reasoning Static interface comparison

OrcaRouter

1.1.3 1.1.4

PASSAutomated static analysis

No policy-significant interface change detected.

View the upgrade review as Markdown

A shareable summary of this comparison for an issue, pull request or ticket. Select the text and copy it.

Tools4 → 4
Added0
Removed0
Schema changes0
Input schema changes0
Output schema changes0
Unclassified schema changes0
Description changes4
New write authority0
New destructive authority0
New unknown authority0
AnalysisPASS

INTERFACE DIFF

What changed, tool by tool

Classification from the recorded findings · definitions from the published snapshots

4 tools with recorded changes

  1. orcarouter_chatModifiedFindingDescriptionMetadataINFO

    What changed

    • orcarouter_chat: declared effect unknown → write.
    • orcarouter_chat: description changed.
    • orcarouter_chat: declared metadata changed (title "" → "OrcaRouter Chat"; declared idempotent: unknown → false; declared open_world: unknown → true).

    Why it could matter

    • See the full evidence for this finding.
    • Models choose and call tools partly from their descriptions.
    • Annotations such as idempotent or open-world hints can inform how clients treat a tool.

    What to verify

    • Review the recorded finding in the published comparison.
    • Spot-check that agents still select this tool as intended.
    • Confirm any client logic that relies on these annotations.
    Declared effect
    unknown → write
    Description
    PreviousSend a single-turn chat request to OrcaRouter. Default model is the workspace's auto-router. Use `orcarouter/<name>` for other routers or `<provider>/<model>` for direct calls. For OpenAI reasoning models (gpt-5/o1/o3/...), max_tokens is automatically routed to max_completion_tokens at the wire level.
    CurrentSend a single-turn chat request to OrcaRouter and return the assistant's response text. Default model is the workspace's auto-router. Use `orcarouter/<name>` for other routers or `<provider>/<model>` for direct calls. For OpenAI reasoning models (gpt-5/o1/o3/...), max_tokens is automatically routed to max_completion_tokens at the wire level. The optional `models` array sets a fallback chain — the primary `model` is tried first, then each entry on failure (5 entries total max, including the primary). Errors are returned as text content with isError:true; common cases include missing API key, rate limits, and upstream provider outages. Requires ORCAROUTER_API_KEY.

    Input schema

    Input schema unchanged.

    8 unchanged entries
    • (schema root)
    • max_tokens
    • model
    • models
    • models › [items]
    • prompt
    • system_prompt
    • temperature

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
  2. orcarouter_model_cardModifiedFindingDescriptionMetadataINFO

    What changed

    • orcarouter_model_card: declared effect unknown → read.
    • orcarouter_model_card: description changed.
    • orcarouter_model_card: declared metadata changed (title "" → "OrcaRouter Model Card"; declared idempotent: unknown → true; declared open_world: unknown → true).

    Why it could matter

    • See the full evidence for this finding.
    • Models choose and call tools partly from their descriptions.
    • Annotations such as idempotent or open-world hints can inform how clients treat a tool.

    What to verify

    • Review the recorded finding in the published comparison.
    • Spot-check that agents still select this tool as intended.
    • Confirm any client logic that relies on these annotations.
    Declared effect
    unknown → read
    Description
    PreviousGet detailed information about a single model: pricing, context window, supported endpoints, latency.
    CurrentGet detailed information about a single model — display name, long description, pricing (per-call and per-million tokens), context window, max output, modalities (input/output), supported endpoints, latency percentiles (p50/p95), and release date. Use this when you already know the model id and want full details; for browsing or filtering across many models use orcarouter_models_list instead. Returns isError:true with a clear hint when the id is not found. Read-only, no API key required.

    Input schema

    Input schema unchanged.

    2 unchanged entries
    • (schema root)
    • model

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
  3. orcarouter_models_listModifiedFindingDescriptionMetadataINFO

    What changed

    • orcarouter_models_list: declared effect unknown → read.
    • orcarouter_models_list: description changed.
    • orcarouter_models_list: declared metadata changed (title "" → "Browse OrcaRouter Models"; declared idempotent: unknown → true; declared open_world: unknown → true).

    Why it could matter

    • See the full evidence for this finding.
    • Models choose and call tools partly from their descriptions.
    • Annotations such as idempotent or open-world hints can inform how clients treat a tool.

    What to verify

    • Review the recorded finding in the published comparison.
    • Spot-check that agents still select this tool as intended.
    • Confirm any client logic that relies on these annotations.
    Declared effect
    unknown → read
    Description
    PreviousList available LLM models. Filter by provider, capability, or minimum context length — filters are applied server-side by the OrcaRouter backend.
    CurrentList LLM models in the OrcaRouter catalog. Each entry includes id, name, description, owned_by, context_length, supported_endpoint_types, and pricing (both per-token and per-million tokens). Filter by `provider`, `capability`, or `min_context` — filters compose (all conditions must match) and are applied server-side. Discover valid provider ids first with orcarouter_providers_list. Returns the full catalog when called without filters. Read-only, no API key required.

    Input schema

    Input schema unchanged.

    4 unchanged entries
    • (schema root)
    • capability
    • min_context
    • provider

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
  4. orcarouter_providers_listModifiedFindingDescriptionMetadataINFO

    What changed

    • orcarouter_providers_list: declared effect unknown → read.
    • orcarouter_providers_list: description changed.
    • orcarouter_providers_list: declared metadata changed (title "" → "List OrcaRouter Providers"; declared idempotent: unknown → true; declared open_world: unknown → true).

