer",++ "minimum": 0++ },++ "errors": {++ "type": "integer",++ "minimum": 0++ },++ "success_rate": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1++ },++ "fallback_rate": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1++ },++ "streamed_share": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1++ },++ "cache_hit_rate": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1++ },++ "cache_read_share": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1,++ "description": "Cache-read tokens as a share of all input tokens."++ },++ "ttft_ms": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "latency_ms": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "tps": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "tokens": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "input": {++ "type": "integer",++ "minimum": 0++ },++ "output": {++ "type": "integer",++ "minimum": 0++ },++ "reasoning": {++ "type": "integer",++ "minimum": 0++ },++ "cache_read": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "cost": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "charged_usd": {++ "type": "number",++ "minimum": 0++ },++ "list_usd": {++ "type": "number",++ "minimum": 0++ },++ "cache_saved_usd": {++ "type": "number",++ "minimum": 0++ },++ "per_call_usd": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "per_million_output_usd": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ }++ }++ },++ "tasks": {++ "type": [++ "object",++ "null"++ ],++ "additionalProperties": false,++ "properties": {++ "count": {++ "type": "integer",++ "minimum": 0++ },++ "cost_per_task_usd": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "time_per_task_ms": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ }++ }++ },++ "top_errors": {++ "type": "array",++ "maxItems": 5,++ "items": {++ "type": "object",++ "additionalProperties": false,++ "required": [++ "error_class",++ "count"++ ],++ "properties": {++ "error_class": {++ "type": "string",++ "maxLength": 60++ },++ "count": {++ "type": "integer",++ "minimum": 0++ }++ }++ }++ }++ }++}nnew file mode 100644@@@ -0,0 +1,13 @@++{++ "calls": [++ {++ "system": "actor",++ "run_id": "r1",++ "provider": "deepseek",++ "model": "x",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z",++ "operation": "telepathy"++ }++ ]++}nnew file mode 100644@@@ -0,0 +1,11 @@++{++ "calls": [++ {++ "system": "actor",++ "provider": "deepseek",++ "model": "x",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ }++ ]++}nnew file mode 100644@@@ -0,0 +1,812 @@++{++ "calls": [++ {++ "system": "actor",++ "run_id": "r0",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r1",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r2",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r3",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r4",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r5",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r6",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r7",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r8",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r9",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r10",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r11",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r12",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r13",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r14",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r15",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r16",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r17",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r18",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r19",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r20",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r21",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r22",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r23",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r24",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r25",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r26",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r27",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r28",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r29",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r30",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r31",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r32",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r33",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r34",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r35",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r36",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r37",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r38",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r39",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r40",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r41",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r42",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r43",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r44",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r45",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r46",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r47",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r48",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r49",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r50",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r51",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r52",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r53",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r54",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r55",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r56",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r57",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r58",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r59",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r60",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r61",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r62",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r63",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r64",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r65",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r66",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r67",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r68",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r69",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r70",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r71",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r72",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r73",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r74",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r75",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r76",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r77",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r78",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r79",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r80",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r81",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r82",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r83",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r84",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r85",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r86",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r87",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r88",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r89",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r90",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r91",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r92",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r93",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r94",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r95",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r96",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r97",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r98",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r99",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ },++ {++ "system": "actor",++ "run_id": "r100",++ "provider": "p",++ "model": "m",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z"++ }++ ]++}nnew file mode 100644@@@ -0,0 +1,49 @@++{++ "calls": [++ {++ "system": "actor",++ "turn_id": "tsk_01JD8C4QJ7Z3K9W2X5V6N1M0PA:3",++ "provider": "deepseek",++ "model": "deepseek-v4-flash",++ "surface": "actor.task",++ "paid_by": "openvibe_key",++ "input": 12000,++ "output": 800,++ "reasoning": 0,++ "cache_read": 9000,++ "cache_write": 0,++ "cache_write_ttl": null,++ "images": 0,++ "audio_seconds": 0,++ "video_seconds": 0,++ "latency_ms": 4100,++ "ttft_ms": 610,++ "attempts": 1,++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z",++ "operation": "chat",++ "streamed": true,++ "tps": 88.4,++ "task": "actor.task",++ "task_id": "tsk_01JD8C4QJ7Z3K9W2X5V6N1M0PA",++ "harness": "openvibe",++ "place": "provider",++ "tool_calls": 2++ },++ {++ "system": "node",++ "run_id": "cmd_01JD8C4QJ7Z3K9W2X5V6N1M0PB",++ "provider": "ollama",++ "model": "qwen2.5:3b",++ "outcome": "succeeded",++ "at": "2026-11-12T23:30:00Z",++ "operation": "chat",++ "streamed": true,++ "ttft_ms": 900,++ "tps": 12.5,++ "place": "machine",++ "input": 300,++ "output": 120++ }++ ]++}nnew file mode 100644@@@ -0,0 +1,5 @@++{++ "group": "person",++ "key": "usr_x",++ "calls": 3++}nnew file mode 100644@@@ -0,0 +1,74 @@++{++ "group": "model",++ "key": "deepseek-v4-flash",++ "provider": "deepseek",++ "range": {++ "from": "2026-11-05",++ "to": "2026-11-12"++ },++ "calls": 18420,++ "succeeded": 18311,++ "errors": 109,++ "success_rate": 0.9941,++ "fallback_rate": 0.012,++ "streamed_share": 0.71,++ "cache_hit_rate": 0.04,++ "cache_read_share": 0.63,++ "ttft_ms": {++ "p50": 540,++ "p90": 980,++ "p95": 1310,++ "n": 13080++ },++ "latency_ms": {++ "p50": 3900,++ "p90": 9100,++ "p95": 12800,++ "n": 18420++ },++ "tps": {++ "p50": 86,++ "p90": 121,++ "p95": 133,++ "n": 12990++ },++ "tokens": {++ "input": 210000000,++ "output": 9100000,++ "reasoning": 0,++ "cache_read": 132000000,++ "cache_write": 0++ },++ "cost": {++ "charged_usd": 61.2,++ "list_usd": 74.9,++ "cache_saved_usd": 19.8,++ "per_call_usd": 0.0033,++ "per_million_output_usd": 6.72++ },++ "tasks": {++ "count": 4120,++ "cost_per_task_usd": {++ "p50": 0.006,++ "p90": 0.031,++ "p95": 0.05,++ "n": 4120++ },++ "time_per_task_ms": {++ "p50": 14000,++ "p90": 61000,++ "p95": 98000,++ "n": 4120++ }++ },++ "top_errors": [++ {++ "error_class": "rate_limited",++ "count": 71++ },++ {++ "error_class": "timeout",++ "count": 30++ }++ ]++}@@@ -17336,14 +17336,14 @@}},"ai.call.recorded": {-- "version": "1.0.0",++ "version": "1.1.0","owner": "ai","status": "active","schema": {"$schema": "https://json-schema.org/draft/2020-12/schema","$id": "https://openvibe.network/contracts/events/payloads/ai.call.recorded.v1.json","title": "AiCallRecordedPayload",-- "description": "ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai.",++ "description": "ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai. Since 1.1.0 (ai-metrics.md): OPERATION, STREAMED, TPS, QUEUE_MS, TASK, TASK_ID, TASK_MS, HARNESS, PLACE, ERROR_CLASS, FALLBACKS, CACHE_HIT, TOOL_CALLS and REGION, all optional. Products other than AI send their calls to POST /api/v1/usage/calls (ai.call-report@1); AI prices and publishes them.","type": "object","required": ["system",@@@ -17560,6 +17560,854 @@"at": {"type": "string","format": "date-time"++ },++ "operation": {++ "enum": [++ "chat",++ "completion",++ "embedding",++ "image",++ "image_edit",++ "speech",++ "transcription",++ "translation",++ "rerank",++ "moderation",++ "decision",++ "realtime",++ "batch",++ "tool",++ "other",++ null++ ],++ "description": "Since 1.1.0: what kind of call it was."++ },++ "streamed": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."++ },++ "tps": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."++ },++ "queue_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."++ },++ "task": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."++ },++ "task_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."++ },++ "task_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."++ },++ "harness": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."++ },++ "place": {++ "enum": [++ "provider",++ "machine",++ "community",++ "plan",++ "host",++ null++ ],++ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."++ },++ "error_class": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."++ },++ "fallbacks": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "maximum": 50,++ "description": "Since 1.1.0: how many offers failed before the one that answered."++ },++ "cache_hit": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."++ },++ "tool_calls": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: tool calls the model asked for in this call."++ },++ "region": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 40,++ "description": "Since 1.1.0: the provider region or data centre, when known."++ }++ }++ }++ },++ "ai.call-report": {++ "version": "1.0.0",++ "owner": "ai",++ "status": "active",++ "schema": {++ "$schema": "https://json-schema.org/draft/2020-12/schema",++ "$id": "https://openvibe.network/contracts/ai/call-report.v1.json",++ "title": "AiCallReport",++ "description": "ai.call-report@1 (ai-metrics.md): up to 100 AI calls a product made without OpenVibe.AI (Actor’s own model calls, a Codes harness turn, a local model on a person’s machine through Bot, Vibe), sent to AI’s POST /api/v1/usage/calls with the capability ai.usage.report. Each call is ai.call.recorded@1’s shape; the price is optional (AI prices from its rate cards: the charged amount first, then the list price) and SYSTEM + RUN_ID or TURN_ID is the idempotency key (a call sent twice is recorded once). AI publishes each as ai.call.recorded@1.",++ "type": "object",++ "additionalProperties": false,++ "required": [++ "calls"++ ],++ "properties": {++ "calls": {++ "type": "array",++ "minItems": 1,++ "maxItems": 100,++ "items": {++ "type": "object",++ "required": [++ "system",++ "provider",++ "model",++ "outcome",++ "at"++ ],++ "additionalProperties": false,++ "properties": {++ "subject": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 128,++ "description": "The person the call was made for, or null when the call was anonymous."++ },++ "attribution": {++ "type": "string",++ "maxLength": 200,++ "description": "The site or app the call came from, as '<type>:<id>' (for example 'site:design'), empty when nothing is known."++ },++ "surface": {++ "type": "string",++ "maxLength": 200,++ "description": "The product surface: 'design.generate', 'codes.turn', 'ai.generate'. Free text, so a new surface needs no new contract."++ },++ "system": {++ "type": "string",++ "maxLength": 100,++ "description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."++ },++ "provider": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 128++ },++ "model": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 200++ },++ "effort": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 64,++ "description": "The reasoning effort the call asked for, when it asked for one."++ },++ "paid_by": {++ "type": "string",++ "enum": [++ "own_key",++ "openvibe_key",++ "plan",++ "own_machine",++ "free_tier",++ "network_allowance",++ "org_key"++ ]++ },++ "paid_by_detail": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 200,++ "description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."++ },++ "input": {++ "type": "integer",++ "minimum": 0,++ "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields."++ },++ "output": {++ "type": "integer",++ "minimum": 0++ },++ "reasoning": {++ "type": "integer",++ "minimum": 0++ },++ "cache_read": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write_ttl": {++ "type": [++ "string",++ "null"++ ],++ "enum": [++ "5m",++ "1h",++ null++ ],++ "description": "How long the written cache entry lives, when the provider says."++ },++ "images": {++ "type": "integer",++ "minimum": 0++ },++ "audio_seconds": {++ "type": "number",++ "minimum": 0++ },++ "video_seconds": {++ "type": "number",++ "minimum": 0++ },++ "list_cost_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the tokens cost at the human-typed list prices. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "charged_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the payer was actually charged. A person's own key is never charged here: 0. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "fee_usd": {++ "type": "number",++ "minimum": 0,++ "description": "The network's fee on top of the cost, when the OpenVibe key paid. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "cache_saved_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the cached tokens saved against the plain input price. