chore: update changelogs
This commit is contained in:
can1357
@@ -4,12 +4,12 @@
|
||||
|
||||
### Added
|
||||
|
||||
- Added `ThinkingLevel.Max` ("max") above `xhigh`, mapping to the catalog `Effort.Max` tier.
|
||||
- Added the `ThinkingLevel.Max` ("max") configuration option, mapping to the `Effort.Max` tier for supported models.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed remote compaction for Codex Responses Lite models (GPT-5.6 family): both the V1 `/responses/compact` request and the V2 `compaction_trigger` stream now apply the lite rewrite (instructions as an input item, no top-level `instructions`/`tools`, `all_turns` reasoning replay on V2) and send the `x-openai-internal-codex-responses-lite` header, matching codex-rs routing compaction through `build_responses_request`.
|
||||
- Fixed aborted tool-result hooks from continuing into another provider call before the abort settled. ([#4963](https://github.com/can1357/oh-my-pi/issues/4963))
|
||||
- Fixed remote compaction behavior for Codex Responses Lite (GPT-5.6 family) models across both V1 and V2 endpoints to ensure correct formatting and routing.
|
||||
- Fixed an issue where aborted tool-result hooks could trigger subsequent provider calls before the abort signal fully settled.
|
||||
|
||||
## [16.3.12] - 2026-07-08
|
||||
|
||||
|
||||
+10
-21
@@ -4,33 +4,22 @@
|
||||
|
||||
### Added
|
||||
|
||||
- Added `max` as a first-class reasoning effort option across providers and wire schemas
|
||||
- Updated `max` reasoning budget to 32768 tokens across all provider budget tables
|
||||
|
||||
- Added model-driven Codex Responses Lite: `responsesLite` now defaults to the catalog `useResponsesLite` flag (codex-rs `use_responses_lite`, set on the GPT-5.6 family), so lite requests are sent without per-call opt-in.
|
||||
- Added the full Responses Lite wire contract: lite requests move tools into a leading `{type: "additional_tools", role: "developer"}` input item and the base instructions into a developer message, omit top-level `instructions`/`tools`, and force `parallel_tool_calls: false`, mirroring codex-rs `build_responses_request`.
|
||||
- Added concurrent reasoning summaries on Codex Responses: requests with a reasoning summary send `stream_options: { reasoning_summary_delivery: "sequential_cutoff" }`, and the stream decoder consumes the matching atomic `response.reasoning_summary_text.done` events (resolved by `item_id`/`output_index`, stale dones dropped, incremental `.delta`/`.part.*` events ignored under the cutoff contract). The cutoff gate reads the post-`onPayload` wire body on both transports, and `response.reasoning_summary_text.done` now counts as websocket watchdog progress.
|
||||
- Added Novita API-key login with authenticated key validation and `NOVITA_API_KEY` discovery ([#4917](https://github.com/can1357/oh-my-pi/pull/4917) by [@jason-wu-ai](https://github.com/jason-wu-ai)).
|
||||
- Added `"max"` as a first-class reasoning effort across provider options, wire types (`reasoning_effort`/`reasoning.effort`), server intake guards, and the Codex request transformer; user `max` now serializes 1:1 to the provider `max` tier instead of being reachable only through the retired shifted effort maps. Inbound Anthropic gateway requests now map `output_config.effort` onto `options.reasoning`.
|
||||
- Added "max" as a first-class reasoning effort option across providers (including Anthropic, Google, Bedrock, and OpenAI), supporting a maximum reasoning budget of 32,768 tokens.
|
||||
- Added and standardized the "Responses Lite" wire contract and transport, enabling automatic activation via model-level catalog flags, moving tools and instructions into developer input items, disabling parallel tool calls, and stripping image detail instead of falling back to the full transport.
|
||||
- Added support for concurrent reasoning summaries on Codex Responses using the sequential-cutoff streaming contract.
|
||||
- Added Novita API-key login with authenticated key validation and automatic NOVITA_API_KEY environment variable discovery.
