llx-0.0.1
x86_64-linux.default
· build #14
· raw
unpackPhase
1unpacking source archive /nix/store/naw0n071s62dyiy2shjwl7z1lbmh3r65-source2source root is sourceconfigurePhase
3no configure script, doing nothingbuildPhase
4Picked up JAVA_TOOL_OPTIONS: -Duser.home=/build/tmp.3TfkKC5t345Picked up JAVA_TOOL_OPTIONS: -Duser.home=/build/tmp.3TfkKC5t346GUARDRAILS 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.ai.utils.unicode-test11 sanitize-surrogates-handles-surrogate-edge-cases12 preserves valid emoji surrogate pairs13 removes unpaired high surrogate14 removes unpaired low surrogate15 removes high surrogate at end of string16 removes multiple unpaired surrogates in one string17 preserves mixed content: emoji, CJK, math symbols, special quotes18 handles nil and empty input19 passes through plain ASCII unchanged20 truncate-limits-string-length21 truncates only when input exceeds max-len22 coerces nil to empty string23 sanitize-payload-deep-walks-data-structures24 sanitizes strings nested in maps, vectors, and mixed structures25 real-world LinkedIn data with emoji preserved26 unpaired surrogates stripped from tool result content27 handles bare string input28 handles bare vector input29 passes through non-string leaves unchanged3031ol.llx.ai.adapters.common-test32 empty-usage-shape-is-canonical33 trim-trailing-slash-removes-single-trailing-slash34 parse-json-safe-returns-decoded-or-empty-map35 parse-json-lenient-falls-back-to-decode36 uses decode-safe when it succeeds37 falls back to decode when decode-safe returns nil38 uses decode directly when decode-safe is absent3940ol.llx.agent.fx-test41 fx-execute-tool-uses-active-schema-registry-for-input-coercion-test42 fx-call-llm-emits-llm-error-on-non-canonical-event-type-test43 execute-fx-validates-effect-shape-test44 fx-call-llm-uses-default-stream-fn-when-not-provided-test45 fx-execute-tool-uses-updated-schema-config-from-live-agent-test46 fx-call-llm-emits-llm-error-on-hook-failure-test47 fx-call-llm-runs-hooks-and-maps-events-test4849ol.llx.agent-test50 prompt-validates-messages-test51 create-agent-initializes-state-test52 subscribe-unsubscribe-test53 rehydrate-agent-uses-snapshot-test54 set-schema-config-updates-custom-message-validation-on-live-agent-test55 create-agent-default-convert-to-llm-test56 create-agent-rejects-missing-custom-schema-registration-test57 effect-execute-tool-tool-call-schema-test58 tool-and-pending-tool-call-schema-test59 custom-message-schemas-validate-message-and-messages-test60 :ol.llx.agent/custom-message-schemas requires namespace-qualified dispatch keys61 :ol.llx.agent/message rejects custom roles when not registered62 :ol.llx.agent/message accepts registered custom role63 :ol.llx.agent/messages accepts canonical + registered custom messages64 :ol.llx.agent/messages rejects invalid registered custom message payloads65 canonical messages remain valid with custom registrations enabled66 tool-schema-tightening-on-commands-and-state-test67 :ol.llx.agent/command-set-tools expects :ol.llx.agent/tool entries68 :ol.llx.agent/create-agent-opts expects :ol.llx.agent/tool entries in :tools69 :ol.llx.agent.loop/state expects :ol.llx.agent/tool entries in :tools70 command-wrappers-dispatch-through-driver-run-test71 prompt dispatches vector messages72 continue dispatches the continue command73 abort dispatches the abort command74 state mutators dispatch commands75 create-agent-requires-env-contract-test76 tool-call-schema-contract-test77 custom-message-public-api-validation-test78 create-agent-ignores-initial-state-option-test79 set-model-validates-model-shape-test80 set-schema-config-ignores-nil-fields-test81 nil schema-registry preserves the current user registry82 nil custom-message-schemas preserves the current dispatch map83 rehydrate-agent-custom-message-validation-test84 set-schema-config-clears-user-additions-without-removing-canonical-schemas-test85 tool-signal-and-event-schema-tightening-test86 custom-message-schema-may-reference-provided-schemas-test8788ol.llx.ai.utils.overflow-test89 context-overflow-detection90 detects explicit provider messages91 detects 400/413 status codes92 detects silent overflow with context window93 false for non-overflow errors9495ol.llx.ai.utils.tool-validation-test96 validate-tool-call97 success case98 tool not found99 validation errors are structured100 missing required field101 human-readable error message includes tool name and arguments102 tool-not-found error message includes tool name103 coerces string values using the input schema104 applies schema defaults from the input schema105 resolves custom schema references from the active registry106107ol.llx.ai.adapters.openai-completions-test108 decode-event-stream-contract109 decode-event-stream-falls-back-to-choice-usage110 response->assistant-message-calculates-usage-costs111 build-request-omits-reasoning-effort-when-model-lacks-reasoning112 build-request-zai-thinking-format-sends-thinking-object113 response->assistant-message-maps-provider-finish-reason-errors114 decode-event-thinking-to-text-transition115 build-request-zai-disables-thinking-when-no-reasoning116 build-request-sanitizes-unpaired-surrogates-in-user-text117 build-request-openai-compatible-omits-auth-and-respects-compat-overrides118 decode-event-tracks-thinking-signature119 build-request-sanitizes-unpaired-surrogates-in-tool-result-text120 decode-event-extracts-reasoning-details-to-tool-call-signature121 response->assistant-message-falls-back-to-choice-usage122 build-request-reads-provider-specific-env-api-key123 decode-event-maps-provider-finish-reason-errors124 normalize-tool-call-id-mistral-avoids-collision-for-distinct-source-ids125 normalize-tool-call-id-openai-non-pipe-ids-are-truncated-only126 build-request-missing-api-key-message-includes-env-var-name127 convert-message-restores-thinking-field-from-signature128 convert-message-reconstructs-reasoning-details-from-tool-signatures129 build-request-forwards-tools-and-tool-choice-with-compat-token-field130 normalize-tool-call-id-mistral-shape131 normalization is deterministic 9-char alphanumeric132 build-request-preserves-valid-emoji-surrogate-pairs133 normalize-tool-call-id-pipe-ids-use-call-segment-sanitize-and-truncate134 build-request-includes-reasoning-effort-for-reasoning-model135 normalize-tool-call-id-openai-compatible-non-pipe-ids-are-unchanged136 decode-event-emits-thinking-events-for-reasoning-content137 build-request-batches-tool-result-images-for-openai-completions138 build-request-qwen-thinking-format-sends-enable-thinking139 build-request-emits-provider-payload-trove-signal140 build-request-tool-choice-sentinel-strings-pass-through141 decode-event-stream-usage-calculates-costs142 normalize-tool-call-id-matches-upstream-issue-1022-test-id143144ol.llx.agent.loop-test145 handle-command-replace-messages-test146 streaming-transition-llm-error-test147 transitions to idle and sets error148 emits message-end and turn-end149 step-full-happy-path-test150 state progression151 final state has both messages152 agent-end is emitted on final step153 agent-end is not emitted on intermediate steps154 handle-command-continue-empty-queues-test155 tool-executing-transition-abort-test156 transitions to idle and clears pending-tool-calls157 emits turn-end158 handle-command-continue-with-follow-up-all-mode-test159 step-abort-from-tool-executing-to-idle-test160 handle-command-prompt-when-not-idle-test161 step-abort-from-streaming-to-idle-test162 abort signal from streaming163 abort command from streaming164 handle-command-set-schema-config-test165 handle-command-append-message-test166 streaming-transition-llm-done-with-steering-queue-starts-next-turn-test167 moves directly into the next streaming turn168 appends the finished assistant message and queued steering message169 continues the run by ending the turn and scheduling more llm work170 tool-executing-transition-tool-result-last-tool-test171 clears pending-tool-calls172 appends result to messages and resumes llm173 handle-command-set-tools-test174 agent-end-not-emitted-when-staying-idle-test175 handle-command-continue-when-not-idle-test176 handle-command-set-steering-mode-test177 streaming-transition-llm-done-with-follow-up-queue-starts-next-turn-test178 starts a new turn from follow-up messages when no steering exists179 continues the run with another llm call180 step-signal-llm-done-with-tools-test181 tool-executing-transition-tool-error-with-steering-interrupts-remaining-tools-test182 does not execute the next real tool and resumes llm after synthetic skipped results183 keeps one steering message queued in one-at-a-time mode184 appends error result, skipped tool results, and dequeued steering message185 closed-transition-is-terminal-test186 any signal returns state unchanged with no effects187 handle-command-set-follow-up-mode-test188 agent-end-emitted-on-streaming-to-idle-test189 handle-command-set-model-test190 step-signal-llm-done-no-tools-to-idle-test191 step-prompt-when-streaming-is-rejected-test192 route-from-idle-test193 idle-transition-invalid-signal-test194 initial-state-has-expected-shape-test195 handle-command-continue-with-steering-all-mode-test196 handle-command-continue-steering-before-follow-up-test197 step-prompt-from-idle-to-streaming-test198 streaming-transition-llm-chunk-test199 handle-command-reset-test200 handle-command-clear-steering-queue-test201 handle-command-prompt-from-idle-test202 idle-transition-prompt-start-test203 appends messages and transitions to streaming204 emits agent-start, turn-start, message events, and call-llm205 call-llm receives the full message history including new messages206 tool-executing-transition-unknown-signal-test207 streaming-transition-llm-done-prefers-steering-over-follow-up-test208 uses steering messages first and leaves follow-up queued209 continues immediately with call-llm210 handle-command-abort-when-idle-test211 idle-transition-continue-start-test212 appends messages and transitions to streaming213 emits turn-start (no agent-start), message events, and call-llm214 call-llm receives the full message history including new messages215 step-tool-loop-test216 state progression through tool loop217 tool completion resumes llm218 final state has all messages219 agent-end emitted on final transition to idle220 tool-executing-transition-tool-result-with-remaining-test221 processes result and keeps remaining tools222 appends result to messages223 emits tool-execution-end, message events, and starts next tool224 streaming-transition-llm-start-test225 handle-command-set-system-prompt-test226 streaming-transition-abort-test227 transitions to idle and clears stream-message228 emits message-end and turn-end229 command-predicate-test230 recognizes commands231 rejects signals232 rejects events233 handle-command-follow-up-test234 handle-command-abort-when-streaming-test235 tool-executing-transition-tool-error-last-tool-test236 clears pending-tool-calls237 records error result and resumes llm238 handle-command-steer-test239 handle-command-clear-all-queues-test240 route-from-streaming-test241 idle routes to idle242 tool-executing routes to tool-executing243 closed routes to closed244 streaming stays streaming245 streaming-transition-llm-done-with-tools-test246 transitions to tool-executing247 sets pending-tool-calls and clears stream-message248 appends the message249 emits message-end, tool-execution-start, and execute-tool250 agent-end-emitted-on-error-to-idle-test251 tool-executing-transition-tool-error-with-remaining-test252 records error result and keeps remaining tools253 emits tool-execution-end, message events, and starts next tool254 handle-command-continue-with-follow-up-one-at-a-time-test255 tool-executing-transition-tool-result-with-steering-interrupts-remaining-tools-test256 clears pending tool calls and keeps remaining steering queued in one-at-a-time mode257 appends current tool result, synthetic skipped results, and dequeued steering message258 emits current result events, skipped tool lifecycle events, steering message events, and resumes llm259 streaming-transition-unknown-signal-test260 handle-command-clear-follow-up-queue-test261 tool-executing-transition-tool-update-test262 handle-command-continue-with-steering-one-at-a-time-test263 agent-end-not-emitted-on-streaming-to-tool-executing-test264 handle-command-clear-messages-test265 tool-executing-transition-tool-result-with-steering-all-mode-dequeues-all-test266 dequeues all steering messages in :all mode267 route-from-tool-executing-test268 with pending tool calls stays tool-executing269 without pending tool calls routes to streaming270 closed routes to closed271 handle-command-set-thinking-level-test272 streaming-transition-llm-done-no-tools-test273 transitions to idle and clears stream-message274 appends the final message275 emits message-end and turn-end276277ol.llx.ai.schema-test278 runtime-boundary-schemas279 accepts runtime adapter boundary maps280 rejects malformed runtime boundary maps281 accepts run-stream argument map contract282 message-schemas283 accepts all three canonical message roles284 assistant message accepts unknown keys285 config-schema286 accepts known provider config287 accepts unknown provider keys288 model-schema289 accepts a