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "price_source": {++ "type": "string",++ "maxLength": 64,++ "description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price). Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "price_date": {++ "type": [++ "string",++ "null"++ ],++ "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",++ "description": "The day the price was checked, when it was. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "latency_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0++ },++ "ttft_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Time to the first token, when the call streamed and it was measured."++ },++ "attempts": {++ "type": "integer",++ "minimum": 0++ },++ "outcome": {++ "type": "string",++ "enum": [++ "succeeded",++ "failed",++ "cancelled",++ "cached"++ ]++ },++ "run_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 100++ },++ "turn_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 100++ },++ "at": {++ "type": "string",++ "format": "date-time"++ },++ "operation": {++ "enum": [++ "chat",++ "completion",++ "embedding",++ "image",++ "image_edit",++ "speech",++ "transcription",++ "translation",++ "rerank",++ "moderation",++ "decision",++ "realtime",++ "batch",++ "tool",++ "other",++ null++ ],++ "description": "Since 1.1.0: what kind of call it was."++ },++ "streamed": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."++ },++ "tps": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."++ },++ "queue_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."++ },++ "task": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."++ },++ "task_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."++ },++ "task_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."++ },++ "harness": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."++ },++ "place": {++ "enum": [++ "provider",++ "machine",++ "community",++ "plan",++ "host",++ null++ ],++ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."++ },++ "error_class": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."++ },++ "fallbacks": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "maximum": 50,++ "description": "Since 1.1.0: how many offers failed before the one that answered."++ },++ "cache_hit": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."++ },++ "tool_calls": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: tool calls the model asked for in this call."++ },++ "region": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 40,++ "description": "Since 1.1.0: the provider region or data centre, when known."++ }++ },++ "anyOf": [++ {++ "required": [++ "run_id"++ ]++ },++ {++ "required": [++ "turn_id"++ ]++ }++ ]++ }++ }++ }++ }++ },++ "report.ai-performance": {++ "version": "1.0.0",++ "owner": "report",++ "status": "active",++ "schema": {++ "$schema": "https://json-schema.org/draft/2020-12/schema",++ "$id": "https://openvibe.network/contracts/report/ai-performance.v1.json",++ "title": "ReportAiPerformance",++ "description": "report.ai-performance@1 (ai-metrics.md): how AI calls performed over a range, for one group (a model, a provider, an operation, a system, a task). Percentiles come from log-scale histograms (within one bucket’s width). Public answers group by model, provider or operation only and show a group with at least 20 calls; system and task groups are for staff. Money is USD; tokens per second is the decode speed after the first token; cost per task sums the calls that share a task id.",++ "type": "object",++ "additionalProperties": false,++ "required": [++ "group",++ "key",++ "calls"++ ],++ "properties": {++ "group": {++ "enum": [++ "model",++ "provider",++ "operation",++ "system",++ "task",++ "place",++ "harness"++ ]++ },++ "key": {++ "type": "string",++ "maxLength": 200++ },++ "provider": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120++ },++ "range": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "from": {++ "type": "string",++ "format": "date"++ },++ "to": {++ "type": "string",++ "format": "date"++ }++ }++ },++ "calls": {++ "type": "integer",++ "minimum": 0++ },++ "succeeded": {++ "type": "integer",++ "minimum": 0++ },++ "errors": {++ "type": "integer",++ "minimum": 0++ },++ "success_rate": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1++ },++ "fallback_rate": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1++ },++ "streamed_share": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1++ },++ "cache_hit_rate": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1++ },++ "cache_read_share": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "maximum": 1,++ "description": "Cache-read tokens as a share of all input tokens."++ },++ "ttft_ms": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "latency_ms": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "tps": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "tokens": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "input": {++ "type": "integer",++ "minimum": 0++ },++ "output": {++ "type": "integer",++ "minimum": 0++ },++ "reasoning": {++ "type": "integer",++ "minimum": 0++ },++ "cache_read": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "cost": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "charged_usd": {++ "type": "number",++ "minimum": 0++ },++ "list_usd": {++ "type": "number",++ "minimum": 0++ },++ "cache_saved_usd": {++ "type": "number",++ "minimum": 0++ },++ "per_call_usd": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "per_million_output_usd": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ }++ }++ },++ "tasks": {++ "type": [++ "object",++ "null"++ ],++ "additionalProperties": false,++ "properties": {++ "count": {++ "type": "integer",++ "minimum": 0++ },++ "cost_per_task_usd": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ },++ "time_per_task_ms": {++ "type": "object",++ "additionalProperties": false,++ "properties": {++ "p50": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p90": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "p95": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0++ },++ "n": {++ "type": "integer",++ "minimum": 0++ }++ }++ }++ }++ },++ "top_errors": {++ "type": "array",++ "maxItems": 5,++ "items": {++ "type": "object",++ "additionalProperties": false,++ "required": [++ "error_class",++ "count"++ ],++ "properties": {++ "error_class": {++ "type": "string",++ "maxLength": 60++ },++ "count": {++ "type": "integer",++ "minimum": 0++ }++ }++ }}}}@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Actor API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Actor as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Actor as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.AI API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.AI as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.AI as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -4088,6 +4088,55 @@}}},++ "/api/v1/usage/calls": {++ "post": {++ "operationId": "post_api_v1_usage_calls",++ "summary": "Report AI calls a product made without OpenVibe.AI (ai.call-report@1): AI prices any that bring no price, records each once and publishes ai.call.recorded@1, so every AI call on the network is in one ",++ "description": "**ai.usage.report** (internal): Report AI calls a product made without OpenVibe.AI (ai.call-report@1): AI prices any that bring no price, records each once and publishes ai.call.recorded@1, so every AI call on the network is in one meter.",++ "tags": [++ "ai.usage"++ ],++ "x-openvibe-capabilities": [++ "ai.usage.report"++ ],++ "x-openvibe-visibility": [++ "internal"++ ],++ "x-openvibe-quota-class": "ai-read",++ "security": [++ {++ "openvibeToken": [++ "ai.usage.report"++ ]++ }++ ],++ "requestBody": {++ "required": false,++ "content": {++ "application/json": {++ "schema": {++ "$ref": "#/components/schemas/ai.call-report.v1"++ }++ }++ }++ },++ "responses": {++ "2XX": {++ "description": "Success"++ },++ "default": {++ "description": "An error (RFC 9457 problem details)",++ "content": {++ "application/problem+json": {++ "schema": {++ "$ref": "#/components/schemas/errors.problem.v1"++ }++ }++ }++ }++ }++ }++ },"/api/v1/workflows/{key}/versions": {"post": {"operationId": "post_api_v1_workflows_key_versions",@@@ -5486,6 +5535,363 @@}}},++ "ai.call-report.v1": {++ "title": "AiCallReport",++ "description": "ai.call-report@1 (ai-metrics.md): up to 100 AI calls a product made without OpenVibe.AI (Actor’s own model calls, a Codes harness turn, a local model on a person’s machine through Bot, Vibe), sent to AI’s POST /api/v1/usage/calls with the capability ai.usage.report. Each call is ai.call.recorded@1’s shape; the price is optional (AI prices from its rate cards: the charged amount first, then the list price) and SYSTEM + RUN_ID or TURN_ID is the idempotency key (a call sent twice is recorded once). AI publishes each as ai.call.recorded@1.",++ "type": "object",++ "additionalProperties": false,++ "required": [++ "calls"++ ],++ "properties": {++ "calls": {++ "type": "array",++ "minItems": 1,++ "maxItems": 100,++ "items": {++ "type": "object",++ "required": [++ "system",++ "provider",++ "model",++ "outcome",++ "at"++ ],++ "additionalProperties": false,++ "properties": {++ "subject": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 128,++ "description": "The person the call was made for, or null when the call was anonymous."++ },++ "attribution": {++ "type": "string",++ "maxLength": 200,++ "description": "The site or app the call came from, as '<type>:<id>' (for example 'site:design'), empty when nothing is known."++ },++ "surface": {++ "type": "string",++ "maxLength": 200,++ "description": "The product surface: 'design.generate', 'codes.turn', 'ai.generate'. Free text, so a new surface needs no new contract."++ },++ "system": {++ "type": "string",++ "maxLength": 100,++ "description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."++ },++ "provider": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 128++ },++ "model": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 200++ },++ "effort": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 64,++ "description": "The reasoning effort the call asked for, when it asked for one."++ },++ "paid_by": {++ "type": "string",++ "enum": [++ "own_key",++ "openvibe_key",++ "plan",++ "own_machine",++ "free_tier",++ "network_allowance",++ "org_key"++ ]++ },++ "paid_by_detail": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 200,++ "description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."++ },++ "input": {++ "type": "integer",++ "minimum": 0,++ "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields."++ },++ "output": {++ "type": "integer",++ "minimum": 0++ },++ "reasoning": {++ "type": "integer",++ "minimum": 0++ },++ "cache_read": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write": {++ "type": "integer",++ "minimum": 0++ },++ "cache_write_ttl": {++ "type": [++ "string",++ "null"++ ],++ "enum": [++ "5m",++ "1h",++ null++ ],++ "description": "How long the written cache entry lives, when the provider says."++ },++ "images": {++ "type": "integer",++ "minimum": 0++ },++ "audio_seconds": {++ "type": "number",++ "minimum": 0++ },++ "video_seconds": {++ "type": "number",++ "minimum": 0++ },++ "list_cost_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the tokens cost at the human-typed list prices. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "charged_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the payer was actually charged. A person's own key is never charged here: 0. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "fee_usd": {++ "type": "number",++ "minimum": 0,++ "description": "The network's fee on top of the cost, when the OpenVibe key paid. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "cache_saved_usd": {++ "type": "number",++ "minimum": 0,++ "description": "What the cached tokens saved against the plain input price. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "price_source": {++ "type": "string",++ "maxLength": 64,++ "description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price). Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "price_date": {++ "type": [++ "string",++ "null"++ ],++ "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",++ "description": "The day the price was checked, when it was. Optional here: AI prices a call that brings no price from its own rate cards."++ },++ "latency_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0++ },++ "ttft_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Time to the first token, when the call streamed and it was measured."++ },++ "attempts": {++ "type": "integer",++ "minimum": 0++ },++ "outcome": {++ "type": "string",++ "enum": [++ "succeeded",++ "failed",++ "cancelled",++ "cached"++ ]++ },++ "run_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 100++ },++ "turn_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 100++ },++ "at": {++ "type": "string",++ "format": "date-time"++ },++ "operation": {++ "enum": [++ "chat",++ "completion",++ "embedding",++ "image",++ "image_edit",++ "speech",++ "transcription",++ "translation",++ "rerank",++ "moderation",++ "decision",++ "realtime",++ "batch",++ "tool",++ "other",++ null++ ],++ "description": "Since 1.1.0: what kind of call it was."++ },++ "streamed": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."++ },++ "tps": {++ "type": [++ "number",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."++ },++ "queue_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."++ },++ "task": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."++ },++ "task_id": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 120,++ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."++ },++ "task_ms": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."++ },++ "harness": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."++ },++ "place": {++ "enum": [++ "provider",++ "machine",++ "community",++ "plan",++ "host",++ null++ ],++ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."++ },++ "error_class": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 60,++ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."++ },++ "fallbacks": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "maximum": 50,++ "description": "Since 1.1.0: how many offers failed before the one that answered."++ },++ "cache_hit": {++ "type": [++ "boolean",++ "null"++ ],++ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."++ },++ "tool_calls": {++ "type": [++ "integer",++ "null"++ ],++ "minimum": 0,++ "description": "Since 1.1.0: tool calls the model asked for in this call."++ },++ "region": {++ "type": [++ "string",++ "null"++ ],++ "maxLength": 40,++ "description": "Since 1.1.0: the provider region or data centre, when known."