Commit Graph

59 Commits

Author SHA1 Message Date
VACInc
740e7687e8 fix(anthropic): don't crash models list when a configured Sonnet 5 model has no cost (#102186)
* fix(anthropic): don't crash models list when a configured Sonnet 5 model has no cost

applyAnthropicSonnet5Cost read params.model.cost.input unconditionally, so
'openclaw models list' aborted with 'Cannot read properties of undefined
(reading input)' whenever config supplied an anthropic Sonnet 5 model row
without cost metadata (e.g. an agents.defaults.models runtime binding).
Guard with optional chaining — a costless model now falls through and gets
the canonical Sonnet 5 cost applied.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(models): normalize missing Sonnet 5 costs

Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>

* chore(plugin-sdk): refresh API baseline

* ci(plugin-sdk): update surface budgets

---------

Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-07-09 22:13:56 +01:00
Vincent Koc
f305e707a3 feat(models): add Claude Mythos 5 support (#101238) 2026-07-06 17:19:49 -07:00
Vortex Openclaw
1f6ddb5df0 feat(models): add Claude Sonnet 5 support (#98254)
* feat(models): add Claude Sonnet 5 support

Co-authored-by: Ariel Bravy <ariel@vortexradar.com>

* fix(models): align Sonnet 5 validation baselines

* fix(models): satisfy Sonnet 5 CI contracts

* fix(models): enforce Sonnet 5 provider contracts

* docs(changelog): defer Sonnet 5 release note

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: Ariel Bravy <ariel@vortexradar.com>
2026-07-07 00:05:35 +01:00
Vincent Koc
2031603542 fix(providers): preserve Mythos max routing 2026-06-11 11:11:21 +09:00
Peter Steinberger
0e7b5c3429 feat(anthropic): support Claude Fable 5 adaptive thinking (#91882)
* feat(anthropic): support Claude Fable 5

* test(anthropic): tighten Fable stream fixtures

* fix(anthropic): preserve Vertex input types

* test(anthropic): use provider-ready Vertex effort

* fix(anthropic): support Fable deployment aliases

* fix(anthropic): discard incomplete Fable output

* feat(anthropic): support Fable on Bedrock

* fix(anthropic): preserve Fable reasoning contracts

* refactor(anthropic): unify canonical Claude model policy

* fix(anthropic): satisfy extension thinking types

* test(anthropic): complete canonical alias fixture

* fix(bedrock): scope thinking case declarations
2026-06-10 08:08:35 -07:00
Peter Steinberger
4fa5092cdc docs: document small extension sources 2026-06-04 21:02:07 -04:00
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
Peter Steinberger
926a165a52 fix(anthropic): bound setup token expiry 2026-05-30 14:14:13 -04:00
Peter Steinberger
1188aa3b81 feat: add Claude Opus 4.8 support (#87890)
* feat: add Claude Opus 4.8 support

* fix: omit Vertex Opus sampling overrides

* fix: preserve Opus adaptive thinking levels

* fix: clamp Anthropic max effort support

* fix: use sha256 for QA mock call ids

* fix: type Anthropic transport test model metadata

* test: update PDF model default for Opus 4.8
2026-05-29 06:10:42 +01:00
Peter Steinberger
bb46b79d3c refactor: internalize OpenClaw agent runtime (#85341)
* refactor: extract agent core package

Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts.

* refactor: extract shared llm runtime

Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.

* refactor: remove pi runtime internals

Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code.

* refactor: tighten agent session runtime

Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts.

* refactor: remove static model and pi auth paths

Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities.