valid model290 accepts supported openai-completions compat profile keys291 accepts unknown model keys292 adapter-and-env-schema293 accepts valid adapter and runtime env294 rejects adapter missing required function slots295 rejects env missing required function slots296 oauth-schema-contracts297 accepts OpenAI Codex provider and API enum values298 accepts oauth credential and provider contracts299 rejects oauth credential map missing required keys300 rejects oauth provider missing required function slots301 usage-schema302 accepts usage where total-tokens equals component sum303 accepts usage where provider total-tokens does not match component sum (Google!)304 schema-registry-rebuilds-when-component-schemas-change305 context-schema306 context is an ordered vector of canonical messages307 context-map enforces required :messages and optional envelope keys308 options-schema309 accepts valid unified request options310 accepts unknown unified request option keys311 accepts valid provider request options including provider-specific keys312 tool input schema field descriptions survive json schema conversion313 options-schema-allows-provider-specific-option-keys314 event-schemas315 accepts stream terminal events316 rejects malformed events317 accepts delta events with required payload318319ol.llx.ai.adapters.openai-codex-responses-test320 build-request-rejects-token-missing-account-id321 build-request-strips-codex-unsupported-payload-fields322 build-request-prefers-explicit-api-key-over-env323 build-request-shapes-codex-url-and-headers324 build-request-disables-reasoning-when-no-reasoning-opts325326ol.llx.ai.client.stream-test327 run-stream-emits-start-and-done-events328 runtime-run-stream-input-requires-runtime-hooks329 requires stream runtime hooks330 run-stream-calls-cancel-when-output-channel-preclosed331332ol.llx.ai.client-test333 complete-openai-completions-non-2xx334 stream-simple-wrapper-normalizes-options335 complete-emits-error-lifecycle-trove-signals336 stream-rejects-unsupported-xhigh-with-structured-error337 complete-rejects-unsupported-xhigh-with-structured-error338 stream-retries-open-stream-on-transient-error339 complete-allows-xhigh-for-supported-model340 stream-close-delegates-to-runtime-cancel-fn341 complete-surfaces-unknown-openai-completions-stop-reason-as-error-message342 complete-transforms-context-before-build-request343 complete-retries-on-transient-error344 complete-retries-without-thread-sleep-hook345 complete-simple-wrapper-normalizes-options346 complete-rejects-malformed-adapter-finalize-result347 opts-registry-overrides-env-registry348 complete-does-not-retry-on-client-error349 unified-opts->request-opts-rejects-provider-shape-in-unified-opts350 complete-emits-lifecycle-trove-signals351 unified-opts->request-opts-normalizes-unified-shape352 complete-returns-deferred353 stream-returns-csp-channel354 complete-simple-wrapper-normalizes-openai-responses-reasoning-to-effort355356ol.llx.ai.models-test357 model-registry-and-lookup358 model-utility-functions359 calculate-cost360 supports-xhigh?361 direct anthropic 4.6 models use the larger context window362 models-equal?363364ol.llx.ai.adapters.google-generative-ai-test365 reasoning-config-gemini-3-pro-uses-level366 build-request-sanitizes-unpaired-surrogates-in-user-and-system367 build-request-emits-provider-payload-trove-signal368 reasoning-config-gemini-25-pro-budget-differs-from-flash369 reasoning-config-omitted-when-model-not-reasoning370 build-request-tool-result-image-forwarding-by-model-capability371 gemini-3 multimodal model forwards image in functionResponse parts372 text-only model drops images from functionResponse373 build-request-converts-canonical-context-to-google-payload374 reasoning-config-disables-thinking-by-default-for-gemini-3375 build-request-gemini-3-preserves-unsigned-tool-calls-with-sentinel376 map-stop-reason-fail-fast-on-unknown377 unknown finish reason in stream decode fails fast378 adapter-registers-tool-call-id-normalizer-with-model-id-gate379 stream-error-normalization-contract380 finalize-throws-on-unknown-stop-reason381 reasoning-config-gemini-3-flash-uses-level382 reasoning-config-gemini-3-pro-clamps-low-effort383 google-normalizer-matches-upstream-issue-1022-test-id-under-gate384 finalize-calculates-usage-costs385 decode-event-tool-call-missing-args-defaults-to-empty-map386 build-request-uses-custom-thinking-budgets387 