    Why it could matter

    • See the full evidence for this finding.
    • Models choose and call tools partly from their descriptions.
    • Annotations such as idempotent or open-world hints can inform how clients treat a tool.

    What to verify

    • Review the recorded finding in the published comparison.
    • Spot-check that agents still select this tool as intended.
    • Confirm any client logic that relies on these annotations.
    Declared effect
    unknown → read
    Description
    PreviousList all model providers on OrcaRouter with their model counts and display metadata. Works without an API key. Useful for discovering provider ids (e.g. 'openai', 'anthropic') to pass to orcarouter_models_list as the `provider` filter.
    CurrentList all model providers on OrcaRouter with their `provider_id`, human-readable `display_name`, `icon_url`, and `model_count`. Call this first to discover valid provider ids (e.g. 'openai', 'anthropic', 'google', 'qwen', 'deepseek') which you can then pass to orcarouter_models_list as the `provider` filter. Takes no parameters and returns the same list on every call until the deployment's catalog changes. Read-only, no API key required.

    Input schema

    Input schema unchanged.

    1 unchanged entry
    • (schema root)

    No output schema is recorded for this tool in either release.

    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool

Evidence and provenance

Static findings
PASS from Modelara’s automated analysis of the two declared interfaces. A policy outcome, not a security rating or a runtime test.
Human review
Automated static analysis. No reviewer decision is recorded for this comparison.
Published evidence
Part of Valyd’s published data generation listed in valyd-data-source.json. Published records are not rewritten.
Show provenance and exact files
Comparison
continuum-ai-corp-orcarouter-mcp/1.1.3~1.1.4The published comparison identifier.
Analyzer
modelara v0.1.8Policy version not recorded.Analyzed Nov 16, 2026, 10:47 PM UTC.
Distribution
npm
Previous release
@orcarouter/mcp@1.1.34 tools · published by the registry May 25, 2026, 4:20 AM UTCArtifact integritysha512-XS/uPHfzYvTU2qcfctyQy3Kn4W1samMZD5yW48hk7Mbgj9oVsrP5zXCDJHWVyXNl1+9tXZDaIgH3ciCTTRLJsg==Interface fingerprintsha256:6ba7a24411619040ad3710a25b330c1d7a94ab8875f6635aa95814d9a01d6f11Exact interface snapshot (JSON)
Current release
@orcarouter/mcp@1.1.44 tools · published by the registry May 26, 2026, 8:47 AM UTCArtifact integritysha512-0EGwysaiM9OYtf8ysiA8RYDA3HgrqgKz1pOMmpECvHKB/HaTSpUppiNMYkZdfjaMi0bZxseOhhoxE6mT18N1gw==Interface fingerprintsha256:a4c5d693ba153da3dd422b307990398ed880bb233ed750829e87ae2548b77f14Exact interface snapshot (JSON)

The integrity value or digest identifies the exact artifact that was inspected; it does not show that the package is safe. The interface fingerprint identifies the declared tools and schemas Modelara recorded for that release.

MODELARA ANALYSIS OUTPUT

Interface findings

Analyzed with Modelara v0.1.8 · Nov 16, 2026

Informational

12 findings
  • orcarouter_chatINFOChanged

    Declared effect unknown → write

    Authority
    UNKNOWNWRITE
  • orcarouter_model_cardINFOChanged

    Declared effect unknown → read

    Authority
    UNKNOWNREAD
  • orcarouter_models_listINFOChanged

    Declared effect unknown → read

    Authority
    UNKNOWNREAD
  • orcarouter_providers_listINFOChanged

    Declared effect unknown → read

    Authority
    UNKNOWNREAD
  • orcarouter_chatINFOChanged

    Description changed

    Authority
    UNKNOWNWRITE
  • orcarouter_model_cardINFOChanged

    Description changed

    Authority
    UNKNOWNREAD
  • orcarouter_models_listINFOChanged

    Description changed

    Authority
    UNKNOWNREAD
  • orcarouter_providers_listINFOChanged

    Description changed

    Authority
    UNKNOWNREAD
  • orcarouter_chatINFOChanged

    Metadata changed

    Show details
    • title "" → "OrcaRouter Chat"
    • declared idempotent: unknown → false
    • declared open_world: unknown → true
    Authority
    UNKNOWNWRITE
  • orcarouter_model_cardINFOChanged

    Metadata changed

    Show details
    • title "" → "OrcaRouter Model Card"
    • declared idempotent: unknown → true
    • declared open_world: unknown → true
    Authority
    UNKNOWNREAD
  • orcarouter_models_listINFOChanged

    Metadata changed

    Show details
    • title "" → "Browse OrcaRouter Models"
    • declared idempotent: unknown → true
    • declared open_world: unknown → true
    Authority
    UNKNOWNREAD
  • orcarouter_providers_listINFOChanged

    Metadata changed

    Show details
    • title "" → "List OrcaRouter Providers"
    • declared idempotent: unknown → true
    • declared open_world: unknown → true
    Authority
    UNKNOWNREAD
What do these results mean?
PASS
No policy-significant interface change detected.
REVIEW
Interface changes require inspection.
FAIL
A policy-significant change was detected.
INVALID
The comparison could not be evaluated reliably.
← Back to OrcaRouter release history