llx-0.0.1
x86_64-linux.packages-default
· build #9
· raw
unpackPhase
1unpacking source archive /nix/store/6iv6bh2ny9xwg5nb2g9h0qy3sbf253ds-source2source root is sourceconfigurePhase
3no configure script, doing nothingbuildPhase
4Picked up JAVA_TOOL_OPTIONS: -Duser.home=/build/tmp.GYho0QmGty5Picked up JAVA_TOOL_OPTIONS: -Duser.home=/build/tmp.GYho0QmGty6GUARDRAILS IS ENABLED. RUNTIME PERFORMANCE WILL BE AFFECTED.7Mode: :runtime config: {:throw? true, :guardrails/use-stderr? true}8Guardrails was enabled because the guardrails.enabled property is set to a (any) value.9--- unit (clojure.test) ---------------------------10ol.llx.agent.driver-test11 prompt-continues-through-queued-steering-without-stalling-test12 abort-cancels-tool-execution-and-returns-to-idle-test13 abort-drops-stale-llm-events-and-allows-reuse-test1415ol.llx.ai.errors-test16 extracts-retry-after-seconds-header17 content-filter-is-not-recoverable18 quota-exceeded-is-not-recoverable19 retry-delay-uses-linear-backoff-for-connection-errors20 retry-after-ms-takes-priority21 predicates-match-error-categories22 llx-error? matches structured errors23 recoverable? matches recoverable errors24 rate-limit-error?25 quota-exceeded-error?26 rate-limited-error?27 timeout-error?28 client-error?29 transient-error?30 should-retry-respects-max-retries31 provider-error-with-custom-recoverability32 retry-delay-uses-server-retry-after-for-rate-limit33 http-status-429-with-quota-body-returns-quota-exceeded34 model-not-found-is-not-recoverable35 http-status->error-maps-common-codes36 400 -> invalid-request37 401 -> authentication-error38 403 -> authorization-error39 404 -> model-not-found40 408 -> timeout41 500 -> server-error42 502 -> server-error43 503 -> server-error44 retry-delay-uses-exponential-backoff-for-rate-limit-without-header45 timeout-error-is-recoverable46 retry-delay-adds-jitter-for-server-errors47 http-status-429-with-quota-and-retry-after-returns-rate-limit48 connection-error-is-recoverable49 retry-loop-async-exhausts-retries-and-throws50 extracts-x-ratelimit-reset-after-header51 retry-loop-async-emits-retry-scheduled-trove-signal52 http-status-unknown-4xx-returns-non-recoverable-provider-error53 returns-nil-when-no-header54 http-status-429-without-quota-returns-rate-limit55 extract-retry-after-from-message-returns-nil-when-missing56 retry-loop-async-retries-transient-and-succeeds57 retry-loop-async-does-not-retry-client-errors58 extracts-retry-after-ms-header59 authentication-error-is-not-recoverable60 retry-loop-async-succeeds-on-first-attempt61 retry-delay-exceeded-is-not-recoverable62 http-status-unknown-5xx-returns-recoverable-provider-error63 caps-at-max-seconds64 server-error-is-recoverable65 retry-loop-async-fails-when-server-retry-delay-exceeds-cap66 rate-limit-error-has-correct-type-and-recoverable67 should-retry-rejects-client-errors68 extract-retry-after-from-message-parses-seconds69 should-retry-allows-transient-errors70 invalid-request-is-not-recoverable7172ol.llx.ai.adapters.google-generative-ai-test73 reasoning-config-disables-thinking-by-default-for-gemini-3-pro74 build-request-emits-provider-payload-trove-signal75 google-normalizer-matches-upstream-issue-1022-test-id-under-gate76 adapter-registers-tool-call-id-normalizer-with-model-id-gate77 decode-event-stream-usage-calculates-costs78 reasoning-config-gemini-3-flash-uses-level79 thought-signature-alone-is-not-thinking80 build-request-tool-result-image-forwarding-by-model-capability81 gemini-3 multimodal model forwards image in functionResponse parts82 text-only model drops images from functionResponse83 reasoning-config-disables-thinking-by-default-for-gemini-384 stream-error-normalization-contract85 reasoning-config-gemini-3-pro-clamps-low-effort86 map-stop-reason-fail-fast-on-unknown87 unknown finish reason in stream decode fails fast88 reasoning-config-disables-thinking-by-default-for-gemini-2589 decode-event-stream-contract90 finalize-throws-on-unknown-stop-reason91 reasoning-config-gemini-25-pro-budget-differs-from-flash92 build-request-uses-custom-thinking-budgets93 build-request-converts-canonical-context-to-google-payload94 reasoning-config-gemini-3-pro-uses-level95 build-request-preserves-valid-emoji-surrogate-pairs96 build-request-gemini-3-preserves-unsigned-tool-calls-with-sentinel97 decode-event-tool-call-missing-args-defaults-to-empty-map98 reasoning-config-omitted-when-model-not-reasoning99 open-stream-non-2xx-throws-structured-error100 