Integrated into release/v3.8.29 — Cursor Cloud Agent (cursor-cloud) via official api.cursor.com REST API key, 4th cloud agent mirroring Devin/Jules.
Pre-merge work done on the PR branch (fix-in-place):
- Wired cursor-cloud into the dashboard UI (CLOUD_AGENTS dropdown), health PROVIDER_NAMES, and lobeProviderIcons — it was API-usable but not selectable in the UI and rendered with the Jules fallback.
- Fixed cloud-agent-health-api.test.ts which asserted exactly 3 agents (the PR added a 4th) -> updated count/order + added cursor-cloud coverage.
- file-size baseline: page.tsx 913->922.
FOLLOW-UP (Rule #18): the REST endpoint paths/field names follow Cursor's documented Cloud Agents v0 API but still need a live validation run against a real Cursor API key. The integration is additive/opt-in and baseUrl is overridable per-credential, so any path/version correction needs no code change. Thanks @MRDGH2821 for the issue (#4227).
Integrated into release/v3.8.29 — remove vestigial SLM seam (createSLMStub/SLMInterface) + dead estimateTokensForStats alias. Validated: ultra.test.ts 39/39 green, zero code callers of the removed symbols.
* feat(sse): adapt the Claude flow to Opus 4.7+ adaptive-thinking + fixed-sampling contract
Claude Opus 4.7 and later (Opus 4.7/4.8, Fable 5) changed the Messages API contract:
manual extended thinking was removed (`thinking.type:"enabled"` or ANY `budget_tokens`
returns 400 — adaptive-only, steered by `output_config.effort`) and non-default
`temperature`/`top_p`/`top_k` now return 400 (sampling is fixed). OmniRoute still emitted
both shapes, so OpenAI-format `reasoning_effort` low/medium/high and any client-supplied
sampling param could hard-400 on the most-used provider.
- modelSpecs: new `adaptiveThinkingOnly` flag + `isAdaptiveThinkingOnly()` on opus-4-7/4-8/fable-5
- translator: `reasoning_effort` (every level) -> adaptive + `output_config.effort` for those models
- chatCore: `normalizeClaudeAdaptiveThinking` catch-all collapses residual manual thinking
(passthrough legacy shape / per-model defaults) to `{type:"adaptive"}`, keyed on the model
- registry: strip `temperature`/`top_p`/`top_k` for opus-4-7/4-8/fable-5 (claude + anthropic ids)
Pre-4.7 models (Opus 4.6/4.5, Sonnet, Haiku) keep manual budgets and sampling params.
TDD: +27 cases (adaptive-thinking-normalize, sampling-params, translator). typecheck/lint/file-size green.
* docs(changelog): note Claude Opus 4.7+ adaptive-thinking + fixed-sampling fixes (#4230)
Integrated into release/v3.8.29 (round 7). Studio shows a real engine node for single-engine compression runs via ensureEngineBreakdown (new pure leaf engineBreakdown.ts). Reconciled the file-size baseline (chatCore.ts 5060->5063) + union-merged with the #4202 zenmux rebaseline key after release drift. Validated locally: file-size gate OK + 3/3 tests + typecheck:core clean.
Integrated into release/v3.8.29 (round 7). Media serviceKinds derived from backend registries (single source of truth) unioned with declared kinds; listing + detail pages use the same resolver (no 'listed but 404'). Surfaces MiniMax (tts/video/music) + ~48 previously-invisible media providers. Validated locally: 6/6 tests + typecheck:core clean.
Integrated into release/v3.8.29 (round 7). TPROXY decrypt 4b/N: local-only route (/api/tools/agent-bridge/tproxy, LOCAL_ONLY per routeGuard) + dedicated trust-store CA installer (execFileWithPassword, no shell). Validated locally: 12/12 tests + typecheck:core clean (test-unit does not run on release PRs).
Singleton lifecycle around the decrypt-capable transparent listener (#4200):
builds the dynamic CA (#4173), gates on native-addon availability, holds the
single running handle, counts interceptions, and exposes start / stop / status
for a local-only route (4b) to drive.
