Anthropic exposes `max` as a distinct adaptive-thinking effort above
`xhigh` on Opus 4.7. Previously the validator aliased user input `max`
down to `xhigh`, so users couldn't reach the real top-tier effort
through CCS.
Extend the validator:
- Add `max` to VALID_THINKING_LEVELS and THINKING_LEVEL_RANK (rank 6,
above xhigh)
- Add `max` to THINKING_LEVEL_BUDGETS (65536, CCS-internal numeric
mapping for closest-level lookups)
- Widen ThinkingSupport.maxLevel union to include 'max'
The existing `max: 'xhigh'` alias in findClosestLevel is kept as a
graceful fallback for models whose levels list does not include `max`
(e.g. Codex `gpt-5.4`), because exact-match on validLevels takes
priority — so Opus 4.7 returns `max` directly while Codex still maps
`max` -> `xhigh`.
Update the claude.claude-opus-4-7 catalog entry to expose
`['low', 'medium', 'high', 'xhigh', 'max']` with `maxLevel: 'max'`.
Built [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
Per Anthropic docs, Claude Opus 4.7 only supports adaptive thinking;
manual `thinking.type: "enabled"` with `budget_tokens` is rejected
with HTTP 400.
Switch the claude provider's `claude-opus-4-7` entry from
`type: 'budget'` to `type: 'levels'` with the effort tiers exposed
by the API: `low | medium | high | xhigh`. The proxy is expected to
translate these into `thinking.type: "adaptive"` with the effort
parameter.
Opus 4.6 and Sonnet 4.6 keep `type: 'budget'` for now since the
deprecated mode is still functional on those models.
Built [OnSteroids](https://onsteroids.ai)
Co-Authored-By: OnSteroids <built@onsteroids.ai>
The upstream router-for-me/CLIProxyAPIPlus repo was deleted, breaking any
install/update path that resolved backend: plus. Existing users with
`backend: plus` saved in config.yaml hit 404s on every bootstrap.
Changes:
- Flip DEFAULT_BACKEND from 'plus' to 'original' (platform-detector.ts)
- Flip default cliproxy.backend in createEmptyUnifiedConfig() to 'original'
- Runtime 404 fallback: getConfiguredBackend() degrades 'plus' -> 'original'
with a one-time warning, so existing installations keep working without a
manual reconfig step
- Update CLIProxyBackend docblock to document the fallback behavior
- Update tests to match new default
Retains the 'plus' type and BACKEND_CONFIG entry for forward compatibility
once CCS self-maintains its own Plus fork.
Closes#1062
Keep settings-profile Claude launches aligned with profile-scoped
non-routing env while still stripping routing/auth values.
- build claudeRuntimeEnvVars from filtered global + settings env
- preserve CLAUDE_CODE_MAX_OUTPUT_TOKENS and model defaults for
nested settings-profile launches
- extend browser launch regression coverage to prove global_env
cannot reintroduce routing/auth values
Prevent settings-profile Claude launches from reintroducing
routing/auth env after the final env merge.
- re-strip ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, and
ANTHROPIC_API_KEY after merging envVars
- preserve model-selection env such as ANTHROPIC_MODEL and
ANTHROPIC_DEFAULT_SONNET_MODEL
- add a regression test covering explicit settings-profile
overrides that try to reintroduce routing env
Verification:
- bun test tests/unit/utils/claudecode-env-stripping.test.ts
- bun run validate
- align dev-release workflow with protected-branch bypass used by release.yml
- add a workflow regression test so checkout and release auth do not drift back to github.token
Mirrors the existing `claude-opus-4-6` cache pricing test for both
`claude-opus-4-7` and `claude-opus-4-7-thinking` to explicitly
validate cache creation/read rates in end-to-end cost calculation.
Addresses PResto atrvd/ccs#8 issue #6 (suggestion).
Built [OnSteroids](https://onsteroids.ai)
- reject pending tool_result layouts that cannot be translated without reordering user content
- keep interleaved GLMT tool_use blocks open until finalization instead of stopping early
- cover leading/interleaved tool_result regressions and interleaved streaming tool fragments
Adds a unit test verifying that `claude-opus-4-7` is registered in
the `claude` provider with its provider-specific settings:
- `thinking.zeroAllowed: false` (contrasts with AGY where it is true)
- `extendedContext: true` (1M context via Anthropic API)
Addresses PResto atrvd/ccs#8 issue #4 (suggestion).
Built [OnSteroids](https://onsteroids.ai)
Adds Claude Opus 4.7 as a new model to the AGY (Antigravity) and Claude
provider catalogs, with pricing, Cursor IDE support, and updated defaults
across the codebase.
- Add claude-opus-4-7-thinking and claude-opus-4-7 to AGY catalog
(defaultModel bumped to claude-opus-4-7-thinking)
- Add claude-opus-4-7 entry to Claude provider catalog
- Register claude-opus-4-7-thinking fork alias in CLIProxy config
(CLIPROXY_CONFIG_VERSION bumped 17 -> 18)
- Add pricing for claude-opus-4-7 and claude-opus-4-7-thinking
($5/$25 per million, matching Opus 4.6)
- Add claude-4.7-opus and claude-4.7-opus-fast-mode to Cursor catalog
- Update ANTHROPIC_DEFAULT_OPUS_MODEL in base-claude settings to 4.7
- Update Droid adapter and code-reviewer fallback models to 4.7
- Update unit tests for model-catalog and model-pricing
Opus 4.6 is retained as a supported fallback in both catalogs.
Built [OnSteroids](https://onsteroids.ai)
The previous assertion read the generated CLIProxy config.yaml directly via
getConfigPathForPort(). On the self-hosted CI runner this produced ENOENT even
though applyCliproxyRoutingStrategy returned 'config-only', indicating the
read path and write path diverged in the full test-suite context.
Verify persistence via loadUnifiedConfig() instead — that's the canonical
source mutateUnifiedConfig writes to, independent of regenerateConfig's
file-path resolution.
The SearXNG-to-DuckDuckGo fallback test inherited the caller's CCS_PROFILE_TYPE
via `...process.env`, causing the hook to take the 'native_default_profile'
skip path and produce empty stdout. All other subprocess spawns in this file
set CCS_PROFILE_TYPE to NEUTRAL_PROFILE_TYPE; this one was the outlier.
Deterministic locally when CCS_PROFILE_TYPE=default is set in the shell.
Use ComSpec-aware shell selection for escaped wrapper launches.
Apply it to the remaining Windows Claude launch paths.
Rewrite the Codex exec regression test to use scoped spies so the full suite stays isolated.
Align Windows .cmd/.bat launch behavior with the Codex detector shell contract.
This keeps escaped -c overrides intact through wrapper execution.
Adds regression coverage for the Codex runtime path and the shared Windows shell launch path.
