The consume-once source map kept entries for graph modules the initial
import never loaded (modules only reached via lazy dynamic imports).
Their first import - possibly long after load, and after an on-disk
edit - was served the boot-time snapshot instead of current file
content, and the unconsumed sources stayed in the plugin closure for
the process lifetime.
Clear the map once the entry import settles: everything Bun loaded at
startup was already consumed (keeping the read-once win), and anything
left must be read at its actual import time, matching pre-dedup
behavior for lazy modules. The new regression test passes on the
pre-dedup baseline and fails on the unfixed dedup.
isAllCapsWord matched any multi-letter token without a lowercase letter,
so CJK tokens registered as ALL-CAPS words: two adjacent ones marked the
whole source shouty and silently disabled acronym restoration for every
non-Latin-script message (e.g. '修复 CNPG 集群故障' kept 'Cnpg'). Require an
actual uppercase letter; cased-script shout detection is unchanged.
The PR's changelog, doc comment, and prompt examples all name ETL as a
restored acronym, but the review-response narrowing (vowel heuristic +
allowlist) silently dropped it: ETL bears a vowel and was not listed.
Add it to COMMON_TITLE_ACRONYMS and pin it in the allowlist test.
Narrow acronym restoration so plain all-caps English words such as FIX
and WORK do not get restored when the model naturally capitalizes the
first title word. Restorable all-caps source tokens now need a stronger
acronym signal: a common technical acronym allowlist, digits, or a
consonant-only shape.
This keeps CNPG, ETL, JWT, SQL, and API restoration while preserving the
anti-shout behavior for single emphatic words.
Fixes#4220
- Added an enhanced speech pipeline that utilizes small models to rewrite text for natural language synthesis.
- Implemented `SpeechEnhancer` and `BlockAccumulator` to manage fence-aware text streaming and paragraph splitting.
- Configured a new `speech.enhanced` setting to toggle between mechanical and enhanced vocalization modes.
- Resolved `EPIPE` rejections during speech playback by ensuring stream flushes and suppressing stop-related errors.
reconcileTitleCasing now maps ALL-CAPS source tokens (CNPG, API, ETL,
JWT) into an acronyms table and restores them when the model produces a
plain title-cased artifact (Cnpg). Restoration is disabled when the
source is shouty (>=2 consecutive multi-letter ALL-CAPS tokens like
"FIX the BUG NOW" or "ALL ERROR HANDLING"), and lowercase model output
is left alone so isolated single-word emphasis (WORK -> work) is never
re-shouted.
The three title system prompts (title-system.md, title-system-marker.md,
tiny-title-system.md) also gained an explicit instruction to preserve
ALL-CAPS acronyms verbatim, so a competent model short-circuits via the
verbatim set before post-processing kicks in.
Fixes#4220
Removed the live-context guard that let default model selection persist a new role without changing the active session model. The next prompt's compaction path now owns oversized-context recovery after a switch.
Fixes#4219
- Allowed the priority premium-request fixture to set assistant message `api` values.
- Covered direct Anthropic priority traffic with `api: "anthropic-messages"` so premium-request backfill follows API-family classification.
- Added `SpeakableStream` to strip markdown noise, silence code blocks and tables, normalize links and paths, and emit sentence/clause segments.
- Reworked `Vocalizer` to segment assistant deltas in the parent process, lazily open TTS streams, idle-flush partial thoughts, and chain playback sessions.
- Added gapless streaming playback with ffmpeg/sox backends, ducking-aware pacing, fallback file playback, and immediate stop handling.
- Added IPC `sendAndFlush` support and used it in the TTS worker so audio chunks drain before blocking ONNX inference resumes.
- Added speakable-stream coverage for markdown filtering, segmentation latency, idle flushing, and forced long-segment splits.
- Replaced `grep`, `glob`, and `ast_grep` `paths` inputs with optional single `path` strings while preserving default workspace-root behavior.
- Added shared `toPathList` normalization for legacy arrays and JSON-encoded arrays across tool execution and TUI renderers.
- Updated prompts, fixtures, shims, transcript summaries, and tests to send and display the new `path` argument.
- Updated collab-web search tool cards to read `path` while falling back to legacy `paths` for historical transcripts.