++ }++ },++ "anyOf": [++ {++ "required": [++ "run_id"++ ]++ },++ {++ "required": [++ "turn_id"++ ]++ }++ ]++ }++ }++ }++ },"ai.choice.v1": {"title": "AiChoiceV1","description": "One model and where it comes from, for a task or a run: OpenVibe's supply (openvibe), the person's own provider key (keys), or one of their own computers through OpenVibe Link (machines). A machine choice names the machine; the other sources never do. Used by ai.run-request@1, ai.task@1 and ai.task-defaults@1.",@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Bench API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Bench as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Bench as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Billing API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Billing as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Billing as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Blog API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Blog as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Blog as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Bot API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Bot as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Bot as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Chat API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Chat as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Chat as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Codes API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Codes as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Codes as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Community API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Community as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Community as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe Connect API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe Connect as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe Connect as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Coupons API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Coupons as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Coupons as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Deals API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Deals as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Deals as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Design API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Design as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Design as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Domains API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Domains as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Domains as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Events API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Events as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Events as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Exchange API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Exchange as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Exchange as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Food API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Food as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Food as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Games API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Games as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Games as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Git API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Git as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Git as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Host API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Host as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Host as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -12,8 +12,8 @@"service": "ai","name": "OpenVibe.AI","origin": "https://ai.openvibe.services",-- "operations": 72,-- "capabilities": 19++ "operations": 73,++ "capabilities": 20},{"service": "bench",@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Inventory API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Inventory as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Inventory as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Live API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Live as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Live as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Mail API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Mail as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Mail as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.MediaHub API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.MediaHub as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.MediaHub as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Media API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Media as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Media as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Network API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Network as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Network as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.News API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.News as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.News as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenRestream API",-- "version": "0.420.0",-- "description": "Routes of OpenRestream as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenRestream as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Play API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Play as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Play as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Quest API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Quest as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Quest as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Report API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Report as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Report as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Reviews API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Reviews as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Reviews as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Run API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Run as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Run as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Search API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Search as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Search as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Services API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Services as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Services as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Sources API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Sources as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Sources as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Space API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Space as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Space as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Tips API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Tips as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Tips as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Today API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Today as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Today as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Tools API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Tools as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Tools as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Trade API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Trade as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Trade as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.VIP API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.VIP as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.VIP as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Vision API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Vision as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Vision as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Watch API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Watch as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Watch as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Wiki API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Wiki as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Wiki as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Work API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Work as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Work as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -3,8 +3,8 @@"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema","info": {"title": "OpenVibe.Zone API",-- "version": "0.420.0",-- "description": "Routes of OpenVibe.Zone as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",++ "version": "0.421.0",++ "description": "Routes of OpenVibe.Zone as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.","license": {"name": "MIT","identifier": "MIT"@@@ -162831,9 +162831,9 @@ export interface AiRunError {retry_at?: string | null;}--/** [email protected] (owner: ai) */++/** [email protected] (owner: ai) *//**-- * ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai.++ * ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai. Since 1.1.0 (ai-metrics.md): OPERATION, STREAMED, TPS, QUEUE_MS, TASK, TASK_ID, TASK_MS, HARNESS, PLACE, ERROR_CLASS, FALLBACKS, CACHE_HIT, TOOL_CALLS and REGION, all optional. Products other than AI send their calls to POST /api/v1/usage/calls (ai.call-report@1); AI prices and publishes them.*/export interface AiCallRecordedPayload {/**@@@ -162912,6 +162912,254 @@ export interface AiCallRecordedPayload {run_id?: string | null;turn_id?: string | null;at: string;++ /**++ * Since 1.1.0: what kind of call it was.++ */++ operation?:++ | "chat"++ | "completion"++ | "embedding"++ | "image"++ | "image_edit"++ | "speech"++ | "transcription"++ | "translation"++ | "rerank"++ | "moderation"++ | "decision"++ | "realtime"++ | "batch"++ | "tool"++ | "other"++ | null;++ /**++ * Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one).++ */++ streamed?: boolean | null;++ /**++ * Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure.++ */++ tps?: number | null;++ /**++ * Since 1.1.0: time waiting before the call was sent (a queue, a rate gate).++ */++ queue_ms?: number | null;++ /**++ * Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn).++ */++ task?: string | null;++ /**++ * Since 1.1.0: the task or run this call is one step of, so cost and time add up per task.++ */++ task_id?: string | null;++ /**++ * Since 1.1.0: on the last call of a task, the whole task’s wall time.++ */++ task_ms?: number | null;++ /**++ * Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …).++ */++ harness?: string | null;++ /**++ * Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts.++ */++ place?: "provider" | "machine" | "community" | "plan" | "host" | null;++ /**++ * Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid).++ */++ error_class?: string | null;++ /**++ * Since 1.1.0: how many offers failed before the one that answered.++ */++ fallbacks?: number | null;++ /**++ * Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran).++ */++ cache_hit?: boolean | null;++ /**++ * Since 1.1.0: tool calls the model asked for in this call.++ */++ tool_calls?: number | null;++ /**++ * Since 1.1.0: the provider region or data centre, when known.++ */++ region?: string | null;++}++++/** [email protected] (owner: ai) */++/**++ * ai.call-report@1 (ai-metrics.md): up to 100 AI calls a product made without OpenVibe.AI (Actor’s own model calls, a Codes harness turn, a local model on a person’s machine through Bot, Vibe), sent to AI’s POST /api/v1/usage/calls with the capability ai.usage.report. Each call is ai.call.recorded@1’s shape; the price is optional (AI prices from its rate cards: the charged amount first, then the list price) and SYSTEM + RUN_ID or TURN_ID is the idempotency key (a call sent twice is recorded once). AI publishes each as ai.call.recorded@1.++ */++export interface AiCallReport {++ /**++ * @minItems 1++ * @maxItems 100++ */++ calls: [++ (++ | {++ [k: string]: unknown | undefined;++ }++ | {++ [k: string]: unknown | undefined;++ }++ ),++ ...(++ | {++ [k: string]: unknown | undefined;++ }++ | {++ [k: string]: unknown | undefined;++ }++ )[]++ ];++}++++/** [email protected] (owner: report) */++/**++ * report.ai-performance@1 (ai-metrics.md): how AI calls performed over a range, for one group (a model, a provider, an operation, a system, a task). Percentiles come from log-scale histograms (within one bucket’s width). Public answers group by model, provider or operation only and show a group with at least 20 calls; system and task groups are for staff. Money is USD; tokens per second is the decode speed after the first token; cost per task sums the calls that share a task id.++ */++export interface ReportAiPerformance {++ group: "model" | "provider" | "operation" | "system" | "task" | "place" | "harness";++ key: string;++ provider?: string | null;++ range?: {++ from?: string;++ to?: string;++ };++ calls: number;++ succeeded?: number;++ errors?: number;++ success_rate?: number | null;++ fallback_rate?: number | null;++ streamed_share?: number | null;++ cache_hit_rate?: number | null;++ /**++ * Cache-read tokens as a share of all input tokens.++ */++ cache_read_share?: number | null;++ ttft_ms?: {++ p50?: number | null;++ p90?: number | null;++ p95?: number | null;++ n?: number;++ };++ latency_ms?: {++ p50?: number | null;++ p90?: number | null;++ p95?: number | null;++ n?: number;++ };++ tps?: {++ p50?: number | null;++ p90?: number | null;++ p95?: number | null;++ n?: number;++ };++ tokens?: {++ input?: number;++ output?: number;++ reasoning?: number;++ cache_read?: number;++ cache_write?: number;++ };++ cost?: {++ charged_usd?: number;++ list_usd?: number;++ cache_saved_usd?: number;++ per_call_usd?: number | null;++ per_million_output_usd?: number | null;++ };++ tasks?: {++ count?: number;++ cost_per_task_usd?: {++ p50?: number | null;++ p90?: number | null;++ p95?: number | null;++ n?: number;++ };++ time_per_task_ms?: {++ p50?: number | null;++ p90?: number | null;++ p95?: number | null;++ n?: number;++ };++ } | null;++ /**++ * @maxItems 5++ */++ top_errors?:++ | []++ | [++ {++ error_class: string;++ count: number;++ }++ ]++ | [++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ }++ ]++ | [++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ }++ ]++ | [++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ }++ ]++ | [++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ },++ {++ error_class: string;++ count: number;++ }++ ];}/** [email protected] (owner: ai) */nnew file mode 100644@@@ -0,0 +1,23 @@++{++ "id": "ai.usage.report",++ "version": "1.0",++ "owner": "ai",++ "status": "active",++ "visibility": "internal",++ "description": "Report AI calls a product made without OpenVibe.AI (ai.call-report@1): AI prices any that bring no price, records each once and publishes ai.call.recorded@1, so every AI call on the network is in one meter.",++ "permissions": [++ "ai:usage:report"++ ],++ "resourceConstraints": [++ "none"++ ],++ "quotaClass": "ai-read",++ "events": [++ "ai.call.recorded"++ ],++ "implementedBy": [++ "POST /api/v1/usage/calls"++ ],++ "inputSchema": "ai.call-report@1",++ "outputSchema": "common.no-body@1"++}@@@ -20,24 +20,25 @@"note": "the public API (OpenAI-compatible /v1 and the six operations); its human pages moved to OpenVibe.Exchange on 2026-11-07 and answer 301 there. A run receipt (/runs/:id) and the operator console stay for the person signed in"},"capabilities": [++ "ai.actions.read","ai.app.run",++ "ai.batches.create",++ "ai.batches.read",++ "ai.config.manage","ai.credential.manage",++ "ai.layout.suggest",++ "ai.me.manage",++ "ai.me.read",++ "ai.memory.read",++ "ai.memory.write","ai.model.read","ai.provider.manage","ai.quota.attribution.manage",-- "ai.batches.create",-- "ai.batches.read","ai.run.create","ai.run.read","ai.usage.read",++ "ai.usage.report","ai.workflow.manage",-- "ai.actions.read",-- "ai.memory.read",-- "ai.memory.write",-- "ai.me.read",-- "ai.me.manage",-- "ai.layout.suggest",-- "ai.config.manage","exchange.search.icons"],"eventsProduced": [@@@ -90,14 +91,14 @@],"window": "automatic only while ovhost waits for readiness after the restart (30 s in host.example.json); manual afterwards, as long as no blocker applies","blockers": {-- "none": "the schema code only adds (CREATE \u2026 IF NOT EXISTS, ADD COLUMN; no DROP, RENAME or table rebuild), which an older release ignores"++ "none": "the schema code only adds (CREATE … IF NOT EXISTS, ADD COLUMN; no DROP, RENAME or table rebuild), which an older release ignores"}},"contracts": {"range": ">=0.6.0 <1.0.0"},"leases": {-- "none": "no claims: one process owns its PostgreSQL database (ov_ai); a run is taken with a compare-and-set on its status (queued \u2192 running)"++ "none": "no claims: one process owns its PostgreSQL database (ov_ai); a run is taken with a compare-and-set on its status (queued → running)"}},"notes": "Providers, models, routing profiles, versioned prompt templates and workflows, runs, request logs, citations, scoped cache, quotas and audit. Workflow output is a draft/evidence package attributed to workflow + model + run. ai.run.queued|succeeded|failed|cached have payload contracts (v0.30.0, status planned): AI publishes them once its Events client is wired in; it publishes none today. ai.run.create takes ai.run-request@1 and returns ai.run@1. Produces ai.run@1 effort_requested, effort_applied, effort_rung and ladder receipts; consumes ai.effort@1 and ai.run-request@1 effort/ladder metadata. Actor consumes those receipts; AI does not authorize agent tickets.",@@@ -1,6 +1,6 @@{"name": "openvibe-contracts",-- "version": "0.420.0",++ "version": "0.421.0","description": "Machine-readable contracts for the OpenVibe network: schemas, manifests, ids, error envelope, capability checks.","main": "index.js","types": "generated/typescript/index.d.ts",
@@ -1,5 +1,31 @@
@@ -1,5 +1,31 @@
# Changelog
# Changelog
+## 0.421.0 — 2026-11-12
+
+**Every AI call, measured everywhere** (ai-metrics.md).
+
+- **`ai.call.recorded@1` 1.1.0** adds, all optional:
+ - `operation` (chat, completion, embedding, image, image edit, speech, transcription, translation, rerank,
+ moderation, decision, realtime, batch, tool);
+ - `streamed`, and `tps` (the decode speed after the first token);
+ - `queue_ms`;
+ - `task`, `task_id` and `task_ms`, so cost and time add up per task;
+ - `harness`, and `place` (provider, the person's machine, community, a plan, OpenVibe's hosts);
+ - `error_class`, `fallbacks` and `cache_hit` (an exact-cache answer);
+ - `tool_calls` and `region`.
+- **`ai.call-report@1`:** up to 100 calls a product made without OpenVibe.AI (Actor, Codes harness turns, Link's local
+ models through Bot, Vibe). They go to AI's `POST /api/v1/usage/calls`. AI prices any that bring no price, records
+ each once (by system + run or turn id) and publishes `ai.call.recorded@1`. The capability is `ai.usage.report`.
