0babd1a73f
fix(tts): persist generated speech in media store ( #115647 )
2026-07-29 02:37:19 -04:00
98a066c90e
fix(agents): project llama.cpp-safe tool schemas ( #115598 )
...
Co-authored-by: Jithin Mohandas <mohandasjithin@gmail.com >
2026-07-29 01:33:32 -04:00
ad36646ed1
fix(gateway): reconnect nodes after transient socket failures ( #115539 )
...
* fix(gateway): reconnect nodes after transient socket failures
* fix(browser): refresh bundled gateway reconnect runtime
* fix(gateway): preserve callback-owned reconnect state
2026-07-29 01:15:26 -04:00
34c90a8cb3
fix(process): prevent orphaned Windows child process trees ( #115535 )
...
* test(process): reproduce Windows taskkill process-tree leak
* fix(process): stop leaked Windows child process trees
Escalate only when Windows taskkill reports that graceful process-tree termination failed. Preserve awaited taskkill completion, grace-period fallback, one-shot signaling, and PID-reuse protection.
Closes #110789
Supersedes #112202
Co-authored-by: Mohammed Alkindi <alkndymhmd692@gmail.com >
---------
Co-authored-by: Mohammed Alkindi <alkndymhmd692@gmail.com >
2026-07-29 00:26:32 -04:00
d41a56fca1
feat(memory): isolate curated entries by project ( #115438 )
...
* feat(memory): scope recall to active projects
* feat(memory): preserve project scope in promotion
* docs(memory): explain project-scoped recall
* fix(memory): chunk curated files per entry
* refactor(memory): narrow project scope internals
* fix(memory): exclude annotations from concept tags
* fix(memory): tighten project isolation boundaries
* fix(memory): preserve project path casing
* fix(memory): prioritize project bootstrap candidates
* docs: refresh memory architecture map
* test(memory): cover project scope schema repair
* fix(memory): complete project isolation paths
* fix(memory): close project ranking checks
* fix(memory): reinitialize search provider before ranking
* fix(memory): tolerate missing bootstrap paths
2026-07-28 23:55:49 -04:00
e98675b4b2
refactor(code-mode): unify safe OpenAI tool filtering ( #115460 )
...
* refactor(code-mode): unify OpenAI tool surface filtering
* fix(code-mode): preserve transport visibility and test types
2026-07-28 21:12:43 -04:00
5922dd4380
fix(memory): fall back to keyword search when embeddings cannot start ( #115397 )
...
* fix(memory): degrade bootstrap failures to keyword search
* docs(memory): clarify recovery status projection
* fix(memory): handle bootstrap embedding failures
* fix(memory): trust resolved provider diagnostics
* fix(memory): keep degraded syncs keyword-only
* fix(memory): confirm embedding recovery before semantic mode
* fix(memory): restore semantic readiness after recovery
2026-07-28 21:01:44 -04:00
ad3f74f296
fix(chat): make web and terminal share one session state ( #115429 )
...
* fix(chat): consolidate web and terminal session state
* fix(chat): preserve live history across stale snapshots
2026-07-28 18:53:21 -04:00
d239a59d82
fix(ui): make Control UI ownership and permissions reliable ( #115364 )
...