- Recorded the contiguous coding-agent changelog run for the tool-path breaking change and adjacent TTS entries.
Loaded cached runtime extension provider catalogs before deferred model resolution so dynamic-only providers can satisfy cold-start --model and session resume selection from models.db.\n\nFixes #4216
- Added support for parsing unquoted bareword strings in object and array value positions.
- Implemented safety checks to prevent bareword recovery from masking structure, consuming non-finite atoms, or swallowing valid JSON delimiters.
- Included logic to preserve URL-style and Windows-style paths containing colons while rejecting invalid or ambiguous syntax.
ZenMux discovery only defined a dynamic fetcher when a ZENMUX_API_KEY was
present, and the descriptor lacked the top-level allowUnauthenticated flag
that gates keyless runtime manager creation. Newly published ZenMux models
therefore never reached the runtime models.db cache without a key — they
were stranded until the bundled models.json was regenerated.
Make fetchDynamicModels unconditional (the public /api/v1/models endpoint
needs no auth) and add top-level allowUnauthenticated so the runtime builds
a keyless manager and writes discoveries to models.db, matching the
ollama/lm-studio pattern. ZenMux stays out of #keylessProviders: it is a
paid gateway, so discovered models are cached and findable but not
selectable without credentials (they would 401 at inference).
Also fixes a latent runtime bug: getProviderBaseUrl returns the first
bundled model's baseUrl, which for ZenMux is the anthropic-routed
/api/anthropic. Discovery then fetched /api/anthropic/models (nonexistent)
instead of /api/v1/models, breaking discovery even for keyed users.
normalizeZenMuxOpenAiBaseUrl now remaps a trailing /api/anthropic back to
/api/v1 before the /models fetch.
Op: correct
Restores: spec:ZenMux runtime discovery reflects newly published models in models.db without a ZENMUX_API_KEY
`discoverExtensionPaths` loaded the extension-module capability across all
registered providers (native, claude, codex, gemini, opencode) and then
discarded every item whose `_source.provider !== "native"`. Four foreign
directory walks ran on every session startup only for their results to be
dropped — worst on Windows.
Scope the load to the native provider via the existing `LoadOptions.providers`
filter: `loadCapability(extensionModuleCapability.id, { ...loadOptions,
providers: ["native"] })`. The hook-capability load in the same function is
unchanged (hooks legitimately span providers). Output is identical.
Regression test in `extensions-discovery.test.ts` spies on each extension-module
provider's `load()` and asserts only "native" is invoked.
Fixes#4198
collectExtensionModules already reads every own-source module's text to scan imports; the onLoad rewrite hook then re-read each file. Return a Map<path,source> from the collector and serve it consume-once in onLoad (delete on first hit, disk fallback on miss), so transitive modules are read once and the entry still re-reads on its ?mtime re-import. Adds a regression test asserting exactly one read per graph module.
Closes#4196
- Removed the `requiresReasoningSuppressionPrompt` compatibility flag and associated logic.
- Simplified `buildOpenAIResponsesChainedParams` by removing support for trailing input scaffolding.
- Cleaned up parameter builders and test suites that handled the suppressed developer role messages.
- Simplified the check for empty Anthropic thinking signatures during same-model replays by leveraging optional chaining.
- Preserved the existing behavior of returning an empty array for empty signature strings while cleaning up unnecessary logical branches.
- Extracted the evaluation of `bareModelId(modelId)` into a `canonicalId` variable to avoid duplicate calls.
- Simplified assertions in the prior-turn thinking tests to check for an empty text blocks array directly.
- Stopped same-model official Anthropic replays from falling back to text demotion when thinking blocks lack signatures.
- Ensured unsigned thinking blocks are stripped instead of converted to textual dialect fallbacks when replayed on the same model.
- Removed an unused variable assignment in `renderDemotedThinking`.
ZenMux's `anthropic-messages` route (`zenmux.ai/api/anthropic`) forwards to
signature-enforcing Anthropic and returns full thinking signatures, but the
compat builder classified it as a non-signing reasoning endpoint via the
generic `reasoning && !official` default (`replayUnsignedThinking: true`).
