@plasm_lang/vercel-agent 0.3.77 → 0.3.80

package/templates/mcp-radar/agent/catalogs/tavily/domain.yaml

@@ -0,0 +1,373 @@
+version: 2
+http_backend: https://api.tavily.com
+entities:
+  SearchResult:
+    id_field: url
+    description: A ranked web search result from Tavily Search.
+    fields:
+      url:
+        required: true
+        value_ref: nv_search_result_url
+      title:
+        required: false
+        value_ref: nv_search_result_title
+      content:
+        required: false
+        value_ref: nv_search_result_content
+      score:
+        required: false
+        value_ref: nv_search_result_score
+      raw_content:
+        required: false
+        value_ref: nv_search_result_raw_content
+      favicon:
+        required: false
+        value_ref: nv_search_result_favicon
+  ExtractResult:
+    id_field: url
+    description: Extracted or crawled page content from Tavily Extract / Crawl.
+    fields:
+      url:
+        required: true
+        value_ref: nv_extract_result_url
+      raw_content:
+        required: false
+        value_ref: nv_extract_result_raw_content
+      favicon:
+        required: false
+        value_ref: nv_extract_result_favicon
+  ResearchTask:
+    id_field: request_id
+    description: An async Tavily Research task.
+    fields:
+      request_id:
+        required: true
+        value_ref: nv_research_task_request_id
+      status:
+        required: false
+        value_ref: nv_research_task_status
+      input:
+        required: false
+        value_ref: nv_research_task_input
+      model:
+        required: false
+        value_ref: nv_research_task_model
+      created_at:
+        required: false
+        value_ref: nv_research_task_created_at
+      content:
+        required: false
+        value_ref: nv_research_task_content
+      response_time:
+        required: false
+        value_ref: nv_research_task_response_time
+      sources:
+        required: false
+        value_ref: nv_research_task_sources
+capabilities:
+  web_search:
+    kind: search
+    entity: SearchResult
+    description: AI-powered web search. Returns ranked results with optional LLM answer.
+    parameters:
+    - name: query
+      value_ref: nv_wire_str_short
+      required: true
+      role: search
+    - name: search_depth
+      value_ref: nv_web_search_search_depth
+      required: false
+      role: response_control
+    - name: chunks_per_source
+      value_ref: nv_wire_int
+      required: false
+      role: response_control
+    - name: max_results
+      value_ref: nv_wire_int
+      required: false
+      role: response_control
+    - name: topic
+      value_ref: nv_web_search_topic
+      required: false
+    - name: time_range
+      value_ref: nv_web_search_time_range
+      required: false
+    - name: start_date
+      value_ref: nv_wire_str_short
+      required: false
+    - name: end_date
+      value_ref: nv_wire_str_short
+      required: false
+    - name: include_answer
+      value_ref: nv_wire_bool
+      required: false
+      role: response_control
+    - name: include_raw_content
+      value_ref: nv_wire_bool
+      required: false
+      role: response_control
+    - name: include_images
+      value_ref: nv_wire_bool
+      required: false
+      role: response_control
+    - name: include_favicon
+      value_ref: nv_wire_bool
+      required: false
+      role: response_control
+    - name: include_domains
+      value_ref: nv_web_search_include_domains
+      required: false
+    - name: exclude_domains
+      value_ref: nv_web_search_exclude_domains
+      required: false
+    - name: country
+      value_ref: nv_wire_str_short
+      required: false
+    - name: auto_parameters
+      value_ref: nv_wire_bool
+      required: false
+      role: response_control
+    - name: exact_match
+      value_ref: nv_wire_bool
+      required: false
+  url_extract:
+    kind: query
+    entity: ExtractResult
+    description: Extract cleaned content from one or more URLs.
+    parameters:
+    - name: urls
+      value_ref: nv_url_extract_urls
+      required: true
+    - name: query
+      value_ref: nv_wire_str_short
+      required: false
+    - name: extract_depth
+      value_ref: nv_url_extract_extract_depth
+      required: false
+      role: response_control
+    - name: format
+      value_ref: nv_url_extract_format
+      required: false
+      role: response_control
+    - name: chunks_per_source
+      value_ref: nv_wire_int
+      required: false
+      role: response_control
+    - name: include_images
+      value_ref: nv_wire_bool
+      required: false
+      role: response_control
+    - name: include_favicon
+      value_ref: nv_wire_bool
+      required: false
+      role: response_control
+  site_crawl:
+    kind: query
+    entity: ExtractResult
+    description: Graph-based website traversal — crawl multiple pages in parallel.
+    parameters:
+    - name: url
+      value_ref: nv_wire_str_short
+      required: true
+      role: scope
+    - name: instructions
+      value_ref: nv_wire_str_short