build-request-sanitizes-unpaired-surrogates-in-user-and-system101 finalize-calculates-usage-costs102103ol.llx.ai.registry-test104 registry-patterns105 immutable registry returns new value106 mutable registry107 dynamic registry108 registry-operations109 unregister and clear adapters110 rejects invalid api value111112ol.llx.ai.guardrails-contract-test113 guardrails-enforces-boundary-shapes114 decode-event boundary is enforced for all adapters115116ol.llx.ai.utils.overflow-test117 context-overflow-detection118 detects explicit provider messages119 detects 400/413 status codes120 detects silent overflow with context window121 false for non-overflow errors122123ol.llx.ai.models-test124 model-utility-functions125 calculate-cost126 supports-xhigh?127 direct anthropic 4.6 models use the larger context window128 models-equal?129 model-registry-and-lookup130131ol.llx.ai.adapters.openai-responses-test132 decode-event-message-output-item-done-encodes-versioned-text-signature133 normalize-tool-call-id-trims-trailing-underscores-and-enforces-fc-prefix134 decode-event-response-failed-includes-provider-error-details135 cache-retention-mapping136 cache-control none omits both prompt cache fields137 cache-control long sets 24h retention for direct api.openai.com138 cache-control long does not set retention for non-openai base url139 normalize-tool-call-id-preserves-same-provider-item-ids140 build-request-sanitizes-unpaired-surrogates-in-user-text141 decode-event-stream-contract142 normalize-tool-call-id-matches-upstream-issue-1022-test-id143 normalize-tool-call-id-normalizes-pipe-ids-and-preserves-pairing144 normalize-tool-call-id-gates-by-provider-allowlist145 finalize-calculates-tier-adjusted-cost-when-usage-present146 build-request-emits-provider-payload-trove-signal147 finalize-maps-responses-status-to-canonical-stop-reason148 decode-event-reasoning-summary-part-done-requires-summary-part149 build-request-disables-reasoning-when-no-reasoning-opts150 build-request-preserves-valid-emoji-surrogate-pairs151 finalize-throws-on-unknown-stop-reason152 normalize-tool-call-id-hashes-foreign-item-ids153 build-request-converts-context-to-openai-responses-input154 stream-error-normalization-contract155 build-request-replays-versioned-text-signature-metadata156157ol.llx.agent-test158 tool-signal-and-event-schema-tightening-test159 custom-message-schema-may-reference-provided-schemas-test160 command-wrappers-dispatch-through-driver-run-test161 prompt dispatches vector messages162 continue dispatches the continue command163 abort dispatches the abort command164 state mutators dispatch commands165 rehydrate-agent-custom-message-validation-test166 create-agent-requires-env-contract-test167 tool-call-schema-contract-test168 prompt-validates-messages-test169 create-agent-ignores-initial-state-option-test170 set-schema-config-ignores-nil-fields-test171 nil schema-registry preserves the current user registry172 nil custom-message-schemas preserves the current dispatch map173 custom-message-public-api-validation-test174 effect-execute-tool-tool-call-schema-test175 set-model-validates-model-shape-test176 tool-and-pending-tool-call-schema-test177 set-schema-config-clears-user-additions-without-removing-canonical-schemas-test178 create-agent-initializes-state-test179 set-schema-config-updates-custom-message-validation-on-live-agent-test180 tool-schema-tightening-on-commands-and-state-test181 :ol.llx.agent/command-set-tools expects :ol.llx.agent/tool entries182 :ol.llx.agent/create-agent-opts expects :ol.llx.agent/tool entries in :tools183 :ol.llx.agent.loop/state expects :ol.llx.agent/tool entries in :tools184 create-agent-rejects-missing-custom-schema-registration-test185 custom-message-schemas-validate-message-and-messages-test186 :ol.llx.agent/custom-message-schemas requires namespace-qualified dispatch keys187 :ol.llx.agent/message rejects custom roles when not registered188 :ol.llx.agent/message accepts registered custom role189 :ol.llx.agent/messages accepts canonical + registered custom messages190 :ol.llx.agent/messages rejects invalid registered custom message payloads191 canonical messages remain valid with custom registrations enabled192 rehydrate-agent-uses-snapshot-test193 subscribe-unsubscribe-test194 create-agent-default-convert-to-llm-test195196ol.llx.ai.transform-messages-test197 does-not-duplicate-existing-synthetic-tool-result198 tool-call-id-normalization-avoids-collision-for-mistral199 