+- **`report.ai-performance@1`:** how calls performed for one group (model, provider, operation, system, task, place,
+ harness):
+ - success, fallback, streamed and cache-hit rates;
+ - TTFT, latency and tokens per second at p50, p90 and p95;
+ - tokens, charged and list cost, and cache savings;
+ - cost and time per task;
+ - the top errors.
+
+ Public answers group by model, provider or operation, with at least 20 calls.
+
## 0.420.0 — 2026-11-12
## 0.420.0 — 2026-11-12
**One agent system, measured.** These contracts carry the decisions in `one-system-v2.md`, which come from reading 24
**One agent system, measured.** These contracts carry the decisions in `one-system-v2.md`, which come from reading 24
new file mode 100644
new file mode 100644
@@ -0,0 +1,359 @@
@@ -0,0 +1,359 @@
+{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "$id": "https://openvibe.network/contracts/ai/call-report.v1.json",
+ "title": "AiCallReport",
+ "description": "ai.call-report@1 (ai-metrics.md): up to 100 AI calls a product made without OpenVibe.AI (Actor’s own model calls, a Codes harness turn, a local model on a person’s machine through Bot, Vibe), sent to AI’s POST /api/v1/usage/calls with the capability ai.usage.report. Each call is ai.call.recorded@1’s shape; the price is optional (AI prices from its rate cards: the charged amount first, then the list price) and SYSTEM + RUN_ID or TURN_ID is the idempotency key (a call sent twice is recorded once). AI publishes each as ai.call.recorded@1.",
+ "type": "object",
+ "additionalProperties": false,
+ "required": [
+ "calls"
+ ],
+ "properties": {
+ "calls": {
+ "type": "array",
+ "minItems": 1,
+ "maxItems": 100,
+ "items": {
+ "type": "object",
+ "required": [
+ "system",
+ "provider",
+ "model",
+ "outcome",
+ "at"
+ ],
+ "additionalProperties": false,
+ "properties": {
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 128,
+ "description": "The person the call was made for, or null when the call was anonymous."
+ },
+ "attribution": {
+ "type": "string",
+ "maxLength": 200,
+ "description": "The site or app the call came from, as '<type>:<id>' (for example 'site:design'), empty when nothing is known."
+ },
+ "surface": {
+ "type": "string",
+ "maxLength": 200,
+ "description": "The product surface: 'design.generate', 'codes.turn', 'ai.generate'. Free text, so a new surface needs no new contract."
+ },
+ "system": {
+ "type": "string",
+ "maxLength": 100,
+ "description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."
+ },
+ "provider": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 128
+ },
+ "model": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 200
+ },
+ "effort": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 64,
+ "description": "The reasoning effort the call asked for, when it asked for one."
+ },
+ "paid_by": {
+ "type": "string",
+ "enum": [
+ "own_key",
+ "openvibe_key",
+ "plan",
+ "own_machine",
+ "free_tier",
+ "network_allowance",
+ "org_key"
+ ]
+ },
+ "paid_by_detail": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 200,
+ "description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."
+ },
+ "input": {
+ "type": "integer",
+ "minimum": 0,
+ "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields."
+ },
+ "output": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "reasoning": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_read": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write_ttl": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "enum": [
+ "5m",
+ "1h",
+ null
+ ],
+ "description": "How long the written cache entry lives, when the provider says."
+ },
+ "images": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "audio_seconds": {
+ "type": "number",
+ "minimum": 0
+ },
+ "video_seconds": {
+ "type": "number",
+ "minimum": 0
+ },
+ "list_cost_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the tokens cost at the human-typed list prices. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "charged_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the payer was actually charged. A person's own key is never charged here: 0. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "fee_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "The network's fee on top of the cost, when the OpenVibe key paid. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "cache_saved_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the cached tokens saved against the plain input price. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "price_source": {
+ "type": "string",
+ "maxLength": 64,
+ "description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price). Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "price_date": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",
+ "description": "The day the price was checked, when it was. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "latency_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "ttft_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Time to the first token, when the call streamed and it was measured."
+ },
+ "attempts": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "outcome": {
+ "type": "string",
+ "enum": [
+ "succeeded",
+ "failed",
+ "cancelled",
+ "cached"
+ ]
+ },
+ "run_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 100
+ },
+ "turn_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 100
+ },
+ "at": {
+ "type": "string",
+ "format": "date-time"
+ },
+ "operation": {
+ "enum": [
+ "chat",
+ "completion",
+ "embedding",
+ "image",
+ "image_edit",
+ "speech",
+ "transcription",
+ "translation",
+ "rerank",
+ "moderation",
+ "decision",
+ "realtime",
+ "batch",
+ "tool",
+ "other",
+ null
+ ],
+ "description": "Since 1.1.0: what kind of call it was."
+ },
+ "streamed": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."
+ },
+ "tps": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."
+ },
+ "queue_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."
+ },
+ "task": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."
+ },
+ "task_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."
+ },
+ "task_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."
+ },
+ "harness": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."
+ },
+ "place": {
+ "enum": [
+ "provider",
+ "machine",
+ "community",
+ "plan",
+ "host",
+ null
+ ],
+ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."
+ },
+ "error_class": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."
+ },
+ "fallbacks": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 50,
+ "description": "Since 1.1.0: how many offers failed before the one that answered."
+ },
+ "cache_hit": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."
+ },
+ "tool_calls": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: tool calls the model asked for in this call."
+ },
+ "region": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 40,
+ "description": "Since 1.1.0: the provider region or data centre, when known."
+ }
+ },
+ "anyOf": [
+ {
+ "required": [
+ "run_id"
+ ]
+ },
+ {
+ "required": [
+ "turn_id"
+ ]
+ }
+ ]
+ }
+ }
+ }
+}
@@ -1643,7 +1643,7 @@
@@ -1643,7 +1643,7 @@
},
},
{
{
"id": "ai.call.recorded",
"id": "ai.call.recorded",
- "version": "1.0.0",
+ "version": "1.1.0",
"owner": "ai",
"owner": "ai",
"schema": "events/payloads/ai.call.recorded.v1.json",
"schema": "events/payloads/ai.call.recorded.v1.json",
"visibility": "first-party",
"visibility": "first-party",
@@ -1651,6 +1651,24 @@
@@ -1651,6 +1651,24 @@
"status": "active",
"status": "active",
"adr": "ADR-033"
"adr": "ADR-033"
},
},
+ {
+ "id": "ai.call-report",
+ "version": "1.0.0",
+ "owner": "ai",
+ "schema": "ai/call-report.v1.json",
+ "visibility": "internal",
+ "compatibility": "backward",
+ "status": "active"
+ },
+ {
+ "id": "report.ai-performance",
+ "version": "1.0.0",
+ "owner": "report",
+ "schema": "report/ai-performance.v1.json",
+ "visibility": "internal",
+ "compatibility": "backward",
+ "status": "active"
+ },
{
{
"id": "ai.run.queued",
"id": "ai.run.queued",
"version": "1.0.0",
"version": "1.0.0",
@@ -2,7 +2,7 @@
@@ -2,7 +2,7 @@
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://openvibe.network/contracts/events/payloads/ai.call.recorded.v1.json",
"$id": "https://openvibe.network/contracts/events/payloads/ai.call.recorded.v1.json",
"title": "AiCallRecordedPayload",
"title": "AiCallRecordedPayload",
- "description": "ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai.",
+ "description": "ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai. Since 1.1.0 (ai-metrics.md): OPERATION, STREAMED, TPS, QUEUE_MS, TASK, TASK_ID, TASK_MS, HARNESS, PLACE, ERROR_CLASS, FALLBACKS, CACHE_HIT, TOOL_CALLS and REGION, all optional. Products other than AI send their calls to POST /api/v1/usage/calls (ai.call-report@1); AI prices and publishes them.",
"type": "object",
"type": "object",
"required": [
"required": [
"system",
"system",
@@ -32,7 +32,10 @@
@@ -32,7 +32,10 @@
"additionalProperties": false,
"additionalProperties": false,
"properties": {
"properties": {
"subject": {
"subject": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"maxLength": 128,
"maxLength": 128,
"description": "The person the call was made for, or null when the call was anonymous."
"description": "The person the call was made for, or null when the call was anonymous."
},
},
@@ -51,50 +54,298 @@
@@ -51,50 +54,298 @@
"maxLength": 100,
"maxLength": 100,
"description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."
"description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."
},
},
- "provider": { "type": ["string", "null"], "maxLength": 128 },
- "model": { "type": ["string", "null"], "maxLength": 200 },
- "effort": { "type": ["string", "null"], "maxLength": 64, "description": "The reasoning effort the call asked for, when it asked for one." },
+ "provider": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 128
+ },
+ "model": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 200
+ },
+ "effort": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 64,
+ "description": "The reasoning effort the call asked for, when it asked for one."
+ },
"paid_by": {
"paid_by": {
"type": "string",
"type": "string",
- "enum": ["own_key", "openvibe_key", "plan", "own_machine", "free_tier", "network_allowance", "org_key"]
+ "enum": [
+ "own_key",
+ "openvibe_key",
+ "plan",
+ "own_machine",
+ "free_tier",
+ "network_allowance",
+ "org_key"
+ ]
},
},
"paid_by_detail": {
"paid_by_detail": {
- "type": ["string", "null"],
+ "type": [
+ "string",
+ "null"
+ ],
"maxLength": 200,
"maxLength": 200,
"description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."
"description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."
},
},
- "input": { "type": "integer", "minimum": 0, "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields." },
- "output": { "type": "integer", "minimum": 0 },
- "reasoning": { "type": "integer", "minimum": 0 },
- "cache_read": { "type": "integer", "minimum": 0 },
- "cache_write": { "type": "integer", "minimum": 0 },
+ "input": {
+ "type": "integer",
+ "minimum": 0,
+ "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields."
+ },
+ "output": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "reasoning": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_read": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write": {
+ "type": "integer",
+ "minimum": 0
+ },
"cache_write_ttl": {
"cache_write_ttl": {
- "type": ["string", "null"],
- "enum": ["5m", "1h", null],
+ "type": [
+ "string",
+ "null"
+ ],
+ "enum": [
+ "5m",
+ "1h",
+ null
+ ],
"description": "How long the written cache entry lives, when the provider says."
"description": "How long the written cache entry lives, when the provider says."
},
},
- "images": { "type": "integer", "minimum": 0 },
- "audio_seconds": { "type": "number", "minimum": 0 },
- "video_seconds": { "type": "number", "minimum": 0 },
- "list_cost_usd": { "type": "number", "minimum": 0, "description": "What the tokens cost at the human-typed list prices." },
- "charged_usd": { "type": "number", "minimum": 0, "description": "What the payer was actually charged. A person's own key is never charged here: 0." },
- "fee_usd": { "type": "number", "minimum": 0, "description": "The network's fee on top of the cost, when the OpenVibe key paid." },
- "cache_saved_usd": { "type": "number", "minimum": 0, "description": "What the cached tokens saved against the plain input price." },
+ "images": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "audio_seconds": {
+ "type": "number",
+ "minimum": 0
+ },
+ "video_seconds": {
+ "type": "number",
+ "minimum": 0
+ },
+ "list_cost_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the tokens cost at the human-typed list prices."
+ },
+ "charged_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the payer was actually charged. A person's own key is never charged here: 0."
+ },
+ "fee_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "The network's fee on top of the cost, when the OpenVibe key paid."
+ },
+ "cache_saved_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the cached tokens saved against the plain input price."
+ },
"price_source": {
"price_source": {
"type": "string",
"type": "string",
"maxLength": 64,
"maxLength": 64,
"description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price)."
"description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price)."
},
},
- "price_date": { "type": ["string", "null"], "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$", "description": "The day the price was checked, when it was." },
- "latency_ms": { "type": ["integer", "null"], "minimum": 0 },
- "ttft_ms": { "type": ["integer", "null"], "minimum": 0, "description": "Time to the first token, when the call streamed and it was measured." },
- "attempts": { "type": "integer", "minimum": 0 },
+ "price_date": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",
+ "description": "The day the price was checked, when it was."