* fix(ui): unify connection-owned gateway event dispatch
* fix(qa): keep hosted UI smoke evidence truthful
* fix(ui): make mobile navigation drawer an accessible modal
* refactor(ui): centralize settings search destinations
* fix(ui): own chat media resource lifecycles
* fix(ui): unify sidebar session scope ownership
* refactor(ui): remove obsolete navigation backdrop styles
* refactor(ui): isolate dashboard provider lease capabilities
* fix(ui): centralize gateway operator permissions
* style(ui): format gateway event regressions
* fix(ui): render live dashboard permissions immediately
* fix(ui): enforce approval grant authority
* fix(gateway): fence retired sockets after event gaps
* fix(ui): isolate sidebar gateway fixtures across shared workers
* test(ui): isolate singleton-sensitive browser suites
* fix(ui): retire stale catalog pagination on gateway reconnect
* fix(ui): restore drawer focus after native dialog dismissal
* fix(ui): seed drawer threads and preserve modal focus ownership
* fix(ui): isolate nested native drawer overlay lifecycle
* test(ui): prove isolated dashboard lease authorization
* fix(ui): bound settled managed image resources
* fix(ui): type native modal focus and shared test helper
* fix(ui): correct approval mock types and trim dead export
* fix(ui): keep settings section metadata private
* fix(qa): keep hosted coverage regression within lint limit
* refactor(ui): keep catalog presence in its session data owner
* fix(browser): regenerate bundled copilot runtime
* test(ui): split board lease authorization regressions
* fix(ui): snapshot gateway listener fanout without redundant spread
* fix(ui): bind chat media subscriptions to image lifetime
* fix(ui): extract overlay access lifecycle
* fix(ui): restore guarded media after Lit reconnection
* test(ui): localize board lease fixture title
* fix(ui): reuse system approval fixture labels
* test(ui): narrow managed media lifecycle source
* fix(ui): prevent retired board gateway clients from rolling back leases
* fix(ui): expose pairing to pairing-scoped operators
* fix(ui): preserve legacy device pairing access
* fix(ui): preserve responsive sidebar ownership
* fix(ui): preserve responsive navigation and prove media ownership
* fix(ui): retire revoked catalog and refresh pairing grants
* test(ui): align typed catalog fixtures with main
2026-07-28 16:42:05 -04:00
18ecde3d9f
refactor(chat): keep web and terminal sessions synchronized ( #115377 )
...
* refactor(chat): unify web and TUI session synchronization
* refactor(chat): extract canonical projection and transcript owners
* test(gateway): verify private transcript store identity
* test(agents): protect public transcript storage boundary
* fix(chat): harden cross-client identity and subscription lifecycles
* fix(gateway-client): preserve type-safe release callback rejection
* test(ui): complete shared sidebar gateway fixture
2026-07-28 16:08:10 -04:00
388bcc43a1
fix: make Code Mode reliable across gateway and provider lifecycles ( #115379 )
...
* fix(code-mode): dispose suspended runs and propagate cancellation
* fix(code-mode): preserve request-visible provider tools
* test(code-mode): require real packaged gateway execution
* fix(gateway): load code mode cleanup only during shutdown
2026-07-28 15:21:54 -04:00
c7fecd3b69
fix(compaction): plan cut points in trigger units ( #111886 ) ( #115309 )
2026-07-28 13:24:40 -04:00
1b4a465ea1
feat(gateway): accept WebSocket request trace context ( #113189 )
...
* feat(gateway): accept WebSocket request trace context
* test(gateway): prove WebSocket trace isolation
* test(gateway): simplify traced response match
* ci: allow iOS screenshot validation to finish
* fix(gateway): keep traced request failures scoped
* test(ci): align iOS screenshot timeout contract
* test(ui): reset config route location
* ci: scope iOS screenshots to native changes
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-07-28 13:15:05 -04:00
641c82b5bd
fix(qa): restore full-stack scenarios and truthful suite exits ( #115290 )
...
* fix(qa): restore full-stack scenarios and truthful suite exits
* test(qa): respect plugin boundaries and atomic media delivery
2026-07-28 13:00:22 -04:00
99ec30b44b
feat(plugins): catch code-mode drift between catalogs shipping the same model ( #115183 )
...
* feat(plugins): catch code-mode drift between catalogs sharing one model
Adds a contract test that groups bundled catalog rows by shared upstream
model and requires every row in a group to declare compat.codeMode once any
sibling does. Rows sharing a model id group automatically; rows under
different ids opt in with the new manifest-only `upstreamModel` marker.
Moves the kimi catalog into its manifest so the scan can see it, and records
the tier reseller catalogs were silently missing as explicit "capable".
* docs: regenerate docs map for the shared-model code-mode section
2026-07-28 08:52:21 -04:00
f0bf74bad4
feat(memory): backfill retained session transcripts ( #115162 )
...