Same failure class as GitHub Copilot #2851: when a checkpoint/branch-return
turn is an abandoned tool-use turn (adaptive Sonnet 5 emits a tool call then
ends on `stop`/`end_turn`), `transformMessages` correctly strips its
end_turn-bound, unreplayable signature. On a `replayUnsignedThinking`
endpoint the encoder then re-emitted that block as
`{ type: "thinking", signature: "" }`. An empty signature is rejected by
the signature-enforcing backend with
`400 messages.1.content.0: Invalid signature in thinking`.
Exclude ZenMux from `replayUnsignedThinking` (via a new `zenmux` host
classifier covering the `zenmux` provider id and the `zenmux.ai` url marker)
so unsigned/stripped thinking degrades to text exactly like the official
Anthropic API — wire-valid and lossless of the tool_use pairing. Z.AI /
DeepSeek / other 3p reasoning endpoints (#2005) and cross-model preservation
(#2257/#2265) are unaffected.
Tests:
- packages/catalog/test/anthropic-zenmux-signing-compat.test.ts: zenmux
(provider id and url marker paths) -> replayUnsignedThinking false; generic
3p reasoning -> true; official -> false. Fails before / passes after.
- packages/ai/test/anthropic-zenmux-checkpoint-thinking-signature.test.ts: a
derived-compat zenmux sonnet 5 model never emits an empty-signature
thinking block for a historical checkpoint turn (demotes to text, keeps
tool_use), and still replays a clean signed historical thinking block
natively.
Fixes#4192
- Persist signed message blocks (`text`, `thinking`, `toolCall`) and encrypted reasoning payloads verbatim during session serialization instead of clearing or truncating them.
- Preserve signature keys instead of replacing them with empty strings when they exceed persistence size limits.
- Exempt official first-party OpenAI and Anthropic API endpoints from the leaked-thinking stream healing wrapper to prevent misfires on legitimate visible text fences.
- Exempts official Anthropic, OpenAI, and OpenAI-Codex base URLs from stream-healing logic.
- Adds `isLeakedThinkingHealExempt` to detect official API hosts and avoid processing structured thinking blocks.
- Incorporates Anthropic Foundry toggle detection to accurately route enterprise gateway URLs.
- Refactors stream dispatch exits to conditionally apply `healLeakedThinking`.
- Adds unit tests verifying that leaked fences are preserved for official endpoints but healed on third-party gateways.
- Excluded signed `thinking` blocks and `redactedThinking` blobs from size-based persistence truncation.
- Preserved signature-bound reasoning verbatim to prevent provider validation failures on session replay.
- Maintained normal truncation behavior for unsigned thinking and standard text blocks.
- Stopped calling the consuming `getSteeringMessages` getter during mid-batch interrupt polls to prevent stranding or dropping messages before they reach the injection boundary.
- Skip subsequent steering checks in the poll loop once an interrupt has already triggered.
- Added a regression test to ensure legacy steering remains queued until the injection boundary when no non-consuming peek exists.
The branch-scan rehydrator only rebuilt `#lastCompletedRewind` and wiped
`#checkpointState` unconditionally at entry — so a branch whose latest
checkpoint had not yet been rewound came back with neither an active
checkpoint nor completed-rewind guidance. Reloading such a session (or
`switchSession()` on the same file) made the next `rewind` fail with
"No active checkpoint" even though the checkpoint entry was still the
branch leaf.
Extended the walker to also track the last unresolved checkpoint entry
and, when the branch ends without a rewind-report, seed `#checkpointState`
from that entry (id, `details.startedAt`) so `rewind` can complete
normally. Renamed the method to `#rehydrateCheckpointRewindState` to
reflect the widened responsibility and added a regression test that
truncates the branch to the checkpoint entry, resumes into a fresh
`AgentSession`, and calls `rewind` end-to-end.
Fixes#4187
- Refactored `renderSubagentHudLines` to use `renderTreeList` with dim connectors and a single-space indentation shift.
- Adjusted budget limits to account for the new layout wrapping and tree-list padding.
Cleared checkpoint rewind runtime state when starting new sessions or creating branch sessions so stale completed-rewind guidance cannot leak into unrelated contexts.
Added regression coverage for /new and branch reset paths.
Fixes#4187
Reconstructed the completed rewind marker from the active branch so resumed sessions keep repeat-rewind recovery guidance.
Covered resume rehydration with the checkpoint rewind branch regression test.
Fixes#4187
can1357