+ },
+ "latency_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "ttft_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Time to the first token, when the call streamed and it was measured."
+ },
+ "attempts": {
+ "type": "integer",
+ "minimum": 0
+ },
"outcome": {
"outcome": {
"type": "string",
"type": "string",
- "enum": ["succeeded", "failed", "cancelled", "cached"]
+ "enum": [
+ "succeeded",
+ "failed",
+ "cancelled",
+ "cached"
+ ]
+ },
+ "run_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 100
+ },
+ "turn_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 100
+ },
+ "at": {
+ "type": "string",
+ "format": "date-time"
+ },
+ "operation": {
+ "enum": [
+ "chat",
+ "completion",
+ "embedding",
+ "image",
+ "image_edit",
+ "speech",
+ "transcription",
+ "translation",
+ "rerank",
+ "moderation",
+ "decision",
+ "realtime",
+ "batch",
+ "tool",
+ "other",
+ null
+ ],
+ "description": "Since 1.1.0: what kind of call it was."
+ },
+ "streamed": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."
+ },
+ "tps": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."
+ },
+ "queue_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."
+ },
+ "task": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."
+ },
+ "task_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."
+ },
+ "task_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."
+ },
+ "harness": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."
+ },
+ "place": {
+ "enum": [
+ "provider",
+ "machine",
+ "community",
+ "plan",
+ "host",
+ null
+ ],
+ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."
+ },
+ "error_class": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."
+ },
+ "fallbacks": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 50,
+ "description": "Since 1.1.0: how many offers failed before the one that answered."
+ },
+ "cache_hit": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."
+ },
+ "tool_calls": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: tool calls the model asked for in this call."
},
},
- "run_id": { "type": ["string", "null"], "maxLength": 100 },
- "turn_id": { "type": ["string", "null"], "maxLength": 100 },
- "at": { "type": "string", "format": "date-time" }
+ "region": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 40,
+ "description": "Since 1.1.0: the provider region or data centre, when known."
+ }
}
}
}
}
new file mode 100644
new file mode 100644
@@ -0,0 +1,352 @@
@@ -0,0 +1,352 @@
+{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "$id": "https://openvibe.network/contracts/report/ai-performance.v1.json",
+ "title": "ReportAiPerformance",
+ "description": "report.ai-performance@1 (ai-metrics.md): how AI calls performed over a range, for one group (a model, a provider, an operation, a system, a task). Percentiles come from log-scale histograms (within one bucket’s width). Public answers group by model, provider or operation only and show a group with at least 20 calls; system and task groups are for staff. Money is USD; tokens per second is the decode speed after the first token; cost per task sums the calls that share a task id.",
+ "type": "object",
+ "additionalProperties": false,
+ "required": [
+ "group",
+ "key",
+ "calls"
+ ],
+ "properties": {
+ "group": {
+ "enum": [
+ "model",
+ "provider",
+ "operation",
+ "system",
+ "task",
+ "place",
+ "harness"
+ ]
+ },
+ "key": {
+ "type": "string",
+ "maxLength": 200
+ },
+ "provider": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120
+ },
+ "range": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "from": {
+ "type": "string",
+ "format": "date"
+ },
+ "to": {
+ "type": "string",
+ "format": "date"
+ }
+ }
+ },
+ "calls": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "succeeded": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "errors": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "success_rate": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1
+ },
+ "fallback_rate": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1
+ },
+ "streamed_share": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1
+ },
+ "cache_hit_rate": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1
+ },
+ "cache_read_share": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1,
+ "description": "Cache-read tokens as a share of all input tokens."
+ },
+ "ttft_ms": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "latency_ms": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "tps": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "tokens": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "input": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "output": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "reasoning": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_read": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "cost": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "charged_usd": {
+ "type": "number",
+ "minimum": 0
+ },
+ "list_usd": {
+ "type": "number",
+ "minimum": 0
+ },
+ "cache_saved_usd": {
+ "type": "number",
+ "minimum": 0
+ },
+ "per_call_usd": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "per_million_output_usd": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ }
+ }
+ },
+ "tasks": {
+ "type": [
+ "object",
+ "null"
+ ],
+ "additionalProperties": false,
+ "properties": {
+ "count": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cost_per_task_usd": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "time_per_task_ms": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ }
+ }
+ },
+ "top_errors": {
+ "type": "array",
+ "maxItems": 5,
+ "items": {
+ "type": "object",
+ "additionalProperties": false,
+ "required": [
+ "error_class",
+ "count"
+ ],
+ "properties": {
+ "error_class": {
+ "type": "string",
+ "maxLength": 60
+ },
+ "count": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ }
+ }
+ }
+}
new file mode 100644
new file mode 100644
@@ -0,0 +1,13 @@
@@ -0,0 +1,13 @@
+{
+ "calls": [
+ {
+ "system": "actor",
+ "run_id": "r1",
+ "provider": "deepseek",
+ "model": "x",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z",
+ "operation": "telepathy"
+ }
+ ]
+}
new file mode 100644
new file mode 100644
@@ -0,0 +1,11 @@
@@ -0,0 +1,11 @@
+{
+ "calls": [
+ {
+ "system": "actor",
+ "provider": "deepseek",
+ "model": "x",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ }
+ ]
+}
new file mode 100644
new file mode 100644
@@ -0,0 +1,812 @@
@@ -0,0 +1,812 @@
+{
+ "calls": [
+ {
+ "system": "actor",
+ "run_id": "r0",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r1",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r2",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r3",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r4",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r5",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r6",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r7",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r8",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r9",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r10",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r11",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r12",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r13",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r14",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r15",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r16",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r17",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r18",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r19",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r20",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r21",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r22",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r23",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r24",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r25",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r26",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r27",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r28",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r29",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r30",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r31",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r32",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r33",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r34",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r35",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r36",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r37",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r38",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r39",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r40",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r41",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r42",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r43",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r44",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r45",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r46",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r47",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r48",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r49",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r50",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r51",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r52",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r53",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r54",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r55",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r56",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r57",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r58",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r59",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r60",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r61",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r62",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r63",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r64",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r65",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r66",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r67",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r68",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r69",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r70",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r71",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r72",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r73",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r74",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r75",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r76",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r77",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r78",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r79",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r80",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r81",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r82",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r83",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r84",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r85",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r86",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r87",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r88",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r89",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r90",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r91",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r92",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r93",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r94",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r95",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r96",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r97",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r98",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r99",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ },
+ {
+ "system": "actor",
+ "run_id": "r100",
+ "provider": "p",
+ "model": "m",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z"
+ }
+ ]
+}
new file mode 100644
new file mode 100644
@@ -0,0 +1,49 @@
@@ -0,0 +1,49 @@
+{
+ "calls": [
+ {
+ "system": "actor",
+ "turn_id": "tsk_01JD8C4QJ7Z3K9W2X5V6N1M0PA:3",
+ "provider": "deepseek",
+ "model": "deepseek-v4-flash",
+ "surface": "actor.task",
+ "paid_by": "openvibe_key",
+ "input": 12000,
+ "output": 800,
+ "reasoning": 0,
+ "cache_read": 9000,
+ "cache_write": 0,
+ "cache_write_ttl": null,
+ "images": 0,
+ "audio_seconds": 0,
+ "video_seconds": 0,
+ "latency_ms": 4100,
+ "ttft_ms": 610,
+ "attempts": 1,
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z",
+ "operation": "chat",
+ "streamed": true,
+ "tps": 88.4,
+ "task": "actor.task",
+ "task_id": "tsk_01JD8C4QJ7Z3K9W2X5V6N1M0PA",
+ "harness": "openvibe",
+ "place": "provider",
+ "tool_calls": 2
+ },
+ {
+ "system": "node",
+ "run_id": "cmd_01JD8C4QJ7Z3K9W2X5V6N1M0PB",
+ "provider": "ollama",
+ "model": "qwen2.5:3b",
+ "outcome": "succeeded",
+ "at": "2026-11-12T23:30:00Z",
+ "operation": "chat",
+ "streamed": true,
+ "ttft_ms": 900,
+ "tps": 12.5,
+ "place": "machine",
+ "input": 300,
+ "output": 120
+ }
+ ]
+}
new file mode 100644
new file mode 100644
@@ -0,0 +1,5 @@
@@ -0,0 +1,5 @@
+{
+ "group": "person",
+ "key": "usr_x",
+ "calls": 3
+}
new file mode 100644
new file mode 100644
@@ -0,0 +1,74 @@
@@ -0,0 +1,74 @@
+{
+ "group": "model",
+ "key": "deepseek-v4-flash",
+ "provider": "deepseek",
+ "range": {
+ "from": "2026-11-05",
+ "to": "2026-11-12"
+ },
+ "calls": 18420,
+ "succeeded": 18311,
+ "errors": 109,
+ "success_rate": 0.9941,
+ "fallback_rate": 0.012,
+ "streamed_share": 0.71,
+ "cache_hit_rate": 0.04,
+ "cache_read_share": 0.63,
+ "ttft_ms": {
+ "p50": 540,
+ "p90": 980,
+ "p95": 1310,
+ "n": 13080
+ },
+ "latency_ms": {
+ "p50": 3900,
+ "p90": 9100,
+ "p95": 12800,
+ "n": 18420
+ },
+ "tps": {
+ "p50": 86,
+ "p90": 121,
+ "p95": 133,
+ "n": 12990
+ },
+ "tokens": {
+ "input": 210000000,
+ "output": 9100000,
+ "reasoning": 0,
+ "cache_read": 132000000,
+ "cache_write": 0
+ },
+ "cost": {
+ "charged_usd": 61.2,
+ "list_usd": 74.9,
+ "cache_saved_usd": 19.8,
+ "per_call_usd": 0.0033,
+ "per_million_output_usd": 6.72
+ },
+ "tasks": {
+ "count": 4120,
+ "cost_per_task_usd": {
+ "p50": 0.006,
+ "p90": 0.031,
+ "p95": 0.05,
+ "n": 4120
+ },
+ "time_per_task_ms": {
+ "p50": 14000,
+ "p90": 61000,
+ "p95": 98000,
+ "n": 4120
+ }
+ },
+ "top_errors": [
+ {
+ "error_class": "rate_limited",
+ "count": 71
+ },
+ {
+ "error_class": "timeout",
+ "count": 30
+ }
+ ]
+}
@@ -17336,14 +17336,14 @@
@@ -17336,14 +17336,14 @@
}
}
},
},
"ai.call.recorded": {
"ai.call.recorded": {
- "version": "1.0.0",
+ "version": "1.1.0",
"owner": "ai",
"owner": "ai",
"status": "active",
"status": "active",
"schema": {
"schema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://openvibe.network/contracts/events/payloads/ai.call.recorded.v1.json",
"$id": "https://openvibe.network/contracts/events/payloads/ai.call.recorded.v1.json",
"title": "AiCallRecordedPayload",
"title": "AiCallRecordedPayload",
- "description": "ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai.",
+ "description": "ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai. Since 1.1.0 (ai-metrics.md): OPERATION, STREAMED, TPS, QUEUE_MS, TASK, TASK_ID, TASK_MS, HARNESS, PLACE, ERROR_CLASS, FALLBACKS, CACHE_HIT, TOOL_CALLS and REGION, all optional. Products other than AI send their calls to POST /api/v1/usage/calls (ai.call-report@1); AI prices and publishes them.",
"type": "object",
"type": "object",
"required": [
"required": [
"system",
"system",
@@ -17560,6 +17560,854 @@
@@ -17560,6 +17560,854 @@
"at": {
"at": {
"type": "string",
"type": "string",
"format": "date-time"
"format": "date-time"
+ },
+ "operation": {
+ "enum": [
+ "chat",
+ "completion",
+ "embedding",
+ "image",
+ "image_edit",
+ "speech",
+ "transcription",
+ "translation",
+ "rerank",
+ "moderation",
+ "decision",
+ "realtime",
+ "batch",
+ "tool",
+ "other",
+ null
+ ],
+ "description": "Since 1.1.0: what kind of call it was."
+ },
+ "streamed": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."
+ },
+ "tps": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."
+ },
+ "queue_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."
+ },
+ "task": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."