* feat(memory): enumerate retained session transcripts
* feat(memory): add session transcript backfill
* test(memory): cover session backfill workflows
* docs(memory): document session transcript backfill
* fix(memory): preserve oldest session backfill ordering
* fix(memory): harden session archive backfill
* test(memory): prove owner-turn provenance gating
* fix(memory): persist session backfill progress
* fix(memory): preserve ranged backfill progress
* fix(memory): order per-file backfill candidates
* fix(memory): retain paged backfill diary entries
* fix(memory): preserve rem backfill diary history
* fix(memory): adapt backfill to retained session identity
* fix(memory): keep rem backfill preview-only
* fix(memory): satisfy backfill CI guards
2026-07-28 08:12:30 -04:00
d28fb52651
fix(openai): preserve incomplete Responses stream output ( #115132 )
...
* fix(openai): recover incomplete Responses stream output
* test: include incomplete SSE in transport discovery
2026-07-28 07:03:05 -04:00
28630a9a65
feat(memory): provenance-gated memory with dreaming on by default ( #114819 )
...
* feat(memory): add provenance and recall metadata to the memory index
* feat(memory): provenance-gated promotion and capture hygiene
* feat(dreaming): LLM consolidation with deterministic gates, on by default
* feat(active-memory): deterministic recall lane with escalation default
* feat(memory): user model file and standing intents
* docs(memory): document the memory architecture
* fix(memory): live-QA fixes — metadata writers, provenance classes, intent scope, claim accumulation
2026-07-28 06:04:25 -04:00
2025c3d1b8
feat(system-agent): give Ask OpenClaw ambient page context ( #114943 )
...
* feat(ui): add custodian page context
* fix(system-agent): keep planner input free of the pending-proposal marker
* fix(system-agent): preserve context-free call shape
* refactor(system-agent): isolate page context boundaries
* fix(gateway): canonicalize UI context
* fix(gateway): enforce ASCII page context
2026-07-28 05:30:44 -04:00
d1b8701e37
fix(openai): honor per-turn timeout and retry controls ( #115017 )
...
Honor existing per-turn timeout and retry controls across OpenAI Responses, Azure Responses, and OpenAI-compatible Chat Completions. Add real SDK HTTP regressions for all three transports.\n\nRefs: #114203
2026-07-28 05:04:51 -04:00
4b05d83035
fix: generated images do not appear in native chat ( #115042 )
...
* fix(chat): render managed images in native clients
Co-authored-by: Francesco Giannicola <francescogiannicola1@gmail.com >
* chore: keep release changelog owned
* refactor(macos): split managed image loading
* test(apple): prove managed image header policy
* test(native): stabilize managed image proof
* test(apple): satisfy strict concurrency checks
---------
Co-authored-by: Francesco Giannicola <francescogiannicola1@gmail.com >
2026-07-28 04:39:53 -04:00
98b8a18b4c
fix(node): harden reconnect and local inference cancellation ( #115033 )
...
* fix(node): harden reconnect and local inference cancellation
* fix(browser): refresh bundled gateway client
* fix(gateway): preserve restart after reconnect reset
* fix(node): preserve tracked remote command ownership
2026-07-28 04:18:51 -04:00
81628fb323
fix(memory): preserve QMD results in noisy command output ( #115023 )
2026-07-28 04:09:28 -04:00
0d7fb8eb39
refactor(fs): adopt fs-safe 0.5 core primitives ( #113705 )
...
* refactor(fs): unify exclusive file publication
* fix(fs): fence stale lock reclamation
* refactor(fs): bound wiki scans and secret reads
* chore(fs): finalize fs-safe 0.5 compatibility
* fix(fs): preserve publication ownership and legacy mode
* fix(fs): fail closed on unverifiable lock owners
* fix(fs): preserve concurrent backup publications
* refactor(fs): preserve ambiguous backup outputs
* fix(fs): preserve mixed-version lock coordination
* refactor(file-transfer): adopt fs-safe archive extraction
* refactor(fs): add bounded walk and secret seams
* refactor(auth): replace proper-lockfile with fs-safe
* fix(fs): honor Windows mode override casing
* refactor(snapshot): adopt fs-safe publication
* refactor(memory-wiki): adopt prunable root walks
* refactor(fleet): adopt bounded archive restore
* fix(fs): preserve post-publication ownership receipts
* refactor(fs): harvest final fs-safe primitives
* style(fs): clean harvest lint
* chore(plugin-sdk): refresh move helper API baseline
* refactor(snapshot): adopt native Windows ACL facts
* refactor(fs): adopt hardened atomic outputs
* fix(fs): scope lock reentrancy to logical owners
* chore(config): lower env var count budget
* fix(deps): adopt published fs-safe 0.5.0
* fix(ci): align SDK surface ratchets
* fix(ci): regenerate SDK API baseline after rebase
* fix(fs): preserve owner-scoped file lock nesting
* fix(ci): refresh SDK API baseline for file locks
* fix(fs): separate SQLite and file lock reentrancy
* fix(imessage): bound pinned attachment reads
* fix(agents): narrow session-key lock options
* fix(fs): preserve fs-safe 0.5 compatibility contracts
* fix(windows): retain private SQLite directory owner
* refactor(sqlite): centralize exclusive coordinator
* refactor(snapshot): isolate Windows ACL policy
* fix(windows): retain snapshot ACL inspector
* chore(config): realign env budget after rebase
* test(agents): accept canonical sandbox escape error
* docs(changelog): defer fs-safe release note
2026-07-28 03:41:47 -04:00
0216fbd4e4
fix(providers): prevent idle timeouts during hidden reasoning ( #114997 )
2026-07-28 03:30:43 -04:00
0297f0ed39
test(ai): freeze packed-package and stream parity contracts ( #114843 )
...
* test(ai): freeze provider and package parity
* refactor(ai): remove provider transport package cycles
* fix(ai): drop unused stream-options re-export
2026-07-27 23:43:57 -04:00
4273ca9dbd
refactor(sessions): remove file-era transcript runtime ( #113233 )
...
* refactor(sessions): keep helper transcripts in memory
* refactor(sessions): remove file-era transcript storage
* test(sessions): use SQLite identity in attempt persistence
* test(codex): isolate legacy transcript fixtures
* fix(sessions): preserve SQLite transcript identity
* fix(sessions): harden transcript lifecycle invariants
* fix(sessions): validate transcript identities
* fix(sessions): close identity compatibility gaps
* fix(sessions): preserve leaf and plugin identities
* fix(sessions): retain dispatch transcript targets
* fix(sessions): preserve active transcript context
* fix(sessions): isolate artifact accounting
* fix(sessions): bound SQLite usage accounting
* fix(sessions): retain bounded latest usage
* fix(sessions): align rebased transcript targets
* test(sessions): align accessor scope fixture
* fix(telegram): derive SQLite transcript identity
* refactor(sessions): remove file-era compaction residue
* chore(sessions): lower max-lines baseline
* fix(sessions): preserve structured transcript identity
* test(sessions): align doctor identity assertions
* fix(sessions): isolate default SDK database
* refactor(sessions): remove dead file-era exports
* fix(sessions): reconcile SQLite transcript identity
* fix(sessions): pass checkpoint identity explicitly
* test(sessions): make entry field probe explicit
* test(sessions): satisfy transcript cleanup lint
* test(sessions): align diagnostics identity proof
* fix(sessions): finish transcript runtime teardown
* fix(sessions): preserve transcript identity invariants
* fix(sessions): harden transcript compatibility edges
* fix(sessions): preserve checkpoint transcript anchors
* fix(sessions): preserve SQLite lifecycle invariants
* fix(sessions): retarget compaction successors
* test(sessions): preserve transcript fixture semantics
* feat(plugin-sdk): add command transcript targets
* fix(sessions): serialize transcript rewrites
* fix(sessions): validate legacy successor identity
* fix(sessions): normalize compaction ownership
* fix(sessions): validate successor identity before adoption
* fix(sessions): preserve plugin transcript ownership
* fix(sessions): carry transcript identity through commands
* fix(sessions): import legacy checkpoint artifacts into SQLite
* fix(sessions): preserve successor transcript ownership
* fix(sessions): align transcript consumers with target identity
* fix(sessions): scope transcript token estimates
* fix(sessions): retain agent identity across lifecycle hooks
* fix(sessions): resolve scoped SQLite targets
* fix(sessions): isolate lifecycle transcript targets
* fix(sessions): validate compaction agent ownership
* fix(sessions): preserve reset and cleanup lifecycle
* fix(sessions): serialize prompt cleanup lifecycle
* fix(sessions): remove stale lock import
* fix(sessions): preserve reset target context
* fix(sessions): fence prompt reload takeover
* fix(sessions): unblock abort and default lifecycle reads
* fix(sessions): validate legacy successor scope
* fix(sessions): reject metadata-only runtime rows
* fix(sessions): propagate custom transcript stores
* fix(sessions): preserve adopted retry targets
* fix(sessions): allow unkeyed usage reads
* fix(sessions): harden runtime target boundaries
* fix(sessions): serialize retry transcript writes
* fix(sessions): bound prompt reload disposal
* fix(sessions): complete retry marker identity
* fix(sessions): keep legacy marker identity minimal
* test(sessions): tighten teardown fixture types
* fix(sessions): preserve compatibility target identity
* test(sessions): persist post-checkpoint boundary turn
* test(sessions): align runtime store mock contracts
* style(sessions): simplify persisted identity guard
* fix(sessions): prefer complete typed targets
* fix(sessions): recover legacy marker targets
* test(sessions): align marker lookup fixture scope
* fix(sessions): validate partial transcript targets
* fix(sessions): reconcile partial transcript identities
* fix(sessions): canonicalize compatibility identities
* test(sessions): cover compatibility aliases
* fix(sessions): adopt legacy successor identity
* fix(sessions): preserve usage read identity
* fix(sessions): preserve partial marker compatibility
* fix(sessions): validate legacy successor mappings
* fix(sessions): reconcile marker store mappings
* fix(sessions): preserve legacy fallback identity
* fix(sessions): harden marker alias resolution
* fix(sessions): prefer verified successor aliases
* fix(sessions): resolve preferred marker aliases
* fix(sessions): serialize cleanup admission
* fix(sessions): align marker lookup scopes
* fix(codex): type marker alias summaries
* style(sessions): satisfy changed lint
* test(sessions): align structured target assertions
* fix(sessions): reconcile latest identity contracts
* fix(sessions): validate transcript identity boundaries
* docs(sessions): explain stable registry keys
* fix(sessions): harden compatibility target round trips
* fix(sessions): port usage identity to split modules
* test(sessions): align subagent transcript identity
* fix(sessions): finish transcript identity migration
* fix(agents): route subagent completion capture through transcript targets
* fix(agents): settle SQLite prompt handoff during cleanup
* chore: shrink max-lines baseline after teardown
* fix(sessions): port teardown across split runtime owners
* fix(sessions): carry transcript targets through split owners
* test(agents): use SQLite compaction target in abort coverage
* chore: retain unrelated max-lines suppressions
* chore: shrink max-lines baseline after main splits
* style(agents): const compaction checkpoint locals
* fix(sessions): harden SQLite teardown boundaries
* test(sessions): use typed metadata in predicate isolation fixture
* test(agents): cover malformed settlement rejections lint-safely
* fix(sessions): close remaining SQLite identity races
* fix(agents): fail closed on incomplete successor targets
* fix(sessions): preserve transcript identity fallbacks
* fix(agents): preserve session-key abort admission
* fix(trajectory): validate incomplete export targets
* test(sessions): drop retired pricing cache imports
* fix(sessions): validate partial transcript identities
* fix(sessions): close transcript identity edge cases
* fix(plugins): reserve retired transcript locator slot
* fix(sessions): scope transcript locks by target
* style(sessions): simplify SDK initialization error
* fix(sessions): preserve initialized transcript state
* fix(codex): verify mirrored history session keys
* fix(sessions): reject stale transcript ownership
* fix(sessions): anchor asynchronous transcript ownership
* fix(sessions): measure active transcript state
* fix(sessions): preserve scoped transcript compaction
* fix(sessions): harden transcript identity and lifecycle
* fix(sessions): resolve scoped command transcript stores
* fix(sessions): make transcript appends failure-atomic
* fix(sessions): enforce scoped transcript ownership
* fix(sessions): reject cross-owner transcript handoffs
* fix(sessions): fence cleanup transcript ownership
* fix(sessions): retire stale write ownership contexts
* fix(sessions): preserve pending session migration state
* fix(sessions): validate migrated transcript ownership
* fix(sessions): validate usage transcript targets
* fix(sessions): clear predecessor transcript metadata
* fix(sessions): align durable session event targets
* fix(sessions): fence late prompt handoffs
* fix(sessions): fence lifecycle transcript fallbacks
* fix(sessions): bound zero-length memory capture
* fix(sessions): preserve transcript teardown ownership
* fix(sessions): reject duplicate cleanup ownership
* fix(sessions): serialize runtime writes with sqlite leases
* fix(sessions): close sqlite teardown concurrency gaps
* fix(sessions): preserve nested lifecycle failures
* fix(sessions): canonicalize sqlite transcript ownership
* fix(sessions): settle disposed prompt handoffs
* fix(sessions): resolve canonical attempt lock targets
* test(sessions): align canonical target fixtures
* test(sessions): retire redundant jsonl parser coverage
* refactor(sessions): split active transcript cursors
* test(memory): retire legacy marker fixture
* fix(sessions): preserve canonical transcript access after rebase
* fix(sessions): fence prompt lease and return transcript targets
* fix(sessions): colocate transcript leases with target store
* fix(sessions): canonicalize transcript lease and worker targets
* fix(sessions): preserve plugin and fork identity markers
* fix(sessions): complete sqlite transcript target migration
* fix(sessions): integrate canonical followup identity
* fix(sessions): preserve bounded transcript topology
* fix(sessions): validate transcript identity boundaries
* fix(context): separate caller and successor targets
* test(sessions): split persistence compatibility coverage
* test(sessions): preserve fixture topology efficiently
* chore(sdk): refresh plugin api baseline
* test(agents): align compaction lock target mocks
* test(sessions): seed malformed transcript fixtures directly
* fix(agents): canonicalize transcript compatibility inputs
* fix(agents): type optional tool result ids
* test(ci): stabilize loaded process timing
* test(tui): wait for collect queue admission
2026-07-27 22:33:24 -04:00
d5e46646f2
refactor(gateway-protocol): derive schema registries from owner fragments ( #114817 )
...
* refactor(protocol): share schema owner barrel
* refactor(protocol): extract ordered schema fragments
* refactor(protocol): compose public schema registry
* docs(protocol): document schema fragments
* ci(protocol): guard schema registry structure
* style(protocol): satisfy registry guard lint
2026-07-27 21:08:20 -04:00
a1e0c9ea09
refactor(packages): DM-policy contract suite, dead routes, package folds ( #114776 )
...
* test(channels): share DM policy contract suite
* refactor(memory): remove dead host CLI routes
* refactor(acp): use canonical normalization helpers
* refactor(web): fold provider runtime into core
* refactor(packages): remove dead runtime exports
* chore(knip): drop retired ACP entry roots
2026-07-27 20:20:13 -04:00
313daad549
perf(gateway): warm handler families and cache identity avatars ( #114754 )
...
* perf(gateway): warm handler families and cache identity avatars
* chore: drop changelog edit (release-generation-owned)
* fix(ci): regenerate protocol models, satisfy knip, absorb sidecar drift
- commit regenerated Swift GatewayModels for the additive cron.list param
- split the avatar data-url cache into assistant-avatar-cache.ts so its
factory has a production consumer (knip production scan)
- de-export prewarm family names/type; test now drives fake families only
- postReadySidecarCount 2 -> 3: main added a post-ready sidecar in parallel
2026-07-27 19:37:13 -04:00
b5bb29a36e
fix(code-mode): preserve direct tools and secure suspended runs ( #114778 )
...
Preserve trusted policy-required message delivery and native image/computer tools across Code Mode catalogs and provider transports. Keep preferred Gemini capability metadata during live discovery, escape MCP declaration keywords, and reject suspended-run resumes with missing owner identity. Add before-and-after regressions for each user path. Closes #114753 .
2026-07-27 18:47:33 -04:00
7394262cd1
feat: per-model code-mode capability flags with an "auto" master-switch tier ( #114695 )
...
* feat(tools): per-model code-mode capability flags and auto master-switch tier
* feat(anthropic): flag claude-sonnet-4-6 as code-mode preferred
* revert(anthropic): drop claude-sonnet-4-6 from the code-mode preferred set
* test(anthropic): type the manifest compat field in the catalog contract test
* fix(anthropic): carry catalog compat onto hand-built forward-compat model rows
2026-07-27 16:47:41 -04:00
9588a10f12
refactor(ai): unify Responses transport factories ( #114357 )
...