|
||||
|
||||
### Changed
|
||||
|
||||
- Refactored Responses Lite transport to move tools and instructions into input items
|
||||
- Updated Responses Lite to force parallel tool calling off and strip image detail
|
||||
- Standardized Responses Lite activation via model-level catalog flags
|
||||
- Recognized Pro Lite as a paid plan tier for OpenAI Codex models
|
||||
- Changed Responses Lite image handling to match current codex-rs: a lite request containing input images now stays on the lite transport with image `detail` stripped, instead of silently falling back to the full Responses shape.
|
||||
- Changed effort budget tables (`ANTHROPIC_THINKING`, `GOOGLE_THINKING`, `BEDROCK_CLAUDE_THINKING`, Bedrock `defaultBudgets`) to carry a `max` row (32768), and `getGoogleBudget` to resolve `max` to the largest bucket explicitly.
|
||||
- Recognized Pro Lite as a paid plan tier for OpenAI Codex models.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed xAI SuperGrok multi-account rotation when an account returns HTTP 403 `run out of credits` / `personal-team-blocked:spending-limit`. That account-local cap is now classified as a usage limit so `streamSimple` auth-retry and `rotateSessionCredential` switch to a sibling `xai-oauth` credential instead of sticking to the exhausted account.
|
||||
- Fixed concurrent reasoning summaries to ignore legacy streaming events under cutoff contract
|
||||
- Fixed sequential-cutoff Codex reasoning summaries repeating earlier content when atomic summary snapshots are replayed or extended.
|
||||
- Fixed error classification for typed AWS credential-resolution failures (`AwsCredentialsError`) to map them to authentication failures. ([#5030](https://github.com/can1357/oh-my-pi/pull/5030) by [@usr-bin-roygbiv](https://github.com/usr-bin-roygbiv))
|
||||
- Fixed OpenAI-compatible chat-completions streams preserving vLLM-style trailing cached-token usage chunks so `cacheRead` and billable `input` session stats are accurate ([#5022](https://github.com/can1357/oh-my-pi/issues/5022)).
|
||||
- Fixed `xai-oauth/grok-4.5` Responses requests to omit unsupported `reasoning.summary` while preserving the documented `reasoning.effort` payload ([#4998](https://github.com/can1357/oh-my-pi/issues/4998)).
|
||||
- Fixed Codex OAuth credential selection to re-check blocked accounts during ranking and clear stale usage-limit blocks when live usage shows all reported windows recovered ([#4980](https://github.com/can1357/oh-my-pi/issues/4980)).
|
||||
- Fixed xAI SuperGrok multi-account rotation to correctly treat HTTP 403 credit exhaustion and spending limit errors as usage limits, triggering a credential rotation to a sibling account.
|
||||
- Fixed error classification for AWS credential-resolution failures (AwsCredentialsError) to correctly map them as authentication failures.
|
||||
- Fixed OpenAI-compatible chat-completions streams to preserve vLLM-style trailing cached-token usage chunks, ensuring accurate cacheRead and billable input session statistics.
|
||||
- Fixed xai-oauth/grok-4.5 Responses requests to omit the unsupported reasoning.summary field while preserving the reasoning.effort payload.
|
||||
- Fixed Codex OAuth credential selection to re-check blocked accounts during ranking and clear stale usage-limit blocks once live usage indicates recovery.
|
||||
|
||||
## [16.3.15] - 2026-07-09
|
||||
|
||||
|
||||
@@ -2,25 +2,21 @@
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Breaking Changes
|
||||
|
||||
- Redesigned reasoning effort ladders to be wire-exact, removing the shifted five-tier effort mapping. Models now expose exactly the effort tiers their upstream APIs accept, mapped 1:1. Removed SHIFTED_FIVE_TIER_EFFORT_MAP, ANTHROPIC_ADAPTIVE_EFFORT_MAP_4_TIER, and per-host xhigh-to-max alias maps. Selecting an unsupported tier now automatically clamps down via clampThinkingLevelForModel. Devin effort routing is now mapped 1:1 onto per-tier siblings.
