Commit Graph

21 Commits

Author SHA1 Message Date
Peter Steinberger 2e6457b8e6 fix(codex): restore GPT-5.6 reasoning effort options (#126182)
* fix(codex): preserve model effort capabilities

Keep public model identities separate from app-server execution routing, and retain provider-owned complete effort metadata when account discovery is partial.

Fixes #126005

* refactor(codex): avoid redundant thread rotation

* fix(codex): preserve model fallbacks without leaking wire ids
2026-08-18 22:56:20 -07:00
Hannes Rudolph 34c3d15a6b fix(macos): complete Codex onboarding and model picker (#124829)
* fix(setup): refresh Codex registry with staged install

* fix(macos): verify inference before onboarding handoff

* fix(setup): use native Codex home for subscription auth

* fix(codex): honor attempt-scoped setup config

* fix(macos): align onboarding handoff with reopen

* fix(setup): await prepared model convergence

* fix(ui): avoid false auth state for empty catalog

* fix(setup): scope catalog convergence to Codex gateway

* fix(setup): publish the committed runtime catalog

* fix(models): project configured static runtime models

* fix(codex): expose app-server model catalog

* fix(models): preserve Codex auth across reloads

* fix(ci): align Codex onboarding checks

* test(ui): stabilize dock suppression environment

* fix(codex): honor discovery config in app-server model catalog

The manifest documents discovery.enabled (bundled fallback list) and
discovery.timeoutMs (default 2500ms) for model discovery; the new catalog
path used the generic 60s request timeout and ignored the enable gate.
Also drop the test-only listModels injection seam in favor of vi.mock.

* fix(setup): refuse prepared Codex auth over an explicit remote transport

configureCodexCliPreparedAuth silently rewrote an explicitly configured
websocket/unix app-server to local stdio (keeping a dangling url), moving
the credential boundary onto this host. Fail setup with actionable
guidance instead; also surface the root cause when the prepared model
catalog refresh fails after activation.

* refactor(agents): one canonical model-catalog identity key

Three near-identical key helpers existed (models-list-result,
models-list-configured-static, harness/model-catalog). Export
resolveModelCatalogIdentityKey from the route-policy owner, collapse the
duplicate dedupe loops into dedupeByKey, make donor enrichment Map-based,
and inline the one-off harness-augment wrapper.

* fix(macos): restore custodian handoff for fresh activations

Landing every finish on the plain dashboard stranded the custodian
first-run flow (memory import, channels, permissions, hatch). Fresh
activations now hand off to custodian onboarding; live-verified
pre-existing setups reopen the normal dashboard, matching the removed
already-configured shortcut. Tests pin the destination per path.

Also isolate the post-startup Codex login test from developer machines:
ambient OPENAI_API_KEY and a real Codex login made it assert-fail.

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-08-17 23:31:12 -07:00
Marvinthebored 2404d41de2 fix(codex): preserve delegation when image generation is denied (#124598)
Forward exact audited tool denies into agent harnesses so Codex can disable native image generation without dropping delegation. Fail closed when managed policy forces image generation and rotate retained threads when effective native config changes.

Co-authored-by: Marvinthebored <262704729+Marvinthebored@users.noreply.github.com>
2026-08-16 21:42:38 +05:30
Peter Steinberger 0a6b95a3df feat: cloud workers for the codex runtime (remote-exec placements) (#123743)
* feat(gateway): add remote-exec cloud placements

* feat(codex): run cloud turns through remote exec

* fix(sandbox): quote ssh_config path directives containing whitespace

Crabbox lease keys default to ~/Library/Application Support/... on macOS;
unquoted IdentityFile/UserKnownHostsFile/CertificateFile arguments tokenize
on the space and fail as 'extra arguments'. Found via live remote-exec
cloud-worker proof.

* test: consolidate gateway maintenance schedule coverage

* fix(ci): invalidate plugin sdk declarations on state changes
2026-08-14 16:46:56 -07:00
ClawSweeper 036bcc1a65 fix(agents): self-heal unsupported harness transports (#123258)
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-08-13 13:08:35 -07:00
Peter Steinberger fc0147b529 test(plugins): remove duplicate setup cases (#122515) 2026-08-12 00:19:22 -07:00
keshavbotagent 3807eb9c58 fix(codex): preserve allowed tools under channel policy (#122282)
Preserve Codex native tools when conversation policies deny only audited OpenClaw capabilities. Fail closed for computer-control denies and retain structured plan progress.

