Skip to content

0.1.8 Beta5: Run the full maintained K2.7 Code Provider regression #276

Open

Description

@NOirBRight

Parent

#351 (part of #248)

Outcome

Run the full maintained-Provider regression for the Ollama Cloud K2.7 Code configuration against every generic Responses capability shipped in Beta2 through Beta4.

This is independent maintenance evidence for a bundled Provider configuration. It does not inherit GLM results, select production behavior, or restrict user-configured endpoints.

Required coverage

  • Beta2: exact route identity; native/adapt/omit/required-unavailable behavior; standard functions; namespace/custom structural mapping; hosted-tool omission; V1/V2 isolation; no cross-Provider proxy.
  • Beta3: complete client-executed tool_search and reversible Code Mode workflows.
  • Beta4: complete client-owned Collaboration V2 lifecycle and user-owned agent configuration safety.
  • Retained Beta1 continuation, context-window, visibility, catalog ownership, and identity regressions.

Acceptance criteria

  • Streaming/non-streaming text, multi-turn history, standard function calls/results/replay, and stable terminal/error behavior complete through the real CLI.
  • Every Beta2 structural disposition relevant to the route is exercised.
  • Client tool_search, Code Mode, and Collaboration V2 complete through the same generic production implementation.
  • Optional unsupported hosted tools are absent; a required unavailable hosted tool fails before sampling.
  • Exact Provider/model identity remains unchanged across turns, reconnect, adaptation, and permitted retry.
  • No request reaches Official/OpenAI or another Provider to execute a tool.
  • K2.7 evidence is independent from GLM evidence.
  • Failures distinguish upstream model behavior, maintained configuration, and generic CodexHub defects.
  • A regression failure must not be fixed by adding a K2.7-specific tool codec or routing branch.
  • Evidence is bounded and bound to exact candidate SHA, CLI version, Provider/model/protocol, and catalog identity.

Out of scope

  • Chat Completions, which remains Beta6.
  • Turning the regression result into a runtime model allowlist or public claim that only this model is supported.

Blocked by

Activity

  1. added
    enhancementNew feature or request
    ready-for-agentFully specified, ready for an AFK agent
    wayfinder:taskWayfinder implementation task
    tier:heavyOrchestrator provider tier: heavy
    P1Priority 1: current iteration goal
    on Jul 31, 2026
  2. changed the title [-]0.1.8 Beta1: Qualify K2.7 Code core Responses end to end[/-] [+]0.1.8 Beta2: Qualify K2.7 Code core Responses end to end[/+] on Aug 1, 2026
  3. changed the title [-]0.1.8 Beta2: Qualify K2.7 Code core Responses end to end[/-] [+]0.1.8 Beta3: Regression-test the maintained Ollama Cloud K2.7 Code Provider[/+] on Aug 4, 2026
  4. changed the title [-]0.1.8 Beta3: Regression-test the maintained Ollama Cloud K2.7 Code Provider[/-] [+]0.1.8 Beta5: Run the full maintained K2.7 Code Provider regression[/+] on Aug 4, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    P1Priority 1: current iteration goalcampaign:0.1.8-beta50.1.8 Beta5 maintained-Provider regression campaignenhancementNew feature or requestready-for-agentFully specified, ready for an AFK agenttier:heavyOrchestrator provider tier: heavywayfinder:taskWayfinder implementation task

    Projects

    No projects

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions