- Guarded `session_stop` continuations against aborted or superseded hook results before queueing hidden follow-up turns.
- Reported compaction recovery continuations from `#checkCompaction` and skipped stop hooks while internal recovery owns the next turn.
- Let terminal empty-stop retry caps fall through to `session_stop` and added regression coverage for aborts, empty-stop caps, and promotion recovery.
- Kept `resolveDialect("auto")` on the legacy GLM fallback when a tool-less model has no catalog-recognized dialect.
- Added `sdk-dialect` coverage for unclassified tool-less models alongside MiniMax preferred dialect routing.
- Updated the coding-agent changelog entry to mention MiniMax auto-mode routing.
- Routed `resolveDialect("auto")` through `preferredDialect(model.id)` when a tool-less model exposes an id, preserving the legacy GLM fallback for id-less models.
- Added `sdk-dialect` coverage for MiniMax and Qwen auto owned dialect selection while keeping native and explicit dialect behavior unchanged.
- Updated getApiKey signatures to accept a Model and return ApiKey or ApiKeyResolver.
- Updated stream key handling to resolve credentials per model and use seedApiKeyResolver for retries.
- Added antigravityEndpointMode setting with auto/production/sandbox endpoint selection.
- Added 429/5xx endpoint failover for Gemini stream, usage, search, and image calls.
- Fixed context breakdown to anchor estimates on the latest completed assistant usage message after compaction.
- Adjusted pending-context usage selection to prefer an in-turn provider anchor when available at/after cutoff.
- Added a contextUsageRevision cache token so status-line context memo invalidates after snapshot clear.
- Added context snapshot metadata to AssistantMessage for prompt and non-message token history.
- Anchored context usage calculations on assistant snapshots and computed percent numerically.
- Updated status-line, /context, selector, and interactive mode flows to share session usage totals.
- Extended status-line cache fingerprinting and invalidation for assistant usage and prompt/tool/skill changes.
OpenRouter previously omitted `max_tokens` entirely (except for specific models) to prevent unintended provider filtering when a model's catalog default `maxTokens` exceeded an upstream's actual capacity. This could lead to incorrect routing if a model had a high catalog cap but individual providers under OpenRouter did not.
- Read tool result details now include optional per-line number arrays so displayed content can retain original line mappings.
- Read tool group and renderer now forward code start-line and line-number metadata into code-cell rendering.
- Code cell rendering now draws aligned line-number gutters and pads hidden-line hints to keep gutter alignment.
Kept missing-file and directory identity validation on Windows while skipping only the Unix mode-bit rejection.
Added regression tests for Windows missing and directory identity paths.
Fixes#2850
Skipped Unix mode-bit validation for ssh identity files on native Windows while preserving the stricter check for Unix-like platforms.
Added regression coverage for Windows ssh argument building with permissive low mode bits and for Unix rejection of group/world-readable keys.
Fixes#2850
Routed git.enabled through the status-line settings refresh path so runtime toggles close existing watchers and redraw the top border immediately.
Fixes#2847
Added a git.enabled setting and skipped footer/status-line git probes when integration is disabled or no git-backed status segment is rendered.
Fixes#2847
- Added `images.describeForTextModels` configuration defaulting to true for text models.
- Added `describeAttachedImagesForTextModel` to persist images and generate local:// descriptions.
- Added image-description notices to session flow with hidden typing and pre-user insertion.
- Added fallback behavior that returns notes when vision is unavailable or output is empty.
- Updated the coding-agent modes tips to mention PI_DIALECT for providers that mis-handle native tool calls.
- Clarified a troubleshooting option for restoring behavior when inference providers cannot parse tool-call payloads.
- Added ZAI GLM-5.2 reasoning-effort mapping, translating minimal to none and xhigh to max.
- Enabled ZAI and zhipu GLM-5.2 completion requests to send reasoning_effort and tool_stream.
- Added provider token clamping so GLM-5.2 completion requests use capped max_tokens.