Co-authored-by: Ayaan Zaidi <hi@obviy.us>
Co-authored-by: Kelaw - Keshav's Agent <keshavbotagent@gmail.com>
2026-08-12 05:27:08 +00:00
Ayaan Zaidi ec4ae78b75 fix(agents): generate session titles with runtime-owned auth (#122163)
Use the selected harness for isolated title generation, including native Codex auth.
Retry failed dashboard titles from the first user message without overriding manual names.

Co-authored-by: Ayaan Zaidi <hi@obviy.us>
2026-08-12 09:42:16 +05:30
Glucksberg 6318e30077 fix(codex): prevent session-changed errors after /new (#113429)
* test(codex): prove replies after retained session reset

Co-authored-by: Markus <markuscontasul@gmail.com>
Co-authored-by: Josh Lehman <josh@martian.engineering>

* test(codex): verify reset idempotency

* test(codex): prove reset keeps binding writable

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: Josh Lehman <josh@martian.engineering>
2026-08-08 08:55:25 -07:00
Josh Avant ce67ffb70e feat(agents): add tool-free isolated completion (#114343)
* feat: add isolated pure-inference completion

* fix(google): block ambient system prompt writes

* docs: refresh generated map
2026-07-30 13:24:45 -05:00
keshavbotagent 46f4018ff9 fix(codex): recover in-place session resets (#114056)
* fix(codex): recover in-place session resets

* fix(codex): preserve retired generation fences

---------

Co-authored-by: Josh Lehman <josh@martian.engineering>
2026-07-26 16:49:57 -07:00
Peter Steinberger 40b10eb3d1 perf: avoid plugin cold loads in request hot paths (#109348)
* perf: avoid cold plugin discovery in hot paths

* chore: remove stale harness policy re-export

* fix: preserve active thinking clamps in status
2026-07-16 14:54:32 -07:00
Peter Steinberger 0ff265838b fix(codex): preserve shutdown cleanup across live builds (#106418) 2026-07-13 06:41:19 -07:00
Peter Steinberger 1b1cebfe42 fix(openai): align auth availability with effective routes (#104685)
* feat(openai): add provider-owned route facts

* fix(openai): harden provider route facts

* test(codex): update rebased auth fixtures

* chore: leave release notes to release workflow

* fix(openai): align route auth with current contracts

* test(openai): align route and shard expectations

* test(openai): satisfy route fixture contracts

* fix(openai): preserve direct profile forwarding

* test(models): complete route auth mocks

* test(codex): type compaction factory mock

* fix(openai): preserve provider-native model ids

* test(agents): align route auth fixtures

* style(agents): format route integrations

* test(plugin-sdk): pin current surface counts
2026-07-11 15:26:48 -07:00
Peter Steinberger 96f0983a85 fix(onboarding): skip setup for configured gateways and require inference first (#102883)
* fix(crestodian): keep onboarding RPCs restart-safe

* fix(profiles): isolate approval state migrations

* fix(crestodian): bypass configured gateway setup

* test(crestodian): type onboarding mocks

* fix(onboarding): require inference before Crestodian

* fix(onboarding): enforce verified inference handoff

* fix(macos): reset setup on gateway endpoint edits

* chore(i18n): refresh native source inventory

* fix(gateway): keep socket on request cancellation

* test(packaging): require workspace templates

* fix(onboarding): bind setup to verified inference

* fix(onboarding): align inference gate contracts

* fix(crestodian): classify concurrent policy rejection

* test(crestodian): expect registry restoration

* fix(onboarding): bind setup to configured gateways

* fix(codex): preserve startup phase deadlines

* test(crestodian): match fail-closed policy ordering

* test(onboarding): assert bound gateway handoff

* fix(codex): bind runtime resolution to spawn cwd

* test(crestodian): assert policy rejection order

* fix(cli): preserve gateway routing across restarts

* fix(macos): fail closed during gateway edits

* test(macos): cover gateway route generation races

* chore: keep release notes out of onboarding PR

* fix(ci): refresh onboarding generated checks

* style(swift): align gateway channel formatting

* fix(ci): refresh plugin SDK surface budgets

* fix(ci): resync native string inventory

* refactor(swift): split gateway channel support

* test(doctor): isolate plugin compatibility registry

* test(macos): isolate gateway onboarding fixtures

* test(macos): assert gateway lease health ordering

* fix(codex): reconcile computer-use startup changes
2026-07-11 10:25:14 -07:00
Peter Steinberger f94a7dc183 feat(codex): supervise native Codex sessions (#104045)
* feat(codex): add native session supervision