* refactor: remove legacy provider compat paths

* docs: remove agent parity notes

* fix: skip provider wildcard metadata parsing

* refactor: share session extension sdk loading

* refactor: inline acpx proxy error formatter

* refactor: fold edit recovery into edit tool

* fix: accept extension batch separator

* test: align startup provider plugin expectations

* fix: restore provider-scoped release discovery

* test: align static asset packaging expectations

* fix: run static provider catalogs during scoped discovery

* fix: add provider entry catalogs for scoped live discovery

* fix: load lightweight provider catalog entries

* fix: refresh provider-scoped plugin metadata

* fix: keep provider catalog entries on release live path

* fix: keep static manifest models in release live checks

* fix: harden release model discovery

* fix: reduce OpenAI live cache probe reasoning

* fix: disable OpenAI cache probe reasoning

* ci: extend OpenAI gateway live timeout

* fix: extend live gateway model budget

* fix: stabilize release validation regressions

* fix: honor provider aliases in model rows

* fix: stabilize release validation lanes

* fix: stabilize release memory qa

* ci: stabilize release validation lanes

* ci: prefer ipv4 for live docker node calls

* fix: restore shared tool-call stream wrapper

* ci: remove legacy pi test shard alias

* fix: clean up embedded agent test drift

* fix: stabilize runtime alias status

* fix: clean up embedded agent ci drift

* fix: restore release ci invariants

* fix: clean up post-rebase runtime drift

* fix: restore release ci checks

* fix: restore release ci after rebase

* fix: remove stale pi runtime path

* test: align compaction runtime expectations

* test: update plugin prerelease expectations

* fix: handle claude live tool approvals

* fix: stabilize release validation gates

* fix: finish agent runtime import

* test: finish post-rebase agent runtime mocks

* fix: keep codex compaction native

* fix: stabilize codex app-server hook tests

* test: isolate codex diagnostic active run

* test: remove codex diagnostic completion race

# Conflicts:
#	extensions/codex/src/app-server/run-attempt.test.ts

* ci: fix full release manifest performance run id

* refactor: narrow llm plugin sdk boundary

* chore: drop generated google boundary stamps

* fix: repair rebase fallout

* fix: clean up rebased runtime references

* fix: decode codex jwt payloads as base64url

* fix: preserve shipped pi runtime alias

* fix: add scoped sdk virtual modules

* fix: decode llm codex oauth jwt as base64url

* fix: avoid stale vertex adc negative cache

* fix: harden tool arg decoding and codeql path

* fix: keep vertex adc negative checks live

* refactor: consolidate codex jwt and edit helpers

* fix: await codex oauth node runtime imports

* fix: preserve sdk tool and notice contracts

* fix: preserve shipped compat config boundaries

* fix: align codex oauth callback host

* fix: terminate agent-core loop streams on failure

* fix: keep codex oauth callback alive during fallback

* ci: include session tools in critical codeql scans

* fix: keep Cloudflare Anthropic provider auth header

* docs: redirect legacy pi runtime pages

* fix: honor bundled web provider compat discovery

* fix: protect session output spill files

* fix: keep legacy agent dir env blocked

* fix: contain auto-discovered skill symlinks

* fix: harden agent core sdk proxy surfaces

* fix: restore approval reaction sdk compat

* fix: keep live docker runs bounded

* fix: keep codex oauth redirect host aligned

* fix: resolve post-rebase agent runtime drift

* fix: redact anthropic oauth parse failures

* fix: preserve responses strict tool shaping

* fix: repair agent runtime rebase cleanup

* docs: redirect retired parity pages

* fix: bound auto-discovered resources to roots

* fix: repair post-rebase agent test drift

* fix: preserve bundled provider allowlist migration

* fix: preserve manifest-owned provider aliases

* fix: declare photon image dependency

* fix: keep provider headers out of proxy body

* fix: preserve shipped env aliases

* fix: refresh control ui i18n generated state

* fix: quote read fallback paths

* fix: preview edits through configured backend

* test: satisfy core test typecheck

* fix: preserve ZAI usage auth fallback

* test: repair codex diagnostic test

* fix: repair agent runtime rebase drift

* test: finish embedded runner import rename

* fix: repair agent runtime rebase integrations

* test: align compaction oauth fallback expectations

* fix: allow sdk-auth session models

* fix: update doctor tool schema import

* fix: preserve bedrock plugin region

* fix: stream harmony-like prose immediately

* ci: include session runtime in codeql shards

* fix: repair latest rebase integrations

* fix: honor explicit codex websocket transport

* fix: keep openai-compatible credentials provider-scoped

* fix: refresh sdk api baseline after rebase

* fix: route cli runtime aliases through openclaw harness

* test: rename stale harness mock expectation

* test: rename embedded agent overflow calls

* test: clean embedded auth test wording

* test: use openclaw stream types in deepinfra cache test

* fix: refresh sdk api baseline on latest main

* fix: honor bundled discovery compat allowlists

* fix: refresh sdk api baseline after latest rebase

* fix: remove stale rebase imports

* test: rename stale model catalog mock

* test: mock renamed doctor runtime modules

* fix: map canonical kimi env auth

* fix: use internal model registry in bench script

* fix: migrate deepinfra provider catalog entry

* fix: enforce builtin tool suppression

* fix: route compaction auth and proxy payloads safely

* refactor: prune unused llm registry leftovers

* test: update codex hooks session import

* test: fix model picker ci coverage

* test: align model picker auth mock types
2026-05-27 19:24:04 +01:00
Peter Steinberger
4c210e22fa Adapt image compression quality by model (#85742)
* feat: adapt image compression quality