|
||||
|
||||
### Added
|
||||
|
||||
- Added Grok 4.5 model family
|
||||
- Added support for Dolphin Mistral 24b Venice Edition
|
||||
- Added GLM5.2-Fast model
|
||||
- Added Zenmux variants for GPT-5.6 (Luna, Sol, and Terra)
|
||||
- Added Novita as a model provider with authoritative public catalog discovery and generated pricing, limits, modality, reasoning, and tool metadata ([#4917](https://github.com/can1357/oh-my-pi/pull/4917) by [@jason-wu-ai](https://github.com/jason-wu-ai)).
|
||||
- Added `useResponsesLite` to `Model`/`ModelSpec` and Codex discovery parsing of the upstream `use_responses_lite` flag; regenerated `models.json` marks the GPT-5.6 family (`sol`/`terra`/`luna` and their pro aliases) for the Responses Lite transport. Added the `x-openai-internal-codex-responses-lite` marker to `OPENAI_HEADERS`.
|
||||
- Added `Effort.Max` ("max") as a first-class user-facing thinking level above `xhigh`.
|
||||
- Added support for new models: Grok 4.5 family, Dolphin Mistral 24b Venice Edition, GLM5.2-Fast, and Zenmux variants for GPT-5.6 (Luna, Sol, and Terra).
|
||||
- Added Novita as a model provider, including public catalog discovery, pricing, limits, modality, reasoning, and tool metadata.
|
||||
- Added useResponsesLite to Model and ModelSpec to support the Responses Lite transport, enabled by default for the GPT-5.6 family.
|
||||
- Added Effort.Max ("max") as a first-class user-facing thinking level above xhigh.
|
||||
|
||||
### Changed
|
||||
|
||||
- Standardized reasoning effort levels to use a wire-exact `max` tier across all model providers
|
||||
- Refactored Devin model routing to support 1:1 mapping for the `max` effort tier
|
||||
- Normalized stale Ollama model configurations to the new wire-exact effort ladder
|
||||
|
||||
- Updated costs and context windows for various models in the catalog
|
||||
- **Breaking**: Effort ladders are now wire-exact and the shifted five-tier effort mapping is gone. Models expose exactly the effort tiers their wire accepts, mapped 1:1: GPT-5.6+ and Anthropic adaptive models with a real xhigh tier (Opus 4.7+, Sonnet 5+, Fable/Mythos 5) expose `low..max`; legacy adaptive models (Opus 4.6 and all Bedrock adaptive) expose `low/medium/high/max`; Sonnet/Haiku 4.6 expose `low/medium/high`; GLM-5.2 on Z.ai/Zhipu/Umans/Ollama Cloud/Baseten and Sakana Fugu and DeepSeek expose `high/max`; local Ollama reasoning models expose `low/medium/high/max`; Fire Pass Kimi exposes `low..max` with distinct `xhigh` and `max` budgets. Removed `SHIFTED_FIVE_TIER_EFFORT_MAP`, `ANTHROPIC_ADAPTIVE_EFFORT_MAP_4_TIER`, and the per-host `xhigh -> "max"` alias maps; selecting a tier a model lacks clamps down via `clampThinkingLevelForModel`. Devin effort routing is now 1:1 onto per-tier siblings (`max -> -max`; families without a `-max` sibling top out at `xhigh`; the fake `minimal -> -low` fallback is gone). Regenerated `models.json`.
|
||||
- Changed `fillThinkingWireDefaults` to re-derive the effort map whenever the model-defined ladder disagrees with cached metadata, so stale cached surfaces from the shifted-map era normalize to the new wire-exact shape on every `buildModel`.
|
||||
- Standardized reasoning effort levels to use a wire-exact max tier across all model providers, including Devin routing and Ollama configurations.
|
||||
- Updated costs and context windows for various models in the catalog.
|
||||
|
||||
## [16.3.15] - 2026-07-09
|
||||
|
||||
|
||||
@@ -4,36 +4,27 @@
|
||||
|
||||
### Breaking Changes
|
||||
|
||||
- Renamed the bundled agent `explore` to `scout` (including renaming its configuration keys, prompt files, and task definitions). Any configurations, allowlists, or invocations referencing `explore` must now use `scout`.