user-interruption-inserts-only-missing-tool-results200 tool-call-id-normalization-propagates-to-tool-result201 google-gated-normalization-rewrites-assistant-and-tool-result-ids202 cross-model-replay-converts-thinking-and-drops-signatures203 same-model-replay-preserves-thinking-and-signatures204 skipped-assistant-turns-with-error-or-aborted-stop-reasons205 missing-tool-results-get-synthetic-error-message206 fixture-for-aborted-reasoning-skips-aborted-turn207 aborted assistant turn is removed from replay208 synthetic-tool-result-uses-real-time-when-clock-missing209210ol.llx.agent.loop-test211 streaming-transition-llm-done-with-follow-up-queue-starts-next-turn-test212 starts a new turn from follow-up messages when no steering exists213 continues the run with another llm call214 idle-transition-prompt-start-test215 appends messages and transitions to streaming216 emits agent-start, turn-start, message events, and call-llm217 call-llm receives the full message history including new messages218 tool-executing-transition-tool-error-last-tool-test219 clears pending-tool-calls220 records error result and resumes llm221 tool-executing-transition-tool-update-test222 handle-command-set-steering-mode-test223 handle-command-set-thinking-level-test224 tool-executing-transition-unknown-signal-test225 handle-command-steer-test226 handle-command-set-tools-test227 closed-transition-is-terminal-test228 any signal returns state unchanged with no effects229 initial-state-has-expected-shape-test230 handle-command-set-model-test231 streaming-transition-llm-error-test232 transitions to idle and sets error233 emits message-end and turn-end234 step-abort-from-tool-executing-to-idle-test235 step-abort-from-streaming-to-idle-test236 abort signal from streaming237 abort command from streaming238 handle-command-set-follow-up-mode-test239 agent-end-emitted-on-error-to-idle-test240 idle-transition-continue-start-test241 appends messages and transitions to streaming242 emits turn-start (no agent-start), message events, and call-llm243 call-llm receives the full message history including new messages244 streaming-transition-llm-done-with-steering-queue-starts-next-turn-test245 moves directly into the next streaming turn246 appends the finished assistant message and queued steering message247 continues the run by ending the turn and scheduling more llm work248 handle-command-prompt-when-not-idle-test249 handle-command-clear-follow-up-queue-test250 tool-executing-transition-tool-result-last-tool-test251 clears pending-tool-calls252 appends result to messages and resumes llm253 tool-executing-transition-tool-result-with-steering-all-mode-dequeues-all-test254 dequeues all steering messages in :all mode255 step-tool-loop-test256 state progression through tool loop257 tool completion resumes llm258 final state has all messages259 agent-end emitted on final transition to idle260 handle-command-continue-steering-before-follow-up-test261 tool-executing-transition-tool-result-with-remaining-test262 processes result and keeps remaining tools263 appends result to messages264 emits tool-execution-end, message events, and starts next tool265 route-from-streaming-test266 idle routes to idle267 tool-executing routes to tool-executing268 closed routes to closed269 streaming stays streaming270 streaming-transition-unknown-signal-test271 step-prompt-when-streaming-is-rejected-test272 route-from-idle-test273 streaming-transition-llm-start-test274 agent-end-not-emitted-on-streaming-to-tool-executing-test275 handle-command-append-message-test276 command-predicate-test277 recognizes commands278 rejects signals279 rejects events280 handle-command-set-system-prompt-test281 handle-command-reset-test282 handle-command-replace-messages-test283 tool-executing-transition-abort-test284 transitions to idle and clears pending-tool-calls285 emits turn-end286 streaming-transition-llm-done-no-tools-test287 transitions to idle and clears stream-message288 appends the final message289 emits message-end and turn-end290 streaming-transition-llm-chunk-test291 handle-command-clear-messages-test292 handle-command-abort-when-idle-test293 step-signal-llm-done-with-tools-test294 tool-executing-transition-tool-result-with-steering-interrupts-remaining-tools-test295 clears pending tool calls and keeps remaining steering queued in one-at-a-time mode296 appends current tool result, synthetic skipped results, and dequeued steering message297 