- Updated the migration test to assert that legacy cached models are invalidated rather than preserved.
- Verified that subsequent model discovery writes fresh models correctly after invalidation.
- Added a check to omit the `reasoning.summary` parameter on OpenAI Codex models older than version 5.4.
- Introduced `supportsCodexReasoningSummary` in the catalog package to identify compatible model versions.
- Added comprehensive unit tests validating correct parameter inclusion and suppression across models.
Replace the v2->current version UPDATE with a DELETE that clears every row not matching the active schema, so cache-schema bumps actually invalidate stale entries (including pre-V2 Codex rows that still lack remoteCompaction.v2StreamingEnabled).
Fixes#4146
Bump the model cache schema so fresh authoritative OpenAI Codex rows written before V2 remote compaction metadata are ignored and refreshed.
Add coverage for legacy cache rows that would otherwise skip Codex discovery and keep the legacy compaction path.
Fixes#4146
Add provider-native V2 remote compaction metadata to discovered OpenAI Codex models so context-full compaction uses the streaming compaction_trigger path instead of the legacy compact endpoint.
Expose the V2 remote compaction schema fields in models.yml and cover the Codex discovery metadata contract.
Fixes#4146
- Preserved Unicode letters, marks, and numbers during fuzzy-search normalization so CJK and other non-ASCII queries no longer collapse to match-all searches.
- Added regression coverage for Chinese fuzzy filtering against unrelated ASCII items.
Fixes#4114
AGENTS.md forbids inline `await import()` — move `fs`, `path`, and `prompt`
to top-level namespace/named imports. The `prompt-templates` module import
already registers the Handlebars helper as a side-effect, so the render
calls still resolve the new `renderYieldSchema` helper.
Cleared frozen-prefix render state after full-lex renders cannot establish a current appendable prefix, preventing truncated transient text from reusing spacer lines produced with a former tail.
Added regression coverage for truncating back to a previously frozen prefix.
Fixes#3975
- Updated exact substring match assertions to use word-boundary regular expressions.
- Prevents false-positive test failures when target strings overlap with other generated text.
- Improved the leaked-thinking stream projector to clone and sync native tool-call blocks directly.
- Eliminated the need for placeholder IDs and complex rekeying logic in the event controller and argument reveal module.
- Simplified native tool-call validation in owned-stream processing by requiring only a non-empty name.
- Added comprehensive unit tests to ensure tool-call IDs and partial JSON parameters remain intact during healing.
- Removed the canonical model variant indexing, selection, and tracking logic from the model registry and resolver.
- Eliminated the `canonical` sub-command, tab view, search tokens, and equivalence configuration structures from the CLI and model selector components.
- Refined model identification, lookup, and provider fallback resolution to bind exclusively to standard, raw model IDs.
- Relocated the equivalence utility script within the catalog package to support script-only policy generation.
Preserved the referenced model's OpenAI-compatible reasoning-effort support when openai-models-list discovery enriches a thin /v1/models payload. The discovered model still keeps conservative proxy-local store and developer-role defaults, but known reasoning models like gpt-5 no longer force supportsReasoningEffort false and trigger the omitReasoningEffort request path.
Added a regression assertion that a thin proxied gpt-5 keeps supportsReasoningEffort true and omitReasoningEffort false after reference enrichment.
Fixes#3983
Thin OpenAI-compatible proxies that omit context_length / max_model_len on
/v1/models made every discovered model fall back to
DISCOVERY_DEFAULT_CONTEXT_WINDOW (128K/33K), even when the id matched a
bundled model with a much larger intrinsic window. discoverProxyModels
and discoverLiteLLMModels already resolve ids against the bundled
reference index; discoverOpenAIModelsList (which also backs lm-studio
discovery) now does the same.
Behavior:
- Build the reference index once outside the loop and resolve each item
via resolveModelReference().
- contextWindow precedence keeps provider-reported values authoritative:
item.max_model_len ?? item.context_length ?? nativeMetadata?.contextWindow
?? reference?.contextWindow ?? DISCOVERY_DEFAULT_CONTEXT_WINDOW.
- maxTokens uses reference?.maxTokens when available, otherwise the
api-specific discovery default, capped at contextWindow so a bundled
ref for a larger sibling can never over-request output tokens.
- name / reasoning / thinking / input inherit from the reference; native
lm-studio metadata still wins for input modality.
- Provider-specific baseUrl, headers, and local-unknown cost stay local.
- OpenAI-compat flags stay conservative (supportsStore / supportsDeveloperRole
/ supportsReasoningEffort all false) to match the proxy sibling.
Also updated two pre-existing regression tests that used
deepseek-v4-pro / deepseek-r1 / DeepSeek-V4-Flash as stand-in "fictional"
ids to exercise the default-fallback branch. Those model names have since
been added to the bundled catalog, so the tests were renamed to
vllm-lab-fork-* ids that unambiguously miss the reference index while
preserving each test's original default-fallback intent.
Fixes#3983
Added a cross-turn tool-call loop guard that hashes canonical tool names and arguments, ignores intent metadata, and injects a hidden redirect when identical calls reach the configured threshold.
Fixes#3971
- Introduced an `#editVariantCache` to memoize resolved edit modes for model variants.
- Replaced the generic `shallowStringRecord` helper with specialized, type-safe parsing methods for model variants and roles.
- Invalidated the cached edit variants during settings rebuilds and verified correct cache refreshment across project directories.
- Moved Streamable HTTP request and notify timeout cleanup after response body consumption.\n- Added regression coverage for stalled request JSON bodies and stalled notify error bodies.\n\nFixes #3974
can1357