The OS trust-store mechanism is deliberately not baked in: installCa / uninstallCa
are injected by the caller (the route / VPS e2e provides the real installer, which
needs its own trust-store slot so it does not clobber the static MITM cert). The
manager therefore never mutates the trust store itself and stays unit-testable
without root or the native addon.
- startCaptureMode: rejects when unavailable or already running; builds the CA;
wires the injected installCa/uninstallCa through to the decrypt listener.
- stopCaptureMode: stops the handle (close + uninstall CA + revert), idempotent.
- getCaptureStatus: running / available / startedAt / interceptCount / onPort.
Route + real trust-store installer + Traffic Inspector UI tab + VPS
e2e-with-decrypt + addon prebuilds follow (4b+).
* fix(compression): bound mcpAccessibility maxTextChars on the live read path
smartFilterText reserves 300 chars for the truncation tail, so a maxTextChars at/below that
makes headSize <= 0 and the whole tool result is replaced by the notice (total data loss). Two
gaps let a bad value reach the engine: the DB normalizer floored maxTextChars only at > 0, and
the live MCP-server read path (readMcpAccessibilityConfig) did a raw {...DEFAULT, ...parsed}
spread with no bounding at all.
Centralize the floors in a shared clampMcpAccessibilityConfig (engine layer) used by both the DB
normalizer and the server read path; values in (0, 600) fall back to the default. Export the
tail-reserve constant (300) and use it in smartFilterText so the engine and the bounds stay in
sync. The F5.3 headSize >= 0 clamp stays as a second layer.
Defense-in-depth today (the config isn't writable via the settings API yet — making it
configurable is a tracked follow-up in the compression-completeness work); this closes the
data-loss path for when it lands.
Part of the compression "100% functional" program (audit follow-up).
* chore(quality): bump server.ts file-size baseline 1457->1458 (#4206 +1 import)
The RTK R5 grouping strategy (collapse near-equivalent consecutive lines) is read by the
engine (config.enableGrouping / groupingThreshold) but was unreachable in production: the
rtkConfigSchema (.strict()) rejected the two fields on write and normalizeRtkConfig dropped
them on read, so they could never be anything but undefined.
Add enableGrouping (bool) + groupingThreshold (int, 2..100, default 3) to DEFAULT_RTK_CONFIG,
normalizeRtkConfig, and rtkConfigSchema so the feature is actually settable and survives the
DB round-trip. Default stays OFF — no behavior change for existing configs.
Part of the compression "100% functional" program (audit follow-up).
* fix(compression): broaden RTK raw-output secret redaction (Basic/Proxy auth + keys)
F5.3 follow-up. SECRET_PATTERNS missed Authorization / Proxy-Authorization with
Basic (curl -v emits "Basic <base64>") and credential field names that don't
contain token/secret/password as a substring (private_key, access_key, credential).
Add a (Proxy-)Authorization Bearer|Basic pattern and broaden the key-name
alternation. All patterns are flat (no nested quantifiers → no ReDoS).
* fix(compression): drop ReDoS-prone patterns from custom RTK filters
F5.3 follow-up. Custom filters (DATA_DIR/rtk/filters.json) carry user-supplied
regex strings compiled and run against untrusted tool output; a nested unbounded
quantifier ((a+)+, (a*)*, ([a-z]+)+ …) can cause catastrophic backtracking.
validateRtkFilter now drops such patterns via a conservative, dependency-free
heuristic (isReDoSProne) applied to every regex-bearing array in the canonical and
legacy filter shapes. safe-regex would be ideal but is not installable in this
symlinked worktree; the heuristic catches the common single-group nested-quantifier
shapes and is itself linear.
Surfaced (not fixed here): a canonical pack filter omitting `preserve` crashes
validateRtkFilter because rtkFilterPreserveSchema.default({}) leaves the inner arrays
undefined — tracked as a pre-existing fragility.
Integrated into release/v3.8.29 — D7a round-robin sticky state extracted byte-identically to combo/rrState.ts; reconciled with #4194 (baseline combo.ts -> 3398, resolving the over-cap left by #4194).
Integrated into release/v3.8.29 — reconciled with #4188 (chatCore split part A): both byte-identical extractions stacked; baseline chatCore.ts -> 5060.