emits current result events, skipped tool lifecycle events, steering message events, and resumes llm298 tool-executing-transition-tool-error-with-steering-interrupts-remaining-tools-test299 does not execute the next real tool and resumes llm after synthetic skipped results300 keeps one steering message queued in one-at-a-time mode301 appends error result, skipped tool results, and dequeued steering message302 handle-command-continue-empty-queues-test303 handle-command-follow-up-test304 agent-end-not-emitted-when-staying-idle-test305 streaming-transition-abort-test306 transitions to idle and clears stream-message307 emits message-end and turn-end308 idle-transition-invalid-signal-test309 step-signal-llm-done-no-tools-to-idle-test310 handle-command-set-schema-config-test311 handle-command-continue-with-follow-up-all-mode-test312 handle-command-continue-with-steering-all-mode-test313 step-prompt-from-idle-to-streaming-test314 step-full-happy-path-test315 state progression316 final state has both messages317 agent-end is emitted on final step318 agent-end is not emitted on intermediate steps319 streaming-transition-llm-done-with-tools-test320 transitions to tool-executing321 sets pending-tool-calls and clears stream-message322 appends the message323 emits message-end, tool-execution-start, and execute-tool324 handle-command-clear-steering-queue-test325 agent-end-emitted-on-streaming-to-idle-test326 route-from-tool-executing-test327 with pending tool calls stays tool-executing328 without pending tool calls routes to streaming329 closed routes to closed330 handle-command-clear-all-queues-test331 handle-command-continue-when-not-idle-test332 streaming-transition-llm-done-prefers-steering-over-follow-up-test333 uses steering messages first and leaves follow-up queued334 continues immediately with call-llm335 handle-command-continue-with-steering-one-at-a-time-test336 tool-executing-transition-tool-error-with-remaining-test337 records error result and keeps remaining tools338 emits tool-execution-end, message events, and starts next tool339 handle-command-prompt-from-idle-test340 handle-command-abort-when-streaming-test341 handle-command-continue-with-follow-up-one-at-a-time-test342343ol.llx.ai.oauth.cli-test344 login-command-writes-auth-json-in-current-working-directory345 persists oauth credentials to auth.json346347ol.llx.ai.utils.tool-validation-test348 validate-tool-call349 success case350 tool not found351 validation errors are structured352 missing required field353 human-readable error message includes tool name and arguments354 tool-not-found error message includes tool name355 coerces string values using the input schema356 applies schema defaults from the input schema357 resolves custom schema references from the active registry358359ol.llx.ai.utils.rate-limit-test360 rate-limited-detection361 detects structured error types362 detects provider message patterns363 false for non-rate-limit errors364365ol.llx.ai.utils.unicode-test366 truncate-limits-string-length367 truncates only when input exceeds max-len368 coerces nil to empty string369 sanitize-payload-deep-walks-data-structures370 sanitizes strings nested in maps, vectors, and mixed structures371 real-world LinkedIn data with emoji preserved372 unpaired surrogates stripped from tool result content373 handles bare string input374 handles bare vector input375 passes through non-string leaves unchanged376 sanitize-surrogates-handles-surrogate-edge-cases377 preserves valid emoji surrogate pairs378 removes unpaired high surrogate379 removes unpaired low surrogate380 removes high surrogate at end of string381 removes multiple unpaired surrogates in one string382 preserves mixed content: emoji, CJK, math symbols, special quotes383 handles nil and empty input384 passes through plain ASCII unchanged385386ol.llx.ai.oauth.openai-codex-test387 login-openai-codex-state-mismatch-fails388 login-openai-codex-bind-failure-falls-back-to-manual-input389 account-id-extraction390 login-openai-codex-manual-fallback391 parse-authorization-input-cases392 accepts full redirect URL393 accepts code#state format394 accepts query-string format395 falls back to raw code396397ol.llx.ai.model-catalog.generate-test398 build-catalog-deep-merges-nested-override-fields399 render-generated-source-is-stable400 build-catalog-rejects-invalid-override-shapes401 build-catalog-is-deterministically-sorted402 build-catalog-rejects-duplicate-normalized-source-keys403 