+ },
+ "task_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."
+ },
+ "task_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."
+ },
+ "harness": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."
+ },
+ "place": {
+ "enum": [
+ "provider",
+ "machine",
+ "community",
+ "plan",
+ "host",
+ null
+ ],
+ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."
+ },
+ "error_class": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."
+ },
+ "fallbacks": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 50,
+ "description": "Since 1.1.0: how many offers failed before the one that answered."
+ },
+ "cache_hit": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."
+ },
+ "tool_calls": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: tool calls the model asked for in this call."
+ },
+ "region": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 40,
+ "description": "Since 1.1.0: the provider region or data centre, when known."
+ }
+ }
+ }
+ },
+ "ai.call-report": {
+ "version": "1.0.0",
+ "owner": "ai",
+ "status": "active",
+ "schema": {
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "$id": "https://openvibe.network/contracts/ai/call-report.v1.json",
+ "title": "AiCallReport",
+ "description": "ai.call-report@1 (ai-metrics.md): up to 100 AI calls a product made without OpenVibe.AI (Actor’s own model calls, a Codes harness turn, a local model on a person’s machine through Bot, Vibe), sent to AI’s POST /api/v1/usage/calls with the capability ai.usage.report. Each call is ai.call.recorded@1’s shape; the price is optional (AI prices from its rate cards: the charged amount first, then the list price) and SYSTEM + RUN_ID or TURN_ID is the idempotency key (a call sent twice is recorded once). AI publishes each as ai.call.recorded@1.",
+ "type": "object",
+ "additionalProperties": false,
+ "required": [
+ "calls"
+ ],
+ "properties": {
+ "calls": {
+ "type": "array",
+ "minItems": 1,
+ "maxItems": 100,
+ "items": {
+ "type": "object",
+ "required": [
+ "system",
+ "provider",
+ "model",
+ "outcome",
+ "at"
+ ],
+ "additionalProperties": false,
+ "properties": {
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 128,
+ "description": "The person the call was made for, or null when the call was anonymous."
+ },
+ "attribution": {
+ "type": "string",
+ "maxLength": 200,
+ "description": "The site or app the call came from, as '<type>:<id>' (for example 'site:design'), empty when nothing is known."
+ },
+ "surface": {
+ "type": "string",
+ "maxLength": 200,
+ "description": "The product surface: 'design.generate', 'codes.turn', 'ai.generate'. Free text, so a new surface needs no new contract."
+ },
+ "system": {
+ "type": "string",
+ "maxLength": 100,
+ "description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."
+ },
+ "provider": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 128
+ },
+ "model": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 200
+ },
+ "effort": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 64,
+ "description": "The reasoning effort the call asked for, when it asked for one."
+ },
+ "paid_by": {
+ "type": "string",
+ "enum": [
+ "own_key",
+ "openvibe_key",
+ "plan",
+ "own_machine",
+ "free_tier",
+ "network_allowance",
+ "org_key"
+ ]
+ },
+ "paid_by_detail": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 200,
+ "description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."
+ },
+ "input": {
+ "type": "integer",
+ "minimum": 0,
+ "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields."
+ },
+ "output": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "reasoning": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_read": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write_ttl": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "enum": [
+ "5m",
+ "1h",
+ null
+ ],
+ "description": "How long the written cache entry lives, when the provider says."
+ },
+ "images": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "audio_seconds": {
+ "type": "number",
+ "minimum": 0
+ },
+ "video_seconds": {
+ "type": "number",
+ "minimum": 0
+ },
+ "list_cost_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the tokens cost at the human-typed list prices. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "charged_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the payer was actually charged. A person's own key is never charged here: 0. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "fee_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "The network's fee on top of the cost, when the OpenVibe key paid. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "cache_saved_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the cached tokens saved against the plain input price. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "price_source": {
+ "type": "string",
+ "maxLength": 64,
+ "description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price). Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "price_date": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",
+ "description": "The day the price was checked, when it was. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "latency_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "ttft_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Time to the first token, when the call streamed and it was measured."
+ },
+ "attempts": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "outcome": {
+ "type": "string",
+ "enum": [
+ "succeeded",
+ "failed",
+ "cancelled",
+ "cached"
+ ]
+ },
+ "run_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 100
+ },
+ "turn_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 100
+ },
+ "at": {
+ "type": "string",
+ "format": "date-time"
+ },
+ "operation": {
+ "enum": [
+ "chat",
+ "completion",
+ "embedding",
+ "image",
+ "image_edit",
+ "speech",
+ "transcription",
+ "translation",
+ "rerank",
+ "moderation",
+ "decision",
+ "realtime",
+ "batch",
+ "tool",
+ "other",
+ null
+ ],
+ "description": "Since 1.1.0: what kind of call it was."
+ },
+ "streamed": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."
+ },
+ "tps": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."
+ },
+ "queue_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."
+ },
+ "task": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."
+ },
+ "task_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."
+ },
+ "task_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."
+ },
+ "harness": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."
+ },
+ "place": {
+ "enum": [
+ "provider",
+ "machine",
+ "community",
+ "plan",
+ "host",
+ null
+ ],
+ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."
+ },
+ "error_class": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."
+ },
+ "fallbacks": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 50,
+ "description": "Since 1.1.0: how many offers failed before the one that answered."
+ },
+ "cache_hit": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."
+ },
+ "tool_calls": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: tool calls the model asked for in this call."
+ },
+ "region": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 40,
+ "description": "Since 1.1.0: the provider region or data centre, when known."
+ }
+ },
+ "anyOf": [
+ {
+ "required": [
+ "run_id"
+ ]
+ },
+ {
+ "required": [
+ "turn_id"
+ ]
+ }
+ ]
+ }
+ }
+ }
+ }
+ },
+ "report.ai-performance": {
+ "version": "1.0.0",
+ "owner": "report",
+ "status": "active",
+ "schema": {
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "$id": "https://openvibe.network/contracts/report/ai-performance.v1.json",
+ "title": "ReportAiPerformance",
+ "description": "report.ai-performance@1 (ai-metrics.md): how AI calls performed over a range, for one group (a model, a provider, an operation, a system, a task). Percentiles come from log-scale histograms (within one bucket’s width). Public answers group by model, provider or operation only and show a group with at least 20 calls; system and task groups are for staff. Money is USD; tokens per second is the decode speed after the first token; cost per task sums the calls that share a task id.",
+ "type": "object",
+ "additionalProperties": false,
+ "required": [
+ "group",
+ "key",
+ "calls"
+ ],
+ "properties": {
+ "group": {
+ "enum": [
+ "model",
+ "provider",
+ "operation",
+ "system",
+ "task",
+ "place",
+ "harness"
+ ]
+ },
+ "key": {
+ "type": "string",
+ "maxLength": 200
+ },
+ "provider": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120
+ },
+ "range": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "from": {
+ "type": "string",
+ "format": "date"
+ },
+ "to": {
+ "type": "string",
+ "format": "date"
+ }
+ }
+ },
+ "calls": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "succeeded": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "errors": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "success_rate": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1
+ },
+ "fallback_rate": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1
+ },
+ "streamed_share": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1
+ },
+ "cache_hit_rate": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1
+ },
+ "cache_read_share": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 1,
+ "description": "Cache-read tokens as a share of all input tokens."
+ },
+ "ttft_ms": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "latency_ms": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "tps": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "tokens": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "input": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "output": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "reasoning": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_read": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "cost": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "charged_usd": {
+ "type": "number",
+ "minimum": 0
+ },
+ "list_usd": {
+ "type": "number",
+ "minimum": 0
+ },
+ "cache_saved_usd": {
+ "type": "number",
+ "minimum": 0
+ },
+ "per_call_usd": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "per_million_output_usd": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ }
+ }
+ },
+ "tasks": {
+ "type": [
+ "object",
+ "null"
+ ],
+ "additionalProperties": false,
+ "properties": {
+ "count": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cost_per_task_usd": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ },
+ "time_per_task_ms": {
+ "type": "object",
+ "additionalProperties": false,
+ "properties": {
+ "p50": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p90": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "p95": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "n": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ }
+ }
+ },
+ "top_errors": {
+ "type": "array",
+ "maxItems": 5,
+ "items": {
+ "type": "object",
+ "additionalProperties": false,
+ "required": [
+ "error_class",
+ "count"
+ ],
+ "properties": {
+ "error_class": {
+ "type": "string",
+ "maxLength": 60
+ },
+ "count": {
+ "type": "integer",
+ "minimum": 0
+ }
+ }
+ }
}
}
}
}
}
}
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Actor API",
"title": "OpenVibe.Actor API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Actor as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Actor as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.AI API",
"title": "OpenVibe.AI API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.AI as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.AI as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -4088,6 +4088,55 @@
@@ -4088,6 +4088,55 @@
}
}
}
}
},
},
+ "/api/v1/usage/calls": {
+ "post": {
+ "operationId": "post_api_v1_usage_calls",
+ "summary": "Report AI calls a product made without OpenVibe.AI (ai.call-report@1): AI prices any that bring no price, records each once and publishes ai.call.recorded@1, so every AI call on the network is in one ",
+ "description": "**ai.usage.report** (internal): Report AI calls a product made without OpenVibe.AI (ai.call-report@1): AI prices any that bring no price, records each once and publishes ai.call.recorded@1, so every AI call on the network is in one meter.",
+ "tags": [
+ "ai.usage"
+ ],
+ "x-openvibe-capabilities": [
+ "ai.usage.report"
+ ],
+ "x-openvibe-visibility": [
+ "internal"
+ ],
+ "x-openvibe-quota-class": "ai-read",
+ "security": [
+ {
+ "openvibeToken": [
+ "ai.usage.report"
+ ]
+ }
+ ],
+ "requestBody": {
+ "required": false,
+ "content": {
+ "application/json": {
+ "schema": {
+ "$ref": "#/components/schemas/ai.call-report.v1"
+ }
+ }
+ }
+ },
+ "responses": {
+ "2XX": {
+ "description": "Success"
+ },
+ "default": {
+ "description": "An error (RFC 9457 problem details)",
+ "content": {
+ "application/problem+json": {
+ "schema": {
+ "$ref": "#/components/schemas/errors.problem.v1"
+ }
+ }
+ }
+ }
+ }
+ }
+ },
"/api/v1/workflows/{key}/versions": {
"/api/v1/workflows/{key}/versions": {
"post": {
"post": {
"operationId": "post_api_v1_workflows_key_versions",
"operationId": "post_api_v1_workflows_key_versions",
@@ -5486,6 +5535,363 @@
@@ -5486,6 +5535,363 @@
}
}
}
}
},
},
+ "ai.call-report.v1": {
+ "title": "AiCallReport",
+ "description": "ai.call-report@1 (ai-metrics.md): up to 100 AI calls a product made without OpenVibe.AI (Actor’s own model calls, a Codes harness turn, a local model on a person’s machine through Bot, Vibe), sent to AI’s POST /api/v1/usage/calls with the capability ai.usage.report. Each call is ai.call.recorded@1’s shape; the price is optional (AI prices from its rate cards: the charged amount first, then the list price) and SYSTEM + RUN_ID or TURN_ID is the idempotency key (a call sent twice is recorded once). AI publishes each as ai.call.recorded@1.",
+ "type": "object",
+ "additionalProperties": false,
+ "required": [
+ "calls"
+ ],
+ "properties": {
+ "calls": {
+ "type": "array",
+ "minItems": 1,
+ "maxItems": 100,
+ "items": {
+ "type": "object",
+ "required": [
+ "system",
+ "provider",
+ "model",
+ "outcome",
+ "at"
+ ],
+ "additionalProperties": false,
+ "properties": {
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 128,
+ "description": "The person the call was made for, or null when the call was anonymous."
+ },
+ "attribution": {
+ "type": "string",
+ "maxLength": 200,
+ "description": "The site or app the call came from, as '<type>:<id>' (for example 'site:design'), empty when nothing is known."
+ },
+ "surface": {
+ "type": "string",
+ "maxLength": 200,
+ "description": "The product surface: 'design.generate', 'codes.turn', 'ai.generate'. Free text, so a new surface needs no new contract."