* refactor(ai): unify Responses transport factories
* style(ai): format Responses transport executor
2026-07-27 12:40:48 -04:00
89c5b02832
revert(openai): remove loopback Codex proxy support ( #114616 )
...
Reverting PR from runaway clanker, sorry! Won't happen again!
2026-07-27 23:15:42 +08:00
17ed69e103
fix(agents): preserve prompt caches across tool discovery ( #114572 )
2026-07-27 09:58:19 -04:00
6f8a67120c
feat(openai): support loopback Codex proxies ( #114555 )
...
* feat(openai): support loopback Codex proxies
* fix(openai): preserve Codex proxy routes
* fix(openai): enforce canonical Codex proxy path
* fix(openai): support opaque proxy capabilities
* test(openai): isolate proxy capability coverage
* fix(openai): confine proxy capabilities
* test(openai): type proxy image config
2026-07-27 13:31:04 +00:00
92eb942822
fix(ai): safely format circular provider stream errors ( #107800 )
...
* fix(ai): terminate Anthropic streams on circular error objects
* test(ai): reject with a plain circular object without Promise.reject
* test(ai): pin Anthropic error-message semantics and drop totality overclaim
* test(ai): assert terminal event type in Anthropic error-message test
* fix(ai): preserve circular provider error details
---------
Co-authored-by: Altay <altay@hey.com >
2026-07-27 16:28:40 +03:00
14d8c2439f
feat(ui): offer normally-absent core files instead of flagging them missing ( #114559 )
...
* feat(ui): offer normally-absent core files instead of flagging them missing
The Agents core-files editor rendered every unwritten workspace file as a
permanently-badged MISSING tab, so an ordinary workspace looked broken. Absence
is only a fault for required files; SOUL.md, USER.md, and MEMORY.md are normal
to be absent until written.
agents.files.list now marks those entries expectedAbsent, and the editor keeps
them out of the tab strip behind an add picker that creates the file on save.
A missing AGENTS.md still shows as a fault.
* chore(protocol): regenerate Swift gateway models for expectedAbsent
* fix(gateway): carry expectedAbsent through agents.files.get
Clients merge the get response over the listed entry, so a missing-file get
that dropped the flag made a file picked from the add picker re-render as a
MISSING fault. Caught by live Control UI proof, not by the unit tests.
2026-07-27 09:16:10 -04:00
43ff420492
fix(providers): preserve local model discovery and retry ownership ( #114582 )
2026-07-27 09:14:23 -04:00
a01319b27f
fix: account for CJK text in compaction estimates (issue #103930 ) ( #114386 )
...
* fix: account for CJK text in compaction estimates
* fix: share CJK compaction estimator
* fix: format CJK compaction estimator
* fix: make CJK regexes lint-safe
Co-authored-by: qingminlong <qing.minlong@xydigit.com >
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-07-27 08:51:44 -04:00
1564e86fcf
refactor(ai): consolidate Anthropic streaming regression fixtures ( #114511 )
2026-07-27 08:36:34 -04:00
97d3d60b51
fix(markdown): unify reasoning tag parsing ( #113205 )
...
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-07-27 07:48:57 -04:00
91f04499f5
fix(sessions): defer agent self-archive until run completion ( #114522 )
2026-07-27 07:46:22 -04:00
c6b2ec28c8
refactor: mechanical dedup batch (protocol types, update-cli bridge, talk fallback) ( #114432 )
...
* refactor(onboarding): remove search setup barrel
* refactor(plugins): reuse detected package manifest
* test(update): replace global helper bridges
* refactor(talk): remove dead legacy response fallback
* refactor(protocol): derive root types from schema
The maintainer approved broadening the additive schema-backed type surface without a protocol version bump.
* fix(plugins): drop stale package path import
* test(protocol): type dynamic registry lookups
* docs(talk): explain canonical response boundary
* refactor(talk): enforce canonical response input
* fix(protocol): keep root type exports registry-free
* refactor(update): expose helpers through test facades
* fix(protocol): keep result types on leaf schema modules
2026-07-27 06:55:07 -04:00
b8e7f27ff2
feat(ui): let a link's slug settle a shared short-id prefix ( #114486 )
...