generate-models-uses-checked-in-overrides-and-emits-openai-codex-models404 build-catalog-normalizes-supported-providers-only405 generate-models-writes-artifact-using-injected-paths406 build-catalog-supports-provider-qualified-override-keys407 build-catalog-rejects-provider-change-for-existing-id408409ol.llx.ai.oauth-test410 get-oauth-api-key-behavior411 returns nil for missing provider credentials412 returns existing api key when credential is not expired413 refreshes expired credential before returning api key414 refresh-oauth-token-dispatch415 oauth-provider-registry-operations416417ol.llx.ai.client-test418 stream-rejects-unsupported-xhigh-with-structured-error419 complete-retries-on-transient-error420 complete-transforms-context-before-build-request421 stream-simple-wrapper-normalizes-options422 unified-opts->request-opts-normalizes-unified-shape423 stream-retries-open-stream-on-transient-error424 complete-does-not-retry-on-client-error425 stream-close-delegates-to-runtime-cancel-fn426 complete-simple-wrapper-normalizes-options427 stream-returns-csp-channel428 complete-emits-error-lifecycle-trove-signals429 complete-allows-xhigh-for-supported-model430 unified-opts->request-opts-rejects-provider-shape-in-unified-opts431 complete-surfaces-unknown-openai-completions-stop-reason-as-error-message432 complete-rejects-malformed-adapter-finalize-result433 complete-simple-wrapper-normalizes-openai-responses-reasoning-to-effort434 complete-retries-without-thread-sleep-hook435 complete-returns-deferred436 complete-emits-lifecycle-trove-signals437 complete-rejects-unsupported-xhigh-with-structured-error438 complete-openai-completions-non-2xx439 opts-registry-overrides-env-registry440441ol.llx.ai.schema-test442 config-schema443 accepts known provider config444 accepts unknown provider keys445 options-schema-allows-provider-specific-option-keys446 options-schema447 accepts valid unified request options448 accepts unknown unified request option keys449 accepts valid provider request options including provider-specific keys450 tool input schema field descriptions survive json schema conversion451 message-schemas452 accepts all three canonical message roles453 assistant message accepts unknown keys454 runtime-boundary-schemas455 accepts runtime adapter boundary maps456 rejects malformed runtime boundary maps457 accepts run-stream argument map contract458 event-schemas459 accepts stream terminal events460 rejects malformed events461 accepts delta events with required payload462 schema-registry-rebuilds-when-component-schemas-change463 oauth-schema-contracts464 accepts OpenAI Codex provider and API enum values465 accepts oauth credential and provider contracts466 rejects oauth credential map missing required keys467 rejects oauth provider missing required function slots468 adapter-and-env-schema469 accepts valid adapter and runtime env470 rejects adapter missing required function slots471 rejects env missing required function slots472 model-schema473 accepts a valid model474 accepts supported openai-completions compat profile keys475 accepts unknown model keys476 context-schema477 context is an ordered vector of canonical messages478 context-map enforces required :messages and optional envelope keys479 usage-schema480 accepts usage where total-tokens equals component sum481 accepts usage where provider total-tokens does not match component sum (Google!)482483ol.llx.agent.fx-test484 fx-execute-tool-uses-updated-schema-config-from-live-agent-test485 fx-call-llm-uses-default-stream-fn-when-not-provided-test486 execute-fx-validates-effect-shape-test487 fx-call-llm-emits-llm-error-on-hook-failure-test488 fx-execute-tool-uses-active-schema-registry-for-input-coercion-test489 fx-call-llm-emits-llm-error-on-non-canonical-event-type-test490 fx-call-llm-runs-hooks-and-maps-events-test491492ol.llx.ai.adapters.common-test493 parse-json-safe-returns-decoded-or-empty-map494 parse-json-lenient-falls-back-to-decode495 uses decode-safe when it succeeds496 falls back to decode when decode-safe returns nil497 uses decode directly when decode-safe is absent498 trim-trailing-slash-removes-single-trailing-slash499 empty-usage-shape-is-canonical500501ol.llx.ai.client.stream-test502 runtime-run-stream-input-requires-runtime-hooks503 requires stream runtime hooks504 run-stream-calls-cancel-when-output-channel-preclosed505 run-stream-emits-start-and-done-events506507ol.llx.ai.adapters.openai-codex-responses-test508 