+ },
+ "system": {
+ "type": "string",
+ "maxLength": 100,
+ "description": "What ran: 'ai', 'harness:claude-code', 'harness:codex', 'actor', 'node'."
+ },
+ "provider": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 128
+ },
+ "model": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 200
+ },
+ "effort": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 64,
+ "description": "The reasoning effort the call asked for, when it asked for one."
+ },
+ "paid_by": {
+ "type": "string",
+ "enum": [
+ "own_key",
+ "openvibe_key",
+ "plan",
+ "own_machine",
+ "free_tier",
+ "network_allowance",
+ "org_key"
+ ]
+ },
+ "paid_by_detail": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 200,
+ "description": "Which key or plan paid, for example 'anthropic ...a1b2' or 'claude-max'. Never a whole secret."
+ },
+ "input": {
+ "type": "integer",
+ "minimum": 0,
+ "description": "The uncached input tokens. Cache reads and cache writes are counted on their own fields."
+ },
+ "output": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "reasoning": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_read": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "cache_write_ttl": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "enum": [
+ "5m",
+ "1h",
+ null
+ ],
+ "description": "How long the written cache entry lives, when the provider says."
+ },
+ "images": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "audio_seconds": {
+ "type": "number",
+ "minimum": 0
+ },
+ "video_seconds": {
+ "type": "number",
+ "minimum": 0
+ },
+ "list_cost_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the tokens cost at the human-typed list prices. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "charged_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the payer was actually charged. A person's own key is never charged here: 0. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "fee_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "The network's fee on top of the cost, when the OpenVibe key paid. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "cache_saved_usd": {
+ "type": "number",
+ "minimum": 0,
+ "description": "What the cached tokens saved against the plain input price. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "price_source": {
+ "type": "string",
+ "maxLength": 64,
+ "description": "Where the prices came from: 'models' (a person's typed model row), 'pricing' (AI_PRICING_JSON), 'flat' (the flat rates), 'no cache price' (no cache price is typed, so the cache tokens are priced at the input price). Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "price_date": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "pattern": "^[0-9]{4}-[0-9]{2}-[0-9]{2}$",
+ "description": "The day the price was checked, when it was. Optional here: AI prices a call that brings no price from its own rate cards."
+ },
+ "latency_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0
+ },
+ "ttft_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Time to the first token, when the call streamed and it was measured."
+ },
+ "attempts": {
+ "type": "integer",
+ "minimum": 0
+ },
+ "outcome": {
+ "type": "string",
+ "enum": [
+ "succeeded",
+ "failed",
+ "cancelled",
+ "cached"
+ ]
+ },
+ "run_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 100
+ },
+ "turn_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 100
+ },
+ "at": {
+ "type": "string",
+ "format": "date-time"
+ },
+ "operation": {
+ "enum": [
+ "chat",
+ "completion",
+ "embedding",
+ "image",
+ "image_edit",
+ "speech",
+ "transcription",
+ "translation",
+ "rerank",
+ "moderation",
+ "decision",
+ "realtime",
+ "batch",
+ "tool",
+ "other",
+ null
+ ],
+ "description": "Since 1.1.0: what kind of call it was."
+ },
+ "streamed": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one)."
+ },
+ "tps": {
+ "type": [
+ "number",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure."
+ },
+ "queue_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: time waiting before the call was sent (a queue, a rate gate)."
+ },
+ "task": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn)."
+ },
+ "task_id": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 120,
+ "description": "Since 1.1.0: the task or run this call is one step of, so cost and time add up per task."
+ },
+ "task_ms": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: on the last call of a task, the whole task’s wall time."
+ },
+ "harness": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …)."
+ },
+ "place": {
+ "enum": [
+ "provider",
+ "machine",
+ "community",
+ "plan",
+ "host",
+ null
+ ],
+ "description": "Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts."
+ },
+ "error_class": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 60,
+ "description": "Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid)."
+ },
+ "fallbacks": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "maximum": 50,
+ "description": "Since 1.1.0: how many offers failed before the one that answered."
+ },
+ "cache_hit": {
+ "type": [
+ "boolean",
+ "null"
+ ],
+ "description": "Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran)."
+ },
+ "tool_calls": {
+ "type": [
+ "integer",
+ "null"
+ ],
+ "minimum": 0,
+ "description": "Since 1.1.0: tool calls the model asked for in this call."
+ },
+ "region": {
+ "type": [
+ "string",
+ "null"
+ ],
+ "maxLength": 40,
+ "description": "Since 1.1.0: the provider region or data centre, when known."
+ }
+ },
+ "anyOf": [
+ {
+ "required": [
+ "run_id"
+ ]
+ },
+ {
+ "required": [
+ "turn_id"
+ ]
+ }
+ ]
+ }
+ }
+ }
+ },
"ai.choice.v1": {
"ai.choice.v1": {
"title": "AiChoiceV1",
"title": "AiChoiceV1",
"description": "One model and where it comes from, for a task or a run: OpenVibe's supply (openvibe), the person's own provider key (keys), or one of their own computers through OpenVibe Link (machines). A machine choice names the machine; the other sources never do. Used by ai.run-request@1, ai.task@1 and ai.task-defaults@1.",
"description": "One model and where it comes from, for a task or a run: OpenVibe's supply (openvibe), the person's own provider key (keys), or one of their own computers through OpenVibe Link (machines). A machine choice names the machine; the other sources never do. Used by ai.run-request@1, ai.task@1 and ai.task-defaults@1.",
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Bench API",
"title": "OpenVibe.Bench API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Bench as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Bench as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Billing API",
"title": "OpenVibe.Billing API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Billing as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Billing as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Blog API",
"title": "OpenVibe.Blog API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Blog as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Blog as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Bot API",
"title": "OpenVibe.Bot API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Bot as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Bot as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Chat API",
"title": "OpenVibe.Chat API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Chat as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Chat as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Codes API",
"title": "OpenVibe.Codes API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Codes as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Codes as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Community API",
"title": "OpenVibe.Community API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Community as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Community as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe Connect API",
"title": "OpenVibe Connect API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe Connect as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe Connect as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Coupons API",
"title": "OpenVibe.Coupons API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Coupons as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Coupons as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Deals API",
"title": "OpenVibe.Deals API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Deals as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Deals as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Design API",
"title": "OpenVibe.Design API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Design as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Design as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Domains API",
"title": "OpenVibe.Domains API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Domains as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Domains as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Events API",
"title": "OpenVibe.Events API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Events as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Events as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Exchange API",
"title": "OpenVibe.Exchange API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Exchange as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Exchange as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Food API",
"title": "OpenVibe.Food API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Food as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Food as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Games API",
"title": "OpenVibe.Games API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Games as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Games as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Git API",
"title": "OpenVibe.Git API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Git as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Git as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Host API",
"title": "OpenVibe.Host API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Host as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Host as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -12,8 +12,8 @@
@@ -12,8 +12,8 @@
"service": "ai",
"service": "ai",
"name": "OpenVibe.AI",
"name": "OpenVibe.AI",
"origin": "https://ai.openvibe.services",
"origin": "https://ai.openvibe.services",
- "operations": 72,
- "capabilities": 19
+ "operations": 73,
+ "capabilities": 20
},
},
{
{
"service": "bench",
"service": "bench",
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Inventory API",
"title": "OpenVibe.Inventory API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Inventory as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Inventory as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Live API",
"title": "OpenVibe.Live API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Live as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Live as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Mail API",
"title": "OpenVibe.Mail API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Mail as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Mail as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.MediaHub API",
"title": "OpenVibe.MediaHub API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.MediaHub as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.MediaHub as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Media API",
"title": "OpenVibe.Media API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Media as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Media as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Network API",
"title": "OpenVibe.Network API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Network as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Network as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.News API",
"title": "OpenVibe.News API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.News as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.News as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenRestream API",
"title": "OpenRestream API",
- "version": "0.420.0",
- "description": "Routes of OpenRestream as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenRestream as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Play API",
"title": "OpenVibe.Play API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Play as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Play as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Quest API",
"title": "OpenVibe.Quest API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Quest as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Quest as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Report API",
"title": "OpenVibe.Report API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Report as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Report as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Reviews API",
"title": "OpenVibe.Reviews API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Reviews as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Reviews as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Run API",
"title": "OpenVibe.Run API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Run as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Run as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Search API",
"title": "OpenVibe.Search API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Search as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Search as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Services API",
"title": "OpenVibe.Services API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Services as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Services as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Sources API",
"title": "OpenVibe.Sources API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Sources as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Sources as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Space API",
"title": "OpenVibe.Space API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Space as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Space as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Tips API",
"title": "OpenVibe.Tips API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Tips as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Tips as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Today API",
"title": "OpenVibe.Today API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Today as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Today as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Tools API",
"title": "OpenVibe.Tools API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Tools as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Tools as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Trade API",
"title": "OpenVibe.Trade API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Trade as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Trade as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.VIP API",
"title": "OpenVibe.VIP API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.VIP as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.VIP as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Vision API",
"title": "OpenVibe.Vision API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Vision as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Vision as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Watch API",
"title": "OpenVibe.Watch API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Watch as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Watch as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Wiki API",
"title": "OpenVibe.Wiki API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Wiki as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Wiki as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Work API",
"title": "OpenVibe.Work API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Work as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Work as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -3,8 +3,8 @@
@@ -3,8 +3,8 @@
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"info": {
"info": {
"title": "OpenVibe.Zone API",
"title": "OpenVibe.Zone API",
- "version": "0.420.0",
- "description": "Routes of OpenVibe.Zone as the OpenVibe contracts describe them (openvibe-contracts 0.420.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
+ "version": "0.421.0",
+ "description": "Routes of OpenVibe.Zone as the OpenVibe contracts describe them (openvibe-contracts 0.421.0): each operation lists the capabilities it performs; a token for the service's audience must carry one of them unless the route is open. Generated by openvibe-contracts lib/openapi.js; do not edit.",
"license": {
"license": {
"name": "MIT",
"name": "MIT",
"identifier": "MIT"
"identifier": "MIT"
@@ -162831,9 +162831,9 @@ export interface AiRunError {
@@ -162831,9 +162831,9 @@ export interface AiRunError {
retry_at?: string | null;
retry_at?: string | null;
}
}
-/** [email protected] (owner: ai) */
+/** [email protected] (owner: ai) */
/**
/**
- * ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai.
+ * ai.call.recorded v1 (plan L40, one AI meter across the network). One AI call, wherever it happened: OpenVibe.AI's own runs, a harness turn in Codes, an Actor task, Vibe, a local model on a person's own machine. who and where: subject (the person, or null when the call is anonymous), attribution (the site or app the call came from, free text such as 'site:design'), surface (the product surface, free text such as 'design.generate' or 'codes.turn'). what ran: system (ai, harness:claude-code, harness:codex, actor, node), provider, model, effort. who paid: paid_by (own_key, openvibe_key, plan, own_machine, free_tier, network_allowance, org_key) and paid_by_detail (for example 'anthropic ...a1b2' for a person's own key, or 'claude-max' for a plan). tokens: input (the UNCACHED input tokens), output, reasoning, cache_read, cache_write (with cache_write_ttl 5m or 1h), images, audio_seconds, video_seconds. money, in USD: list_cost_usd (what the tokens cost at the human-typed list prices), charged_usd (what the payer was actually charged), fee_usd (the network's fee on top), cache_saved_usd (what the cache saved against the plain input price). price_source says where the prices came from ('models', 'pricing', 'flat', or 'no cache price' when no cache price is typed and the cache tokens are priced at the input price), price_date the day the price was checked. how it went: latency_ms, ttft_ms, attempts, outcome. ids: run_id or turn_id, and at. The record carries NO prompt and NO answer text, ever. A ledger (OpenVibe.AI) rolls the records up; a record consumed twice is stored once (idempotent by system and run_id or turn_id). Envelope: subject { type: run, id: <run_id> } or { type: user, id: <subject> }, visibility internal, priority low, actor service:ai. Since 1.1.0 (ai-metrics.md): OPERATION, STREAMED, TPS, QUEUE_MS, TASK, TASK_ID, TASK_MS, HARNESS, PLACE, ERROR_CLASS, FALLBACKS, CACHE_HIT, TOOL_CALLS and REGION, all optional. Products other than AI send their calls to POST /api/v1/usage/calls (ai.call-report@1); AI prices and publishes them.