|
||||
- Renamed the bundled agent explore to scout, including its configuration keys, prompt files, and task definitions. Any configurations, allowlists, or invocations referencing explore must now use scout.
|
||||
|
||||
### Added
|
||||
|
||||
- Added `max` as a native, first-class thinking tier for supported models
|
||||
- Added `thinkingBudgets.max` configuration setting
|
||||
- Updated terminal theme to support optional `thinkingMax` border color and icons
|
||||
|
||||
- Added a real `max` thinking level above `xhigh` with an optional `thinkingMax` theme border color (falls back to `thinkingXhigh`). `max` owns the top status-line icons (`◉` unicode, fire nerd-font, `[max]` ascii); the nerd-font preset uses an empty-to-full battery ramp for `minimal` through `xhigh` and shuffle while automatic effort is unresolved. `max` appears in cycling, selectors, `--thinking`, `:max` model suffixes, role scopes, settings, and completions on models that genuinely support it; on other models it clamps down like any unsupported tier.
|
||||
|
||||
### Changed
|
||||
|
||||
- Renamed the bundled agent `explore` to `scout` (including all internal references, prompt definitions, and task tool configurations). Any custom configurations or task invocations referencing `explore` must now use `scout`.
|
||||
- Changed `max` from a parse-time alias of `xhigh` to a distinct level everywhere (CLI flag, `:max` suffix, `defaultThinkingLevel`, ACP/RPC): the effort a model receives is now exactly the tier its wire supports, with no shifted remapping. Ultrathink now requests `max` (clamped per model); automatic thinking still tops out at `xhigh`. Added `thinkingBudgets.max` (default 32768).
|
||||
- Fixed collapsed compacted session transcript rebuilds reattaching snapcompact archive image frames to the live TUI, avoiding large retained JSC heaps on resume and transcript refresh. ([#4979](https://github.com/can1357/oh-my-pi/issues/4979))
|
||||
- Added a native, first-class max thinking tier for supported models, including a new thinkingBudgets.max configuration setting, support in CLI flags (--thinking, :max model suffixes), and terminal theme customization (thinkingMax border color and icons).
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed interactive TUI sessions dying with `Unhandled rejection: Cannot set cwd while another same-realm JS runtime is running` after the JS eval worker fell back to the in-process inline path (commonly when the worker could not load `pi_natives`). Concurrent inline eval/browser runtimes now stamp cwd (including the saved `__omp_session__` state) without stealing the exclusive realm, WorkerCore `init` reports failures via `init-failed` instead of throwing out of the microtask path, and constructing a runtime while another same-realm run is live fails explicitly instead of clobbering its globals. ([#4907](https://github.com/can1357/oh-my-pi/pull/4907) by [@cexll](https://github.com/cexll))
|
||||
- Fixed compaction aborting instead of trying an authenticated fallback model when Amazon Bedrock credential resolution fails before a request is sent. ([#5030](https://github.com/can1357/oh-my-pi/pull/5030) by [@usr-bin-roygbiv](https://github.com/usr-bin-roygbiv))
|
||||
- Fixed full-context forks cold-missing OpenAI prompt caches by persisting an inherited provider prompt-cache key separately from the new OMP session id, adding `--prompt-cache-key` for explicit cache affinity, and dropping automatic inheritance when startup changes the model, thinking level, system prompt, or tool schema. ([#5035](https://github.com/can1357/oh-my-pi/issues/5035))
|
||||
- Fixed Codex advisor requests using local `-advisor` session labels as provider session IDs; advisors now use stable UUIDv7 provider identities while keeping labeled transcript names. ([#5040](https://github.com/can1357/oh-my-pi/issues/5040))
|
||||
- Fixed macOS stdio MCP servers launching in a detached session, so `xcrun mcpbridge` can trigger the TCC Apple Events permission prompt and complete startup. ([#4987](https://github.com/can1357/oh-my-pi/issues/4987))
|
||||