open-stream-non-2xx-throws-structured-error388 build-request-preserves-valid-emoji-surrogate-pairs389 thought-signature-alone-is-not-thinking390 reasoning-config-disables-thinking-by-default-for-gemini-3-pro391 decode-event-stream-usage-calculates-costs392 decode-event-stream-contract393 reasoning-config-disables-thinking-by-default-for-gemini-25394395ol.llx.ai.registry-test396 registry-patterns397 immutable registry returns new value398 mutable registry399 dynamic registry400 registry-operations401 unregister and clear adapters402 rejects invalid api value403404ol.llx.ai.oauth-test405 oauth-provider-registry-operations406 refresh-oauth-token-dispatch407 get-oauth-api-key-behavior408 returns nil for missing provider credentials409 returns existing api key when credential is not expired410 refreshes expired credential before returning api key411412ol.llx.ai.guardrails-contract-test413 guardrails-enforces-boundary-shapes414 decode-event boundary is enforced for all adapters415416ol.llx.ai.adapters.anthropic-messages-test417 decode-event-redacted-thinking-round-trips-to-canonical-content418 decode-event-stream-contract419 build-request-enables-adaptive-thinking-for-opus-4-6420 build-request-sanitizes-unpaired-surrogates-in-user-and-system421 image-only-content-does-not-inject-placeholder-text422 build-request-omits-temperature-when-thinking-is-enabled423 decode-event-stream-usage-calculates-costs424 build-request-disables-thinking-when-no-reasoning-opts425 build-request-uses-custom-thinking-budgets426 build-request-preserves-valid-emoji-surrogate-pairs427 build-request-enables-budget-thinking-for-older-reasoning-model428 build-request-replays-redacted-thinking-as-anthropic-redacted-block429 finalize-maps-anthropic-stop-reasons430 build-request-converts-canonical-context-to-anthropic-payload431 build-request-omits-thinking-when-model-not-reasoning432 build-request-enables-adaptive-thinking-for-sonnet-4-6433 build-request-clamps-sonnet-4-6-xhigh-to-high434 normalize-tool-call-id-sanitizes-and-truncates435 finalize-calculates-usage-costs436 build-request-emits-provider-payload-trove-signal437 finalize-throws-on-unknown-stop-reason438439ol.llx.ai.adapters.openai-responses-test440 decode-event-message-output-item-done-encodes-versioned-text-signature441 decode-event-stream-contract442 decode-event-reasoning-summary-part-done-requires-summary-part443 build-request-disables-reasoning-when-no-reasoning-opts444 finalize-calculates-tier-adjusted-cost-when-usage-present445 cache-retention-mapping446 cache-control none omits both prompt cache fields447 cache-control long sets 24h retention for direct api.openai.com448 cache-control long does not set retention for non-openai base url449 stream-error-normalization-contract450 normalize-tool-call-id-preserves-same-provider-item-ids451 build-request-emits-provider-payload-trove-signal452 normalize-tool-call-id-normalizes-pipe-ids-and-preserves-pairing453 build-request-replays-versioned-text-signature-metadata454 normalize-tool-call-id-hashes-foreign-item-ids455 build-request-sanitizes-unpaired-surrogates-in-user-text456 normalize-tool-call-id-trims-trailing-underscores-and-enforces-fc-prefix457 decode-event-response-failed-includes-provider-error-details458 normalize-tool-call-id-matches-upstream-issue-1022-test-id459 normalize-tool-call-id-gates-by-provider-allowlist460 build-request-converts-context-to-openai-responses-input461 build-request-preserves-valid-emoji-surrogate-pairs462 finalize-throws-on-unknown-stop-reason463 finalize-maps-responses-status-to-canonical-stop-reason464465ol.llx.ai.model-catalog.generate-test466 build-catalog-normalizes-supported-providers-only467 build-catalog-rejects-duplicate-normalized-source-keys468 build-catalog-rejects-invalid-override-shapes469 build-catalog-rejects-provider-change-for-existing-id470 render-generated-source-is-stable471 build-catalog-deep-merges-nested-override-fields472 generate-models-writes-artifact-using-injected-paths473 generate-models-uses-checked-in-overrides-and-emits-openai-codex-models474 build-catalog-supports-provider-qualified-override-keys475 build-catalog-is-deterministically-sorted476477ol.llx.ai.oauth.cli-test478 login-command-writes-auth-json-in-current-working-directory479 persists oauth credentials to auth.json480481ol.llx.ai.client.jvm-test482 run-stream-emits-stream-lifecycle-trove-signals483 run-stream-emits-stream-event-error-trove-signal484 