* refactor: move image limits into model metadata

* test: cover adaptive image downscaling

* test: cover image tool live providers

* fix: apply media metadata to all image paths

* fix: align providerless image compression

* fix: add chutes runtime image limits

* fix: optimize image data urls with model limits

* fix: type media metadata merge

* fix: optimize data url byte limits after decode

* fix: preserve data url optimizer fallback

* fix: keep low-side image compression fallbacks

* fix: enforce data url image compression policy

* fix: preserve gif data url media policy

* fix: satisfy adaptive image type checks

* test: keep cron provider-runtime mock current
2026-05-23 21:45:55 +01:00
Peter Steinberger
b6530beb05 fix: prune retired model catalog entries 2026-05-23 16:46:59 +01:00
haoyu-haoyu
353dfeb108 fix(anthropic): migrate 1M context to GA handling
* feat(anthropic): migrate 1M context from beta to GA

Anthropic has graduated the 1M context window from beta to GA.
This commit:

- Stops injecting the context-1m-2025-08-07 beta header when
  context1m: true is configured
- Removes the OAuth token skip logic that was needed because
  Anthropic previously rejected the context-1m beta with OAuth auth
  (OAuth now supports 1M natively)
- Strips the legacy beta header from user-configured anthropicBeta
  arrays to prevent sending a stale header
- Removes the now-unused isAnthropic1MModel helper,
  ANTHROPIC_1M_MODEL_PREFIXES constant, and logger import from
  the stream wrappers

The context1m config param continues to be respected for context
window sizing in context.ts — only the beta header injection is
removed.

Closes #45550 (Phase 1)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(anthropic): migrate 1M context handling to GA

* fix(clownfish): address review for ghcrawl-156721-autonomous-smoke (1)

* fix(anthropic): restrict ga 1m context models

* docs(anthropic): align ga 1m context guidance

* fix(anthropic): normalize ga 1m model metadata

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-05-23 12:29:31 +01:00
Josh Avant
f6de2b3885 Fix Anthropic CLI auth routing for shorthand refs (#84374)
* Fix Anthropic CLI auth routing

* Add changelog for Anthropic CLI routing
2026-05-19 19:58:07 -05:00
Andy Ye
98cc6df7ff fix(anthropic): preserve Claude image capability (#83756)
Summary:
- The PR adds Anthropic Claude 4.x image-capability normalization for stale text-only resolved model rows, regression tests for provider and fallback model resolution, and a changelog entry.
- Reproducibility: yes. for source-level reproduction: current main gates native images on model.input includi ... s text-only. I did not run the command locally because this review was constrained to read-only inspection.

Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(anthropic): preserve Claude image capability

Validation:
- ClawSweeper review passed for head 06dd378ea3.
- Required merge gates passed before the squash merge.

Prepared head SHA: 06dd378ea3
Review: https://github.com/openclaw/openclaw/pull/83756#issuecomment-4482116499

Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
2026-05-18 22:16:01 +00:00
Alex Knight
c438dadc5c Fix Claude CLI runtime migration for gateway turns (#82546)
Summary:
- The PR adds model-scoped `claude-cli` runtime policy to Anthropic CLI migration/default backfill, updates the gateway CLI live-smoke config, tests, and changelog.
- Reproducibility: yes. source inspection gives a high-confidence reproduction path: current main writes `clau ... del/provider-scoped runtime policy. I did not run a live Telegram/Dashboard repro in this read-only review.

Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.

Validation:
- ClawSweeper review passed for head 62cf54484f.
- Required merge gates passed before the squash merge.

Prepared head SHA: 62cf54484f
Review: https://github.com/openclaw/openclaw/pull/82546#issuecomment-4466676206

Co-authored-by: Alex Knight <15041791+amknight@users.noreply.github.com>
2026-05-16 11:54:48 +00:00
Peter Steinberger
2d0c3750d8 test: guard extension provider helpers 2026-05-11 21:01:56 +01:00
Peter Steinberger
4b6e1373f6 test: guard extension lookup helpers 2026-05-11 19:38:00 +01:00
Peter Steinberger
97c1fd51e4 test: tighten anthropic provider assertions 2026-05-10 19:57:49 +01:00
Peter Steinberger
428cc54164 fix(anthropic): backfill haiku api key allowlist 2026-05-10 05:09:12 +01:00
Peter Steinberger
9ef37d1907 test: tighten assertions and harness coverage 2026-05-08 05:28:12 +01:00
Peter Steinberger
1ef85c7d4c test: make suites safe without isolation (#78834)
* test: make suites safe without isolation