- Fixed the ask tool timeout so it auto-selects the recommended option even when the UI selector does not settle on its own. ([#4995](https://github.com/can1357/oh-my-pi/issues/4995))
|
||||
- Fixed LSP workspace diagnostics for Go workspaces so roots with `go.work` are recognized and every `go.work use` module is included in the `go build` package patterns. ([#5038](https://github.com/can1357/oh-my-pi/issues/5038))
|
||||
- Fixed interactive OAuth login success messages waiting on model discovery; `/login xai-oauth` now reports saved credentials immediately while model metadata refreshes in the background. ([#4989](https://github.com/can1357/oh-my-pi/issues/4989))
|
||||
- Fixed Windows bash tool crashes when an explicit timeout fires while a piped command is still streaming output; the JavaScript fallback now reports the timeout without also aborting the native timeout signal. ([#5021](https://github.com/can1357/oh-my-pi/issues/5021))
|
||||
- Fixed subagent `yield` tool calls being discarded when the soft request budget hard-aborted the same assistant turn before the yield result event landed. ([#5006](https://github.com/can1357/oh-my-pi/issues/5006))
|
||||
- Fixed `--tools` filtering in interactive sessions disabling deferred MCP tools; MCP tools discovered from configured servers now stay active when the flag limits only built-in tools. ([#5013](https://github.com/can1357/oh-my-pi/issues/5013))
|
||||
- Fixed kept-alive task subagents entering a repeated provider-call loop after an IRC wake and terminal `yield`. ([#4963](https://github.com/can1357/oh-my-pi/issues/4963))
|
||||
- Fixed a memory leak (large retained JavaScriptCore heaps) in the TUI during session transcript rebuilds and refreshes by properly handling snapcompact archive image frames.
|
||||
- Fixed a crash in interactive TUI sessions (Cannot set cwd while another same-realm JS runtime is running) when the JS evaluation worker falls back to the in-process inline path.
|
||||
- Fixed compaction aborting when Amazon Bedrock credential resolution fails, ensuring it now falls back to trying an authenticated model.
|
||||
- Improved OpenAI prompt cache hit rates for full-context forks by persisting inherited provider prompt-cache keys separately from session IDs, and added a --prompt-cache-key flag for explicit cache affinity.
|
||||
- Fixed Codex advisor requests incorrectly using local session labels as provider session IDs, switching to stable UUIDv7 provider identities.
|
||||
- Fixed macOS stdio MCP servers launching in detached sessions, allowing tools like xcrun mcpbridge to successfully trigger TCC Apple Events permission prompts.
|
||||
- Fixed the ask tool timeout behavior to automatically select the recommended option if the UI selector does not settle.
|
||||
- Fixed LSP workspace diagnostics for Go workspaces to correctly recognize go.work roots and include all specified modules in go build package patterns.
|
||||
- Fixed interactive OAuth login (/login xai-oauth) delaying success messages; credentials are now reported immediately while model metadata refreshes in the background.
|
||||
- Fixed a crash in the Windows bash tool when a timeout occurs while a piped command is streaming output.
|
||||
- Fixed subagent yield tool calls being discarded when a soft request budget aborts the assistant turn before the yield event completes.
|
||||
- Fixed --tools filtering in interactive sessions incorrectly disabling deferred MCP tools from configured servers.
|
||||
- Fixed kept-alive task subagents entering infinite provider-call loops after an IRC wake and terminal yield.
|
||||
|
||||
## [16.3.15] - 2026-07-09
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed resume/session-replace and resize-settle full paints blanking the live viewport before replaying the transcript, preventing flicker on terminals without effective synchronized output ([#5028](https://github.com/can1357/oh-my-pi/issues/5028)).
|
||||
- Fixed terminal flickering during session resume, replacement, or resizing on terminals that do not support synchronized output.
|
||||
|
||||
## [16.3.14] - 2026-07-09
|
||||
|
||||
|
||||
Reference in New Issue
Block a user