- Updated catalog policies to route GLM-5.2 max-token and reasoning support through ZAI/zhipu hosts.
- Removed synthetic HF model entries and aligned GLM-5.2 catalog specs with real providers.
Fixes#2833
- Changed `select_folded_spans` to skip an unfold candidate that exceeded `unfold_limit` and continue processing the remaining BFS queue instead of breaking.
- Added a regression test in `summary.rs` proving a large `<style>` raw-text span no longer starves sibling HTML sections from unfolding.
- Updated the summary unfold-ceiling setting description to document that overflowed candidates stay folded while BFS continues.
- Added default system-prompt guidance to scan skill descriptions and read applicable skill:// content before work.
- Covered the rendered prompt contract with a frontend-design skill regression test.
Fixes#2829
Recorded todo reminder developer messages in the session log so JSONL transcripts match model-visible context when reminders are enabled.\n\nFixes #2824
Merge displayed bridge-backed range and multi-range read lines into the existing hashline snapshot provenance so INS.POST anchors pass visible-line validation after ACP reads.
Fixes#2773
- Added a new `--advisor` flag to argument parsing and launch flag definitions.
- Applied the parsed `advisor` flag as a runtime-only override of `advisor.enabled` during startup.
- Updated advisor-related docs and added parseArgs tests for `--advisor` behavior and position handling.
- Sanitized artifact filenames by normalizing tool names before composing spill paths.
- Applied `wrapToolWithMetaNotice` to custom tool adapters and RPC-host tools in agent-session setup.
- Wrapped SDK-registered extension/custom tools with the same meta-notice adapter during session creation.
- Gave reasoning-capable local auto-thinking classifiers the safe 1024-token answer budget used by online reasoning classifiers.
- Raised the non-reasoning local classifier floor to 16 tokens and allowed tiny completions to honor larger explicit budgets.
- Added regression coverage for qwen3-1.7b and qwen2.5-1.5b local classifier budgets.
Fixes#2808
- Removed the Codex-preferred canonical remapping path for exact `provider/id` model matches.
- Resolved explicit `openai/gpt-5.5` references as `openai` provider without redirecting to `openai-codex`.
- Added regression tests to confirm explicit provider/id and enabled-model patterns are not coalesced to Codex.
- Replaced `process.chdir(tempDir)` plus `PI_REQ_DEBUG=1` auto-naming with explicit `setNextRequestDebugPath` targets, removing the `previousCwd` save/restore and the `debugFiles` directory-scan helper.
- The PI_REQ_DEBUG recording assertions now read each request/response from the path they set, so the test no longer mutates `process.cwd()` or the global debug env flag.
- Added an optional `cwd` parameter to `looksLikeLocalPath` so bare-name local-directory detection resolves against an explicit path; the install-command test now passes a temp dir instead of `process.chdir`-ing into it.
- Removed `issue-1423-repro.test.ts`, whose package-dir-lookup repro relied on `process.chdir` to stage an isolated project.
- Made `JsRuntime` track the realm globals it installs (`#globalOwner`, `#ownedGlobalKeys`, `PRELUDE_GLOBAL_KEYS`) and reclaim them in `dispose()`, re-binding ownership through `#activateGlobals()` on cwd/run-scope/run; disposing an older inline/direct runtime no longer deletes a newer runtime's helper globals, and overlapping same-realm runs are serialized via `enterGlobalRun`.
- Added `WorkerCore.dispose()` (rejects pending tool calls with `ToolError` and disposes the runtime) and invoked it from `spawnInlineWorker` teardown in `context-manager.ts`.
- Updated the `js-static-import-rewrite` test to snapshot and restore any pre-existing `__omp_import__` global instead of unconditionally deleting it.
- Added `runtime-global-dispose.test.ts` covering newer-runtime global survival, older-runtime reactivation, and cross-runtime mutation rejection.
- Clarified the `runWorkerEntrypoint` comment in `cli.ts` about `parentPort` sync-prefix buffering for tab/eval workers.