* feat(ui): let a link's slug settle a shared short-id prefix
Two sessions can share the first block of their uuid, which sent an otherwise
exact link to the disambiguation view even though the slug in that link already
said which session was meant. Capture the slug on short references and use it to
break the tie.
It can only narrow: a slug matching none or several of the tied sessions leaves
the chooser alone, and a reference that already resolves uniquely is untouched.
Generated links stay at their normal length instead of growing a full uuid.
* fix(ui): never settle a slug tie from an incomplete search
A truncated candidate set is an unfinished search, not a tie: an unexamined page
could hold the same short-id prefix under the same slug. Settling there would be
the guess the bounded search exists to avoid, so keep the chooser.
2026-07-27 06:08:51 -04:00
269bc5c89e
fix(cli): preserve machine-readable stdout ( #113654 )
...
Co-authored-by: 1052326311 <65798732+1052326311@users.noreply.github.com >
2026-07-27 05:44:16 -04:00
51f228f6fe
fix(ui): preserve agent-owned session navigation
...
Add agent ownership to observer digests, scope global observer delivery and reconciliation, and centralize application session selection across navigation and reconnects.
Co-authored-by: xbrxr03 <abrarhabib03@gmail.com >
2026-07-27 05:43:19 -04:00
af552d4bc6
feat(ui): resolve session URLs through the gateway with best-effort slug matching ( #114422 )
...
* feat(ui): resolve session URLs through the gateway with best-effort slug matching
Session URLs now resolve a stored board face and a display-name slug through
the gateway instead of guessing from the browser's cached session page.
- An uncached open marks only the in-app navigation, never the shareable href,
so the chat loader can re-derive the face and replace the URL.
- A cached row settles the lookup locally, keeping navigation off the wire.
- A one-segment reference resolves short id, then literal key, then display-name
slug; ties reuse the existing disambiguation view.
* refactor(ui): keep slug ties on short disambiguation prefixes
Slug candidates reused the full uuid, which produced 32-character links in the
disambiguation view. uniqueShortIdPrefix already falls back to the full id when
the bounded search was truncated, so reuse it and drop the flag.
* fix(ui): navigate worktree owner links in-app so the face marker survives
The Worktrees owner link was a bare anchor consuming only the shareable href,
so preferenceDerivedFace was a no-op there and an uncached owner always opened
on chat. Match the other session surfaces: keep the clean href and navigate
with the options on plain clicks.
* fix(ui): search the first uuid block so long session references resolve
The gateway matches sessions.list search as a plain substring and stored keys
hold a hyphenated uuid, so any hyphen-stripped reference past the first block
matched nothing and 404'd. This hit disambiguation links, which offer prefixes
longer than eight characters. Send the first block and keep applying the full
prefix per row.
A resolved slug now canonicalizes to that same short reference instead of a
full uuid, so /chat/main/deploy-monitor settles on -6db92d48.
* docs(ui): record why the face marker stays out of shareable hrefs
2026-07-27 04:31:33 -04:00
b461ae6de8
test(model-catalog): cover normalization and routing boundaries ( #114384 )
2026-07-27 02:56:59 -04:00
0406e66369
fix(ui): keep stable chat rows in insertion order and only sort live tool/stream items by timestamp ( #113266 )
...
* fix(ui): keep stable chat rows in insertion order and only sort live tool/stream items by timestamp
* fix(ui): keep live rows within current turn
* fix(ui): keep current work above queued turns
* fix(ui): keep streamed replies above queued turns
* fix(ui): preserve reconnecting run order
* fix(ui): preserve causal terminal ordering
* fix(ui): bound replay rows to owning turns
* fix(ui): keep question summaries in owning turns
* fix(ui): scope question run ownership to session
* fix(ui): restore reconnecting chat run identity
* fix(ui): remove unused chatItemTimestamp import in chat-thread-build.ts
* fix(ui): correlate question summaries with agent runs
Co-authored-by: Peter Lee <li.xialong@xydigit.com >
* chore(i18n): refresh native source baseline
Co-authored-by: Peter Lee <li.xialong@xydigit.com >
* fix(ui): remove unused chatItemTimestamp export and split tool-stream test file
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-07-27 02:08:22 -04:00
Peter Steinberger