* fix: narrow auth profile credential types

* test: inject channel module loader factory locally
2026-05-07 08:43:29 +01:00
Peter Steinberger
f37fba8d5a fix(anthropic): reject uppercase dynamic model ids 2026-05-07 05:48:14 +01:00
Peter Steinberger
f34b41f198 refactor: split plugin sdk test helpers 2026-04-28 01:14:19 +01:00
Peter Steinberger
0df6e5a473 refactor: expose plugin test helpers via sdk 2026-04-27 23:45:26 +01:00
Peter Steinberger
5b9be2cdb1 fix: migrate agent runtime config 2026-04-26 08:12:44 +01:00
Ayaan Zaidi
76dc66f5fa fix(models): use synthetic auth expiry for status 2026-04-26 09:21:06 +05:30
Neerav Makwana
ad27e0069d fix(models): avoid externalizing Claude CLI auth 2026-04-26 09:21:06 +05:30
Neerav Makwana
911fcb47f1 fix(models): reflect Claude CLI auth status 2026-04-26 09:21:06 +05:30
Vincent Koc
aa27e27f36 fix(models): normalize provider runtime selection (#71259)
* fix(models): normalize provider runtime selection

* fix(models): reverse codex-only runtime migration

* fix(models): default runtime selection to pi

* fix(status): label model runtime clearly

* fix(status): align pi runtime label

* fix(plugins): align tool result middleware runtime naming

* fix(models): validate runtime overrides
2026-04-24 16:56:49 -07:00
Val Alexander
9ea5484fa1 fix: normalize opus 4.7 context window
Normalize Anthropic-owned Opus 4.7 context reporting to 1M while keeping inferred and bare discovery paths conservative.

- normalize Anthropic and claude-cli Opus 4.7 runtime/status context metadata to 1M
- keep inferred-provider and bare discovery ids on discovered conservative limits
- add regression coverage for provider, lookup, status, and discovery-cache paths
- keep the Telegram abort-signal wrapper typing narrow so changed-scope validation stays green
2026-04-22 14:58:16 -05:00
Peter Steinberger
f1805ab54d fix: centralize provider thinking profiles 2026-04-21 09:13:35 +01:00
Peter Steinberger
0d305839e5 fix(anthropic): scope api default normalization 2026-04-21 07:48:21 +01:00
Peter Steinberger
6ce17db11a fix: gate max thinking by model support 2026-04-21 07:02:43 +01:00
Peter Steinberger
e4adb0b0e3 fix: hide adaptive think option for GPT models 2026-04-21 06:19:29 +01:00
Peter Steinberger
a2753e2d9f fix: keep Opus 4.7 effort separate from adaptive thinking 2026-04-17 01:26:11 +01:00
Peter Steinberger
c73a6d2f68 feat: support xhigh for Claude Opus 4.7 2026-04-17 01:26:11 +01:00
Peter Steinberger
628b454eff feat: default Anthropic to Opus 4.7 2026-04-16 16:12:06 +01:00
Peter Steinberger
f2a710ce63 fix(ci): align stale test expectations 2026-04-06 16:53:21 +01:00
Peter Steinberger
ef923805f5 Revert "refactor(cli): remove custom cli backends"
This reverts commit 6243806f7b.
2026-04-06 13:40:42 +01:00
Peter Steinberger
1a47675e6c fix: restore check after CLI seam cleanup 2026-04-05 19:06:34 +01:00
Peter Steinberger
6243806f7b refactor(cli): remove custom cli backends 2026-04-05 18:04:48 +01:00
Peter Steinberger
eb8f0e1bf2 fix(ci): restore plugin sdk exports and ACP typing 2026-04-05 15:44:43 +01:00
Peter Steinberger
71fa5f481d test: split cli backend coverage by ownership 2026-04-05 15:20:15 +01:00
Vincent Koc
9efc033434 fix(anthropic): seed claude-cli model switches 2026-04-05 14:18:02 +01:00
Vincent Koc
1a7c2a9bc8 fix(auth): persist claude-cli login profiles 2026-04-05 14:03:36 +01:00
Peter Steinberger
1fb0b4f557 fix: avoid stale claude-cli auth fallback (#61234) (thanks @darkamenosa) 2026-04-05 18:19:33 +09:00
Tuyen
7e724c6140 Anthropic: seed claude-cli runtime auth on setup 2026-04-05 18:19:33 +09:00
Tuyen
72ba7c8995 Anthropic: address claude-cli review feedback 2026-04-05 18:19:33 +09:00
Tuyen
cd348659ce Anthropic: fix claude-cli runtime auth 2026-04-05 18:19:33 +09:00