*/
*/
export interface AiCallRecordedPayload {
export interface AiCallRecordedPayload {
/**
/**
@@ -162912,6 +162912,254 @@ export interface AiCallRecordedPayload {
@@ -162912,6 +162912,254 @@ export interface AiCallRecordedPayload {
run_id?: string | null;
run_id?: string | null;
turn_id?: string | null;
turn_id?: string | null;
at: string;
at: string;
+ /**
+ * Since 1.1.0: what kind of call it was.
+ */
+ operation?:
+ | "chat"
+ | "completion"
+ | "embedding"
+ | "image"
+ | "image_edit"
+ | "speech"
+ | "transcription"
+ | "translation"
+ | "rerank"
+ | "moderation"
+ | "decision"
+ | "realtime"
+ | "batch"
+ | "tool"
+ | "other"
+ | null;
+ /**
+ * Since 1.1.0: whether the answer came as a stream (TTFT is only measured on one).
+ */
+ streamed?: boolean | null;
+ /**
+ * Since 1.1.0: output tokens per second after the first token (decode speed); null when not streamed or too short to measure.
+ */
+ tps?: number | null;
+ /**
+ * Since 1.1.0: time waiting before the call was sent (a queue, a rate gate).
+ */
+ queue_ms?: number | null;
+ /**
+ * Since 1.1.0: the task kind the call served (a task name, a workflow key, chat.reply, code.turn).
+ */
+ task?: string | null;
+ /**
+ * Since 1.1.0: the task or run this call is one step of, so cost and time add up per task.
+ */
+ task_id?: string | null;
+ /**
+ * Since 1.1.0: on the last call of a task, the whole task’s wall time.
+ */
+ task_ms?: number | null;
+ /**
+ * Since 1.1.0: the harness that made the call (openvibe, dsh, codex, claude-code, gemini-cli, opencode …).
+ */
+ harness?: string | null;
+ /**
+ * Since 1.1.0: where the model ran: a provider’s API, the person’s own machine, a community machine, a signed-in plan, OpenVibe’s own hosts.
+ */
+ place?: "provider" | "machine" | "community" | "plan" | "host" | null;
+ /**
+ * Since 1.1.0: on a failure, its class (rate_limited, timeout, context_length, refused, auth, server, network, invalid).
+ */
+ error_class?: string | null;
+ /**
+ * Since 1.1.0: how many offers failed before the one that answered.
+ */
+ fallbacks?: number | null;
+ /**
+ * Since 1.1.0: true when the whole answer came from OpenVibe’s exact answer cache (no model ran).
+ */
+ cache_hit?: boolean | null;
+ /**
+ * Since 1.1.0: tool calls the model asked for in this call.
+ */
+ tool_calls?: number | null;
+ /**
+ * Since 1.1.0: the provider region or data centre, when known.
+ */
+ region?: string | null;
+}
+
+/** [email protected] (owner: ai) */
+/**
+ * ai.call-report@1 (ai-metrics.md): up to 100 AI calls a product made without OpenVibe.AI (Actor’s own model calls, a Codes harness turn, a local model on a person’s machine through Bot, Vibe), sent to AI’s POST /api/v1/usage/calls with the capability ai.usage.report. Each call is ai.call.recorded@1’s shape; the price is optional (AI prices from its rate cards: the charged amount first, then the list price) and SYSTEM + RUN_ID or TURN_ID is the idempotency key (a call sent twice is recorded once). AI publishes each as ai.call.recorded@1.
+ */
+export interface AiCallReport {
+ /**
+ * @minItems 1
+ * @maxItems 100
+ */
+ calls: [
+ (
+ | {
+ [k: string]: unknown | undefined;
+ }
+ | {
+ [k: string]: unknown | undefined;
+ }
+ ),
+ ...(
+ | {
+ [k: string]: unknown | undefined;
+ }
+ | {
+ [k: string]: unknown | undefined;
+ }
+ )[]
+ ];
+}
+
+/** [email protected] (owner: report) */
+/**
+ * report.ai-performance@1 (ai-metrics.md): how AI calls performed over a range, for one group (a model, a provider, an operation, a system, a task). Percentiles come from log-scale histograms (within one bucket’s width). Public answers group by model, provider or operation only and show a group with at least 20 calls; system and task groups are for staff. Money is USD; tokens per second is the decode speed after the first token; cost per task sums the calls that share a task id.
+ */
+export interface ReportAiPerformance {
+ group: "model" | "provider" | "operation" | "system" | "task" | "place" | "harness";
+ key: string;
+ provider?: string | null;
+ range?: {
+ from?: string;
+ to?: string;
+ };
+ calls: number;
+ succeeded?: number;
+ errors?: number;
+ success_rate?: number | null;
+ fallback_rate?: number | null;
+ streamed_share?: number | null;
+ cache_hit_rate?: number | null;
+ /**
+ * Cache-read tokens as a share of all input tokens.
+ */
+ cache_read_share?: number | null;
+ ttft_ms?: {
+ p50?: number | null;
+ p90?: number | null;
+ p95?: number | null;
+ n?: number;
+ };
+ latency_ms?: {
+ p50?: number | null;
+ p90?: number | null;
+ p95?: number | null;
+ n?: number;
+ };
+ tps?: {
+ p50?: number | null;
+ p90?: number | null;
+ p95?: number | null;
+ n?: number;
+ };
+ tokens?: {
+ input?: number;
+ output?: number;
+ reasoning?: number;
+ cache_read?: number;
+ cache_write?: number;
+ };
+ cost?: {
+ charged_usd?: number;
+ list_usd?: number;
+ cache_saved_usd?: number;
+ per_call_usd?: number | null;
+ per_million_output_usd?: number | null;
+ };
+ tasks?: {
+ count?: number;
+ cost_per_task_usd?: {
+ p50?: number | null;
+ p90?: number | null;
+ p95?: number | null;
+ n?: number;
+ };
+ time_per_task_ms?: {
+ p50?: number | null;
+ p90?: number | null;
+ p95?: number | null;
+ n?: number;
+ };
+ } | null;
+ /**
+ * @maxItems 5
+ */
+ top_errors?:
+ | []
+ | [
+ {
+ error_class: string;
+ count: number;
+ }
+ ]
+ | [
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ }
+ ]
+ | [
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ }
+ ]
+ | [
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ }
+ ]
+ | [
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ },
+ {
+ error_class: string;
+ count: number;
+ }
+ ];
}
}
/** [email protected] (owner: ai) */
/** [email protected] (owner: ai) */
new file mode 100644
new file mode 100644
@@ -0,0 +1,23 @@
@@ -0,0 +1,23 @@
+{
+ "id": "ai.usage.report",
+ "version": "1.0",
+ "owner": "ai",
+ "status": "active",
+ "visibility": "internal",
+ "description": "Report AI calls a product made without OpenVibe.AI (ai.call-report@1): AI prices any that bring no price, records each once and publishes ai.call.recorded@1, so every AI call on the network is in one meter.",
+ "permissions": [
+ "ai:usage:report"
+ ],
+ "resourceConstraints": [
+ "none"
+ ],
+ "quotaClass": "ai-read",
+ "events": [
+ "ai.call.recorded"
+ ],
+ "implementedBy": [
+ "POST /api/v1/usage/calls"
+ ],
+ "inputSchema": "ai.call-report@1",
+ "outputSchema": "common.no-body@1"
+}
@@ -20,24 +20,25 @@
@@ -20,24 +20,25 @@
"note": "the public API (OpenAI-compatible /v1 and the six operations); its human pages moved to OpenVibe.Exchange on 2026-11-07 and answer 301 there. A run receipt (/runs/:id) and the operator console stay for the person signed in"
"note": "the public API (OpenAI-compatible /v1 and the six operations); its human pages moved to OpenVibe.Exchange on 2026-11-07 and answer 301 there. A run receipt (/runs/:id) and the operator console stay for the person signed in"
},
},
"capabilities": [
"capabilities": [
+ "ai.actions.read",
"ai.app.run",
"ai.app.run",
+ "ai.batches.create",
+ "ai.batches.read",
+ "ai.config.manage",
"ai.credential.manage",
"ai.credential.manage",
+ "ai.layout.suggest",
+ "ai.me.manage",
+ "ai.me.read",
+ "ai.memory.read",
+ "ai.memory.write",
"ai.model.read",
"ai.model.read",
"ai.provider.manage",
"ai.provider.manage",
"ai.quota.attribution.manage",
"ai.quota.attribution.manage",
- "ai.batches.create",
- "ai.batches.read",
"ai.run.create",
"ai.run.create",
"ai.run.read",
"ai.run.read",
"ai.usage.read",
"ai.usage.read",
+ "ai.usage.report",
"ai.workflow.manage",
"ai.workflow.manage",
- "ai.actions.read",
- "ai.memory.read",
- "ai.memory.write",
- "ai.me.read",
- "ai.me.manage",
- "ai.layout.suggest",
- "ai.config.manage",
"exchange.search.icons"
"exchange.search.icons"
],
],
"eventsProduced": [
"eventsProduced": [
@@ -90,14 +91,14 @@
@@ -90,14 +91,14 @@
],
],
"window": "automatic only while ovhost waits for readiness after the restart (30 s in host.example.json); manual afterwards, as long as no blocker applies",
"window": "automatic only while ovhost waits for readiness after the restart (30 s in host.example.json); manual afterwards, as long as no blocker applies",
"blockers": {
"blockers": {
- "none": "the schema code only adds (CREATE \u2026 IF NOT EXISTS, ADD COLUMN; no DROP, RENAME or table rebuild), which an older release ignores"
+ "none": "the schema code only adds (CREATE … IF NOT EXISTS, ADD COLUMN; no DROP, RENAME or table rebuild), which an older release ignores"
}
}
},
},
"contracts": {
"contracts": {
"range": ">=0.6.0 <1.0.0"
"range": ">=0.6.0 <1.0.0"
},
},
"leases": {
"leases": {
- "none": "no claims: one process owns its PostgreSQL database (ov_ai); a run is taken with a compare-and-set on its status (queued \u2192 running)"
+ "none": "no claims: one process owns its PostgreSQL database (ov_ai); a run is taken with a compare-and-set on its status (queued → running)"
}
}
},
},
"notes": "Providers, models, routing profiles, versioned prompt templates and workflows, runs, request logs, citations, scoped cache, quotas and audit. Workflow output is a draft/evidence package attributed to workflow + model + run. ai.run.queued|succeeded|failed|cached have payload contracts (v0.30.0, status planned): AI publishes them once its Events client is wired in; it publishes none today. ai.run.create takes ai.run-request@1 and returns ai.run@1. Produces ai.run@1 effort_requested, effort_applied, effort_rung and ladder receipts; consumes ai.effort@1 and ai.run-request@1 effort/ladder metadata. Actor consumes those receipts; AI does not authorize agent tickets.",
"notes": "Providers, models, routing profiles, versioned prompt templates and workflows, runs, request logs, citations, scoped cache, quotas and audit. Workflow output is a draft/evidence package attributed to workflow + model + run. ai.run.queued|succeeded|failed|cached have payload contracts (v0.30.0, status planned): AI publishes them once its Events client is wired in; it publishes none today. ai.run.create takes ai.run-request@1 and returns ai.run@1. Produces ai.run@1 effort_requested, effort_applied, effort_rung and ladder receipts; consumes ai.effort@1 and ai.run-request@1 effort/ladder metadata. Actor consumes those receipts; AI does not authorize agent tickets.",
@@ -1,6 +1,6 @@
@@ -1,6 +1,6 @@
{
{
"name": "openvibe-contracts",
"name": "openvibe-contracts",
- "version": "0.420.0",
+ "version": "0.421.0",
"description": "Machine-readable contracts for the OpenVibe network: schemas, manifests, ids, error envelope, capability checks.",
"description": "Machine-readable contracts for the OpenVibe network: schemas, manifests, ids, error envelope, capability checks.",
"main": "index.js",
"main": "index.js",
"types": "generated/typescript/index.d.ts",
"types": "generated/typescript/index.d.ts",