Drive image-detail clamping from resolved model compat instead of a
provider hardcode, clamp input_image only on known paths, and skip
custom-tool adaptation when freeform is supported.
Seed supportsImageDetailOriginal=false for curated and dynamic xai-oauth
compat, and set the same flag on the eight bundled models.json entries
without regenerating the rest of the catalog.
Fixes#5002
- Instruct the advisor to stop policing scope, ambition, or backwards compatibility unless explicitly requested by the user.
- Adjust the blocker criteria to require explicit contradictions of user instructions rather than subjective assessments of refactor size or scope.
- Added `gpt-5.6-luna`, `gpt-5.6-sol`, and `gpt-5.6-terra` variants for the `opencode-zen` provider.
- Removed deprecated `*-pro` model aliases from the `openai-codex` provider in `models.json`.
- Updated `openai-compat.ts` to restrict pro-reasoning alias generation to the `openai` provider only.
- Adjusted various model `contextWindow`, `maxTokens`, and `cost` parameters to reflect latest upstream metadata.
- Added `perplexity-academic-researcher` model definition.
Recognized SAP AI Core hai-proxy Claude ids in claude-<version>-<kind> order so Anthropic thinking and capability inference stay on the adaptive path.
Fixes#5069
Treat GitHub Copilot discovery input as authoritative during model merges so explicit supports.vision=false is not OR-upgraded from bundled references.
Fixes#4779
- Transitioned DeepSeek models to an explicit `[High, Max]` effort ladder, removing stale alias maps.
- Updated the OpenAI compatibility layer to enforce authoritative `supportsReasoningEffort` and `omitReasoningEffort` flags.
- Synchronized `models.json` definitions to reflect accurate reasoning effort capabilities across the catalog.
- Introduced `Max` as a first-class reasoning effort tier across all packages, including AI providers, coding agent configurations, and RPC protocols.
- Refactored model effort ladders to use wire-exact mappings and removed legacy effort aliasing (e.g., `max-to-xhigh` mapping).
- Updated model registry and provider configurations to support `Max` tier routing, color themes, and UI icon associations.
- Expanded test suites to provide end-to-end coverage for the new reasoning tier, including updated compatibility and fallback scenarios.
- Corrected Novita pricing from ten-thousandths of a dollar per million tokens.
- Validated pasted keys against the authenticated balance endpoint.
- Made live discovery authoritative and excluded models without positive output limits.
- Enabled Codex Responses Lite for GPT-5.6 models by integrating model discovery flags and wire contract updates.
- Implemented request transformations for streaming and remote compaction, including header injection and image detail stripping.
- Introduced sequential-cutoff logic and atomic reasoning summary events for concurrent stream processing.
- Added comprehensive test suites to validate remote compaction, image handling, and reasoning summary delivery.
- Suppressed `reasoning.summary` for xai-oauth Responses requests while preserving other Responses providers' summary defaults.
- Added regression coverage for the `xai-oauth/grok-4.5` reasoning payload and regenerated the bundled catalog entry for its effort dial.
Fixes#4998
- Introduced `getOpenAIPromptCacheKey` to provide a unified identity resolution for both cache keys and affinity headers.
- Enabled `x-grok-conv-id` header support in the OpenAI completions provider for models configured with cache affinity.
- Added comprehensive tests to verify cache affinity header behavior across varied session and cache configuration states.
- Enabled OpenAI pro reasoning mode by integrating reasoning aliases and parameter injection.
- Expanded the model catalog with GPT-5.6 Luna, Sol, Terra, and Meta Muse Spark 1.1.
- Updated model type definitions and provider request transformers to support reasoning configurations.
- Refined model generation scripts to include new pro-reasoning aliases for OpenAI providers.
- Added auto-sealing logic to `FinalizableBlock` to finalize displaceable snapshots when they enter the scrollback area.
- Updated TUI frame emission to publish committed rows and clamp them to segment bounds, ensuring accurate component updates.
- Introduced component tracking and cleanup in event controller tests to prevent resource leaks during finalization.
- Validated state transitions and post-emit synchronization through comprehensive new test suites for transcript and TUI components.
- Added support for GPT-5.6 (Luna, Sol, Terra) models including configuration updates and context window values.
- Implemented automatic effort tier remapping for wire-effort models to ensure proper translation between user-facing tiers and provider requirements.
- Updated Codex request transformers to handle effort shifting and added validation for reasoning configurations.
- Collapsed Devin-specific model variants to unify logical model handling and added comprehensive test coverage for effort resolution.
Cursor GetUsableModels carries no per-model modality metadata; the
reference-less fallback in normalizeCursorModel hardcoded input:
["text"], classifying multimodal families (claude/gpt/codex/gemini) as
vision-blind, so attached images were silently replaced by text
descriptions. Infer modalities from the model family instead, mirroring
inferInputFromGeminiId in discovery/gemini.ts. Bundled references stay
authoritative and text-only families (composer-*, grok-code-*) keep
["text"].
Fixes#4726
Built-in model discovery admitted providers via peekApiKey, which
deliberately never refreshes OAuth rows, so a provider whose only stored
credential was an expired OAuth token was silently dropped from online
discovery and its token was never rotated (model selector 'refresh'
stayed empty for logged-in users).
Resolve built-in discovery keys through an online-only preflight that
refreshes an expired stored OAuth credential, applying the disabled/
configured/targeted provider filters before the side-effecting
resolution so refreshProvider(x) cannot rotate unrelated credentials.
Offline discovery stays peek-only. Under online-if-uncached the
preflight consults the same cache freshness the model manager uses
(2h default TTL, 5min non-authoritative retry) so tokens refresh
exactly when the manager will fetch — a fresh cache never triggers a
token-endpoint call.
Adopted from PR #4896 with two amendments: dropped an unrelated
workflow-notice.md prompt edit, and aligned the preflight cache TTL
with the manager's real 2h default (was 24h, which skipped the refresh
on the common startup path for caches aged 2-24h; regression covered
by the new online-if-uncached tests). Also corrected the stale
'Default: 24h' doc on cacheTtlMs in the catalog.
Fixes#4893
Co-authored-by: roboomp <omp@can.ac>
can1357