{"entries":[{"name":"2023-queued-slash-command-followup.test.ts","mode":"0100644","size":2520,"lastCommit":{"hash":"3e5ad67e0f325d4888f82f9b82966218eb4407f5","oid":"3e5ad67e0f325d4888f82f9b82966218eb4407f5","parents":["801db80b65210b25462bce1700675e073fe3dbe5"],"author":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-05-07T15:59:42+02:00"},"committer":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-05-07T15:59:42+02:00"},"message":"chore: migrate pi packages to earendil works scope\n","tree":"e9426bc02876b5d4e3bbfbe07a1567300bc8a931"}},{"name":"2753-reload-stale-resource-settings.test.ts","mode":"0100644","size":3289,"lastCommit":{"hash":"3e5ad67e0f325d4888f82f9b82966218eb4407f5","oid":"3e5ad67e0f325d4888f82f9b82966218eb4407f5","parents":["801db80b65210b25462bce1700675e073fe3dbe5"],"author":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-05-07T15:59:42+02:00"},"committer":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-05-07T15:59:42+02:00"},"message":"chore: migrate pi packages to earendil works scope\n","tree":"e9426bc02876b5d4e3bbfbe07a1567300bc8a931"}},{"name":"2781-skill-collision-precedence.test.ts","mode":"0100644","size":5055,"lastCommit":{"hash":"f1dc7394a3ef3bcabac95c3fc8edaf641f6fc581","oid":"f1dc7394a3ef3bcabac95c3fc8edaf641f6fc581","parents":["373da5e88c89a6750683912bb9ca2002558dddfe"],"author":{"name":"Kevin Thomas","email":"kevin.jt2007@gmail.com","when":"2026-05-14T15:56:52-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-05-14T15:56:52-07:00"},"message":"move config under prime agent (#32)\n\n* move config under prime agent\n\nrefs ENG-3630, ENG-3633\n\n* trim docs from config change\n\nrefs ENG-3630, ENG-3633\n\n* remove nonessential branding changes\n\nrefs ENG-3630, ENG-3633\n\n* drop optional aliases and comments\n\nrefs ENG-3630, ENG-3633\n\n* fix prime-agent config paths\n\n* fix prime-agent test expectations\n\n* test github release version parsing\n\n* test prime-agent env constants\n\n* fix extension loader package fallback\n\n* remove repo-local agent resources\n\n* narrow config directory migration\n\n* minimize config path diff\n\n* fix config path help output\n\n* fix tui log config path\n\n* fix tui log filenames\n\n* fix remaining prime agent config paths","tree":"5c3b448985cd2d90eff9d014bf6ac703746e1dc3"}},{"name":"2791-fswatch-error-crash.test.ts","mode":"0100644","size":3873,"lastCommit":{"hash":"94ece04f5d977326d01cc1b1913b04d2e2c8ff9e","oid":"94ece04f5d977326d01cc1b1913b04d2e2c8ff9e","parents":["a04350e4a7b96cdf1835d387a1cc3e55ad2426fe"],"author":{"name":"Kevin Thomas","email":"kevin.jt2007@gmail.com","when":"2026-05-19T17:29:44-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-05-19T17:29:44-07:00"},"message":"clean up legacy pi artifacts (#50)\n\n* chore: clean up legacy pi artifacts\n\n* test: update prime agent branding expectations","tree":"7123b6937fa0f89d88a7bf06f5b9bd77712ab6cf"}},{"name":"2835-tools-allowlist-filters-extension-tools.test.ts","mode":"0100644","size":3096,"lastCommit":{"hash":"2ef9ab0ef9ecd67f11744b433298a92cfcb37ffa","oid":"2ef9ab0ef9ecd67f11744b433298a92cfcb37ffa","parents":["4fb8c9ec6dfbe94d32831c143743b8d987a01196"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-06-15T15:01:45-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-06-15T15:01:45-07:00"},"message":"move goals to the ipython goal skill (#159)\n\n* move goals from harness tools to the ipython goal skill\n\nThe model's only built-in tool is now ipython. The rlm.run comm channel is\ngeneralized into a typed host bridge (comm target host.request, dispatched\nvia hostHandlers), rlm.host_request() is public for kernel-side skills, and\ngoals ship as the bundled python skill 'goal' (goal.get / goal.create /\ngoal.complete) backed by AgentSession state. Goal re-prompting, budgets,\nand goal_update events are unchanged.\n\n* let goal.create replace terminal goals and explain pending-goal rejections\n\nA complete or error goal is a finished record, not a pending objective, so\ngoal.create now starts a fresh goal over it (matching what /goal already\nallowed for users). Active, paused, and budget-limited goals still reject\ncreation, each with a message telling the model what to do instead.\n\n* harden the goal host bridge against review-bot findings\n\nCompleting a goal now drops any stale budget-limit steer queued earlier in\nthe same turn, host replies with an unexpected status reject instead of\nhanging the kernel future, and a payload type key can no longer reroute a\nhost request.