* fix(codex): harden supervision integration

* fix(codex): preserve locked harness ownership

* fix(codex): fence native session archive

* fix(codex): revalidate archive binding ownership

* feat(codex): integrate supervision runtime

* feat(sessions): preserve harness-owned execution

* feat(sessions): persist harness ownership invariants

* feat(gateway): enforce harness-owned sessions

* feat(setup): enable detected Codex supervision

* feat(mac): expose supervised Codex sessions

* feat(ui): make Codex sessions actionable

* docs(codex): document session supervision

* test(codex): cover integration ownership

* chore(i18n): refresh supervision inventories

* fix(setup): finalize Codex activation atomically

* test(codex): narrow binding store update

* fix(sessions): preserve legacy model locks

* test(macos): serialize Codex catalog fixtures

* fix(sessions): preserve legacy lock admission

* chore(i18n): reconcile supervision metadata

* test(sessions): mark legacy lock fixture

* fix(macos): drain final Codex catalog frame

* docs: leave supervision note to release

* style(macos): satisfy Codex catalog type length

* chore: record session accessor seam owners

* fix(macos): honor configured Codex supervision

* fix(codex): preserve harness-owned model locks

* fix(codex): satisfy supervision lint gates

* chore(i18n): refresh native supervision inventory

* fix(codex): align supervision validation contracts

* fix(codex): close supervision boundary gaps

* fix(codex): preserve supervision activation contracts

* fix(codex): dispose standalone supervision runtime

* fix(codex): pin supervised source connection

* fix(plugins): bind delegated runs to exact session target

* fix(codex): scope supervised sessions to configured agents

* fix(codex): fingerprint effective supervision home

* fix(codex): normalize supervision plugin policy

* fix(codex): keep supervised bindings stable across upgrades

* fix(codex): guard all supervised binding connections

* fix(codex): preserve catalog filters and pending CAS identity

* fix(codex): preserve supervision identity for diagnostics

* fix(codex): bind uncertain commits to supervision connection

* fix(codex): satisfy supervision type boundaries

* fix(macos): reconcile current main validation

* fix(codex): handle absent runtime config in supervision

* fix(doctor): own local audio acceleration check

* fix(codex): satisfy integration lint gates

* fix(codex): satisfy lifecycle safety guards
2026-07-11 00:12:08 -07:00
Peter Steinberger 0d981095d4 refactor(codex): store app-server thread bindings in SQLite plugin state (#101210)
* test(codex): shorten placeholder auth fixture strings

* feat(plugin-state): add reject-new overflow policy for keyed namespaces

* feat(agents): thread agent identity and session generation through reset and hooks

* refactor(codex): add SQLite-backed app-server thread binding store

* refactor(codex): move app-server runtime callers onto the binding store

* refactor(codex): move conversation, entry, and thread-tool flows onto the binding store

* refactor(codex): move command handlers onto the binding store

* feat(codex): import legacy binding sidecars via doctor state migration

* fix(codex): keep doctor sidecar scan inside stateDir

* fix(codex): make binding migration landable

* chore(changelog): defer release note

* test(plugin-state): stabilize durable-capacity ordering
2026-07-07 03:03:44 +01:00
Peter Steinberger 6868cde4d4 docs: document large extension sources 2026-06-04 21:40:44 -04:00
Peter Steinberger 23dac6c263 test: keep vitest cases under one second 2026-05-31 06:51:34 +01:00
Peter Steinberger 4c33aaa86c refactor: unify OpenAI provider identity (#88451)
* refactor: unify OpenAI provider identity

* refactor: move legacy oauth sidecar doctor helpers

* test: align OpenAI fixtures after rebase

* test: clean OpenAI provider unification

* fix: finish OpenAI provider cleanup

* fix: finish OpenAI cleanup follow-through

* fix: finish OpenAI CI cleanup
2026-05-31 00:29:44 +01:00
Cathryn Lavery 730ac1a68d fix(agents/harness): validate forced plugin harness support before pinning (#74341)
Validates forced plugin harness support for the requested provider/model before pinning Codex or any other plugin harness. This prevents an explicitly forced Codex runtime from accepting unsupported OpenAI-like providers through a hardcoded bypass while preserving implicit PI fallback and CLI runtime alias passthrough.

Regression coverage covers forced Codex rejection for unsupported openai/openai-codex support, Codex provider support declarations, CLI attempt routing, pi-embedded auth/profile forwarding fakes, Testbox scenario probes, and live Docker Codex plugin E2E.

Thanks @cathrynlavery.
2026-05-27 09:59:04 +01:00