build-request-rejects-token-missing-account-id509 build-request-disables-reasoning-when-no-reasoning-opts510 build-request-prefers-explicit-api-key-over-env511 build-request-shapes-codex-url-and-headers512 build-request-strips-codex-unsupported-payload-fields513514ol.llx.ai.adapters.openai-completions-test515 decode-event-stream-contract516 build-request-missing-api-key-message-includes-env-var-name517 decode-event-tracks-thinking-signature518 build-request-emits-provider-payload-trove-signal519 response->assistant-message-falls-back-to-choice-usage520 build-request-tool-choice-sentinel-strings-pass-through521 decode-event-thinking-to-text-transition522 normalize-tool-call-id-openai-compatible-non-pipe-ids-are-unchanged523 build-request-zai-thinking-format-sends-thinking-object524 response->assistant-message-maps-provider-finish-reason-errors525 normalize-tool-call-id-mistral-avoids-collision-for-distinct-source-ids526 build-request-qwen-thinking-format-sends-enable-thinking527 convert-message-reconstructs-reasoning-details-from-tool-signatures528 response->assistant-message-calculates-usage-costs529 build-request-zai-disables-thinking-when-no-reasoning530 build-request-forwards-tools-and-tool-choice-with-compat-token-field531 build-request-sanitizes-unpaired-surrogates-in-user-text532 build-request-openai-compatible-omits-auth-and-respects-compat-overrides533 build-request-omits-reasoning-effort-when-model-lacks-reasoning534 decode-event-stream-usage-calculates-costs535 decode-event-maps-provider-finish-reason-errors536 build-request-sanitizes-unpaired-surrogates-in-tool-result-text537 normalize-tool-call-id-mistral-shape538 normalization is deterministic 9-char alphanumeric539 decode-event-extracts-reasoning-details-to-tool-call-signature540 build-request-preserves-valid-emoji-surrogate-pairs541 normalize-tool-call-id-pipe-ids-use-call-segment-sanitize-and-truncate542 normalize-tool-call-id-matches-upstream-issue-1022-test-id543 decode-event-emits-thinking-events-for-reasoning-content544 decode-event-stream-falls-back-to-choice-usage545 build-request-includes-reasoning-effort-for-reasoning-model546 normalize-tool-call-id-openai-non-pipe-ids-are-truncated-only547 build-request-reads-provider-specific-env-api-key548 convert-message-restores-thinking-field-from-signature549 build-request-batches-tool-result-images-for-openai-completions550551ol.llx.ai.client.jvm-test552 run-stream-emits-stream-lifecycle-trove-signals553 run-stream-wraps-untyped-stream-errors-as-streaming-error554 run-stream-cancel-fn-closes-upstream-body555 run-stream-emits-stream-event-error-trove-signal556 run-stream-validation557 rejects malformed decoded events558 rejects malformed finalize output559 malformed normalize-error still emits terminal error560561ol.llx.ai.adapters.anthropic-messages-test562 finalize-maps-anthropic-stop-reasons563 build-request-omits-thinking-when-model-not-reasoning564 image-only-content-does-not-inject-placeholder-text565 normalize-tool-call-id-sanitizes-and-truncates566 build-request-enables-adaptive-thinking-for-opus-4-6567 build-request-sanitizes-unpaired-surrogates-in-user-and-system568 build-request-omits-temperature-when-thinking-is-enabled569 build-request-clamps-sonnet-4-6-xhigh-to-high570 build-request-preserves-valid-emoji-surrogate-pairs571 build-request-emits-provider-payload-trove-signal572 decode-event-redacted-thinking-round-trips-to-canonical-content573 finalize-calculates-usage-costs574 build-request-replays-redacted-thinking-as-anthropic-redacted-block575 build-request-enables-budget-thinking-for-older-reasoning-model576 finalize-throws-on-unknown-stop-reason577 decode-event-stream-usage-calculates-costs578 decode-event-stream-contract579 build-request-disables-thinking-when-no-reasoning-opts580 build-request-converts-canonical-context-to-anthropic-payload581 build-request-enables-adaptive-thinking-for-sonnet-4-6582 build-request-uses-custom-thinking-budgets583584333 tests, 1549 assertions, 0 failures.585Picked up JAVA_TOOL_OPTIONS: -Duser.home=/build/tmp.GYho0QmGty586Picked up JAVA_TOOL_OPTIONS: -Duser.home=/build/tmp.GYho0QmGtyfixupPhase
587shrinking RPATHs of ELF executables and libraries in /nix/store/1p7pc018h64ggqrfys2a7xq7bqrr0bxq-llx-0.0.1588checking for references to /build/ in /nix/store/1p7pc018h64ggqrfys2a7xq7bqrr0bxq-llx-0.0.1...589patching script interpreter paths in /nix/store/1p7pc018h64ggqrfys2a7xq7bqrr0bxq-llx-0.0.1