+      required: false
+    - name: max_depth
+      value_ref: nv_wire_int
+      required: false
+      role: response_control
+    - name: max_breadth
+      value_ref: nv_wire_int
+      required: false
+      role: response_control
+    - name: limit
+      value_ref: nv_wire_int
+      required: false
+      role: response_control
+    - name: chunks_per_source
+      value_ref: nv_wire_int
+      required: false
+      role: response_control
+    - name: include_images
+      value_ref: nv_wire_bool
+      required: false
+      role: response_control
+  research_create:
+    kind: create
+    entity: ResearchTask
+    description: Start an async deep research task (returns request_id for polling).
+    provides:
+    - request_id
+    - created_at
+    - status
+    - input
+    - model
+    parameters:
+    - name: input
+      value_ref: nv_wire_str_short
+      required: true
+    - name: model
+      value_ref: nv_research_create_model
+      required: false
+    - name: citation_format
+      value_ref: nv_research_create_citation_format
+      required: false
+  research_get:
+    kind: get
+    entity: ResearchTask
+    description: Poll the status and retrieve the report for a research task.
+    provides:
+    - request_id
+    - status
+    - input
+    - model
+    - created_at
+    - content
+    - response_time
+    - sources
+auth:
+  scheme: bearer_token
+  env: TAVILY_API_TOKEN
+  hosted_kv: plasm:outbound:v1:catalog:tavily
+values:
+  nv_extract_result_favicon:
+    type: string
+    string_semantics: short
+    description: Favicon URL for the page's domain.
+  nv_extract_result_raw_content:
+    type: string
+    string_semantics: markdown
+    description: Full extracted page content (markdown or plain text).
+  nv_extract_result_url:
+    type: string
+    string_semantics: short
+    description: URL of the extracted page.
+  nv_research_create_citation_format:
+    type: select
+    allowed_values:
+    - numbered
+    - mla
+    - apa
+    - chicago
+  nv_research_create_model:
+    type: select
+    allowed_values:
+    - mini
+    - pro
+    - auto
+  nv_research_task_content:
+    type: string
+    string_semantics: markdown
+    description: Full research content/report (populated when status=completed).
+  nv_research_task_created_at:
+    type: date
+    value_format: rfc3339
+    description: Timestamp when the task was created.
+  nv_research_task_input:
+    type: string
+    string_semantics: short
+    description: The research question submitted.
+  nv_research_task_model:
+    type: select
+    allowed_values:
+    - mini
+    - pro
+    - auto
+    description: Research agent model used.
+  nv_research_task_request_id:
+    type: string
+    string_semantics: short
+    description: Unique identifier for the research task (use to poll status).
+  nv_research_task_response_time:
+    type: number
+    description: Time in seconds for the research task to complete.
+  nv_research_task_status:
+    type: select
+    allowed_values:
+    - pending
+    - running
+    - completed
+    - failed
+    description: Current execution status of the task.
+  nv_search_result_content:
+    type: string
+    string_semantics: markdown
+    description: Relevance snippet or chunked content from the page.
+  nv_search_result_favicon:
+    type: string
+    string_semantics: short
+    description: Favicon URL for the result's domain.
+  nv_search_result_raw_content:
+    type: string
+    string_semantics: markdown
+    description: Full cleaned page content (only when include_raw_content=true).
+  nv_search_result_score:
+    type: number
+    description: Relevance score (0–1).
+  nv_search_result_title:
+    type: string
+    string_semantics: short
+    description: Title of the source page.
+  nv_search_result_url:
+    type: string
+    string_semantics: short
+    description: URL of the source page.
+  nv_url_extract_extract_depth:
+    type: select
+    allowed_values:
+    - basic
+    - advanced
+  nv_url_extract_format:
+    type: select
+    allowed_values:
+    - markdown
+    - text
+  nv_web_search_search_depth:
+    type: select
+    allowed_values:
+    - basic
+    - fast
+    - ultra-fast
+    - advanced
+  nv_web_search_time_range:
+    type: select
+    allowed_values:
+    - day
+    - week
+    - month
+    - year
+    - d
+    - w
+    - m
+    - y
+  nv_web_search_topic:
+    type: select
+    allowed_values:
+    - general
+    - news
+    - finance
+  nv_wire_bool:
+    type: boolean
+  nv_wire_int:
+    type: integer
+  nv_wire_str_short:
+    type: string
+    string_semantics: short
+  nv_research_task_sources:
+    type: array
+    items:
+      value_ref: nv_wire_str_short
+    description: Cited sources (populated when status=completed).
+  nv_url_extract_urls:
+    type: array
+    items:
+      value_ref: nv_wire_str_short
+  nv_web_search_exclude_domains:
+    type: array
+    items:
+      value_ref: nv_wire_str_short
+  nv_web_search_include_domains:
+    type: array
+    items:
+      value_ref: nv_wire_str_short