run-stream-wraps-untyped-stream-errors-as-streaming-error485 run-stream-validation486 rejects malformed decoded events487 rejects malformed finalize output488 malformed normalize-error still emits terminal error489 run-stream-cancel-fn-closes-upstream-body490491ol.llx.agent.driver-test492 abort-cancels-tool-execution-and-returns-to-idle-test493 prompt-continues-through-queued-steering-without-stalling-test494 abort-drops-stale-llm-events-and-allows-reuse-test495496ol.llx.ai.errors-test497 retry-delay-uses-exponential-backoff-for-rate-limit-without-header498 quota-exceeded-is-not-recoverable499 content-filter-is-not-recoverable500 extracts-retry-after-ms-header501 model-not-found-is-not-recoverable502 provider-error-with-custom-recoverability503 server-error-is-recoverable504 predicates-match-error-categories505 llx-error? matches structured errors506 recoverable? matches recoverable errors507 rate-limit-error?508 quota-exceeded-error?509 rate-limited-error?510 timeout-error?511 client-error?512 transient-error?513 extract-retry-after-from-message-returns-nil-when-missing514 retry-loop-async-fails-when-server-retry-delay-exceeds-cap515 returns-nil-when-no-header516 http-status-429-without-quota-returns-rate-limit517 timeout-error-is-recoverable518 retry-delay-exceeded-is-not-recoverable519 retry-loop-async-exhausts-retries-and-throws520 invalid-request-is-not-recoverable521 retry-loop-async-retries-transient-and-succeeds522 caps-at-max-seconds523 http-status->error-maps-common-codes524 400 -> invalid-request525 401 -> authentication-error526 403 -> authorization-error527 404 -> model-not-found528 408 -> timeout529 500 -> server-error530 502 -> server-error531 503 -> server-error532 retry-delay-uses-linear-backoff-for-connection-errors533 should-retry-allows-transient-errors534 should-retry-respects-max-retries535 connection-error-is-recoverable536 extracts-x-ratelimit-reset-after-header537 should-retry-rejects-client-errors538 rate-limit-error-has-correct-type-and-recoverable539 retry-delay-uses-server-retry-after-for-rate-limit540 http-status-unknown-5xx-returns-recoverable-provider-error541 extracts-retry-after-seconds-header542 retry-after-ms-takes-priority543 http-status-429-with-quota-and-retry-after-returns-rate-limit544 retry-loop-async-does-not-retry-client-errors545 retry-loop-async-emits-retry-scheduled-trove-signal546 extract-retry-after-from-message-parses-seconds547 retry-delay-adds-jitter-for-server-errors548 http-status-unknown-4xx-returns-non-recoverable-provider-error549 authentication-error-is-not-recoverable550 http-status-429-with-quota-body-returns-quota-exceeded551 retry-loop-async-succeeds-on-first-attempt552553ol.llx.ai.utils.rate-limit-test554 rate-limited-detection555 detects structured error types556 detects provider message patterns557 false for non-rate-limit errors558559ol.llx.ai.oauth.openai-codex-test560 login-openai-codex-state-mismatch-fails561 login-openai-codex-manual-fallback562 parse-authorization-input-cases563 accepts full redirect URL564 accepts code#state format565 accepts query-string format566 falls back to raw code567 account-id-extraction568 login-openai-codex-bind-failure-falls-back-to-manual-input569570ol.llx.ai.transform-messages-test571 cross-model-replay-converts-thinking-and-drops-signatures572 user-interruption-inserts-only-missing-tool-results573 google-gated-normalization-rewrites-assistant-and-tool-result-ids574 skipped-assistant-turns-with-error-or-aborted-stop-reasons575 missing-tool-results-get-synthetic-error-message576 tool-call-id-normalization-propagates-to-tool-result577 synthetic-tool-result-uses-real-time-when-clock-missing578 does-not-duplicate-existing-synthetic-tool-result579 same-model-replay-preserves-thinking-and-signatures580 fixture-for-aborted-reasoning-skips-aborted-turn581 aborted assistant turn is removed from replay582 tool-call-id-normalization-avoids-collision-for-mistral583584333 tests, 1549 assertions, 0 failures.585Picked up JAVA_TOOL_OPTIONS: -Duser.home=/build/tmp.3TfkKC5t34586Picked up JAVA_TOOL_OPTIONS: -Duser.home=/build/tmp.3TfkKC5t34fixupPhase
587shrinking RPATHs of ELF executables and libraries in /nix/store/fs3cxl806p4bi4jw0ifnfmxkya5kangp-llx-0.0.1588checking for references to /build/ in /nix/store/fs3cxl806p4bi4jw0ifnfmxkya5kangp-llx-0.0.1...589patching script interpreter paths in /nix/store/fs3cxl806p4bi4jw0ifnfmxkya5kangp-llx-0.0.1