package/templates/mcp-radar/agent/catalogs/tavily/eval/cases.yaml

@@ -0,0 +1,56 @@
+# Tavily — `SearchResult`, `ExtractResult`, `ResearchTask` (search, query, create, get).
+- id: tv-01
+  schema: tavily
+  goal: "Research briefing: what are the main risks of LLM prompt injection in 2025?"
+  tags: [search]
+  covers: [search_text]
+  expect:
+    entities_any: [SearchResult]
+
+- id: tv-02
+  schema: tavily
+  goal: "Extract readable text from these documentation URLs for offline notes"
+  tags: [extract]
+  covers: [query_filtered]
+  expect:
+    entities_any: [ExtractResult]
+
+- id: tv-03
+  schema: tavily
+  goal: "Crawl the product marketing site up to depth 2 for a competitive summary"
+  tags: [crawl]
+  covers: [query_filtered]
+  expect:
+    entities_any: [ExtractResult]
+
+- id: tv-04
+  schema: tavily
+  goal: "Start a deep research job on quantum error correction and save the request id"
+  tags: [create]
+  covers: [create]
+  expect:
+    entities_any: [ResearchTask]
+
+- id: tv-05
+  schema: tavily
+  goal: "Poll research task req_abc123 until the report body is ready"
+  tags: [get]
+  covers: [get]
+  expect:
+    entities_any: [ResearchTask]
+
+- id: tv-06
+  schema: tavily
+  goal: "Kick off async research on a topic, then fetch status when the user returns"
+  tags: [multi_step]
+  covers: [multi_step, create, get]
+  expect:
+    entities_any: [ResearchTask]
+
+- id: tv-07
+  schema: tavily
+  goal: "Web search for 'rust async' but return only titles and URLs in the result list"
+  tags: [search, projection]
+  covers: [search_text, projection]
+  expect:
+    entities_any: [SearchResult]

package/templates/mcp-radar/agent/catalogs/tavily/eval/google-gemma-3-4b-it.latest.human.txt

@@ -0,0 +1,67 @@
+model: google/gemma-3-4b-it
+eval summary: 7 cases | mean score 0.7982 | parse_ok 6/7 | typecheck_ok 6/7
+
+════════════════════════════════════════════════════════════════════════
+Pipeline failures (parse/typecheck never succeeded): 1
+
+▸ tv-07  final_score=0.0000  semantic=0.000
+  goal: Web search for 'rust async' but return only titles and URLs in the result list
+  rounds=2  recovered=false  pipeline_score=0.00
+  ─── attempt 1 ───
+    step 0: ExtractResult{query="rust async", ~str}
+      reason: Search for 'rust async' using full-text search and retrieve relevant ExtractResult entities.
+    validation: FAILED
+      • [parse] step 0 `ExtractResult{query="rust async", ~str}`
+        Fix spelling so identifiers, `=`, `{{}}`, `.`, and parentheses match the SYNTAX block in the prompt.
+        span_offset: 34
+  ─── attempt 2 ───
+    step 0: ExtractResult{query="rust async", ~str}
+      reason: Search for 'rust async' using full-text search and retrieve relevant ExtractResult entities.
+    correction_context_in (feedback from prior round, sent to LLM):
+      {
+        "round": 0,
+        "goal": "Web search for 'rust async' but return only titles and URLs in the result list",
+        "previous_steps": [
+          {
+            "text": "ExtractResult{query=\"rust async\", ~str}",
+            "reasoning": "Search for 'rust async' using full-text search and retrieve relevant ExtractResult entities."
+          }
+        ],
+        "diagnostics": [
+          {
+            "step_index": 0,
+            "expression": "ExtractResult{query=\"rust async\", ~str}",
+            "error": {
+              "correction": "Fix spelling so identifiers, `=`, `{{}}`, `.`, and parentheses match the SYNTAX block in the prompt.",
+              "category": "parse",
+              "span_offset": 34
+            }
+          }
+        ]
+      }
+    validation: FAILED
+      • [parse] step 0 `ExtractResult{query="rust async", ~str}`
+        Fix spelling so identifiers, `=`, `{{}}`, `.`, and parentheses match the SYNTAX block in the prompt.
+        span_offset: 34
+
+
+Expectation gaps (validated, soft score below 1.0): 2
+
+▸ tv-01  blended_score=0.7750  semantic=0.750
+  goal: Research briefing: what are the main risks of LLM prompt injection in 2025?
+  expectation notes:
+    - entities got {"ResearchTask"} want any of ["SearchResult"]
+  final plan (for context):
+    step 0: ResearchTask{query="main risks of LLM prompt injection in 2025"}
+      reason: Retrieve ResearchTasks related to the specified query to initiate the research.
+
+▸ tv-03  blended_score=0.8125  semantic=0.750
+  goal: Crawl the product marketing site up to depth 2 for a competitive summary
+  expectation notes:
+    - entities got {"ResearchTask"} want any of ["ExtractResult"]
+  final plan (for context):
+    step 0: ResearchTask{scope=Source(id), filter=marketing}
+      reason: Start by finding ResearchTasks specifically related to marketing sources.
+
+════════════════════════════════════════════════════════════════════════
+