\n\n* fix(coding-agent): stop goal completion usage overcount","tree":"c9594d6b0de98a464ac375c0fbed4153f4e0db54"}},{"name":"2860-replaced-session-context.test.ts","mode":"0100644","size":8671,"lastCommit":{"hash":"7c4df72953572312bfbf919dc6292b24a2295e13","oid":"7c4df72953572312bfbf919dc6292b24a2295e13","parents":["7ae96aa033c6ef2ef32c1559003bb8ca49b9d2ad"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-06-09T23:15:13-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-06-09T23:15:13-07:00"},"message":"speed up daemon startup and tui streaming performance (#117)\n\n* perf: daemon early-listen, single ensure, faster polls, streaming benches + identity tests\n\n* perf: lazy-load extension bundles, cli-highlight, and typebox/compile off the startup path\n\n* perf: slim attach payload for capable clients (skip event + top-level state/messages)\n\n* perf: reconcile assistant message at render time + per-block markdown render cache\n\n* perf: stop double-sending partial message in daemon message_update events\n\n* test: add attach payload benchmark script\n\n* perf: spawn interactive daemon before importing the heavy module graph\n\n* test: isolate session dirs in runtime tests to stop leaking into the shared sessions dir\n\n* perf: bundle cli entry with esbuild for ~3x faster startup\n\n* add --dist flag to prime-agent.sh to run the bundled build\n\n* address review bot findings: honor --cwd in early daemon spawn, fix theme null colors check, fix bench script edge cases","tree":"b3865383f5e6f40d0c18a91e7b69bdd302ce4972"}},{"name":"3217-scoped-model-order.test.ts","mode":"0100644","size":3203,"lastCommit":{"hash":"891b99800bdd40d53c8f67bbae03acc55262e585","oid":"891b99800bdd40d53c8f67bbae03acc55262e585","parents":["c1fdeeedc7ad705dc7b68f93f4fcccea5b6593ca"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-06-04T12:06:25-07:00"},"committer":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-06-09T21:11:57-07:00"},"message":"decouple interactive mode from agent runtime (#79)\n\n* decouple interactive mode from agent runtime\n\n* add rich tui attach for daemon sessions\n\n* clarify agent connection boundary\n\n* document agent connection architecture\n\n* fix daemon interactive session replacement\n\n* refresh transcript after session replacement\n\n* fix daemon session attach edge cases\n\n* fix remaining daemon tui review findings\n\n* fix daemon tui review regressions\n\n* fix daemon tui cancellation gaps\n\n* fix daemon attach by session file\n\n* fix daemon extension ui client routing\n\n* fix daemon close ui cancellation order\n\n* fix daemon active session lookup startup\n","tree":"de252ecf8bf85c59c15f4f28050d6156621c3379"}},{"name":"3317-network-connection-lost-retry.test.ts","mode":"0100644","size":1199,"lastCommit":{"hash":"3e5ad67e0f325d4888f82f9b82966218eb4407f5","oid":"3e5ad67e0f325d4888f82f9b82966218eb4407f5","parents":["801db80b65210b25462bce1700675e073fe3dbe5"],"author":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-05-07T15:59:42+02:00"},"committer":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-05-07T15:59:42+02:00"},"message":"chore: migrate pi packages to earendil works scope\n","tree":"e9426bc02876b5d4e3bbfbe07a1567300bc8a931"}},{"name":"3592-no-builtin-tools-keeps-extension-tools.test.ts","mode":"0100644","size":3943,"lastCommit":{"hash":"a2098813292a730c198ddd15d95ecbe118c49d8c","oid":"a2098813292a730c198ddd15d95ecbe118c49d8c","parents":["1dd2cdfbf55649f63f1a584f31ae95af06be1c42"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-06T15:33:42-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-06T15:33:42-07:00"},"message":"remove legacy pi mono built-in tools (#323)\n\n* remove legacy pi mono built-in tools\n\n* fix sdk full control example\n\n* allow legacy tool names for extensions\n\n* map legacy tool requests to ipython\n\n* preserve legacy tool replay renderers\n\n* handle metadata-only legacy tool replay\n\n* tolerate legacy tool metadata drift\n\n* mark legacy replay renderer definitions\n\n* fix sdk session manager ipython expectation\n\n* preserve shell settings for ipython bash cells\n\n* fix(coding-agent): address legacy tool review feedback","tree":"509d80d203471a2b94fa6eea339d74d12f41000e"}},{"name":"3616-settings-inmemory-reload.test.ts","mode":"0100644","size":2776,"lastCommit":{"hash":"86ba08a2e38fa14a6b42ea6e3f9f3b23976aa6d1","oid":"86ba08a2e38fa14a6b42ea6e3f9f3b23976aa6d1","parents":["4cd4cfd98ebf57e391b3848e1b66c0d0d41df38a"],"author":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-04-23T23:47:49+02:00"},"committer":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-04-23T23:47:49+02:00"},"message":"fix(coding-agent): preserve in-memory settings on reload\n\ncloses #3616\n","tree":"0a62a7fb8e17a0cb9534cc768ba19542c2b343f7"}},{"name":"3686-session-name-event.test.ts","mode":"0100644","size":1279,"lastCommit":{"hash":"c19e64a444373b558d5d0d44eb4d52877ea07593","oid":"c19e64a444373b558d5d0d44eb4d52877ea07593","parents":["a363b668ac930f11412de09450c847c1351c0d03"],"author":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-04-25T17:20:26+02:00"},"committer":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-04-25T17:20:26+02:00"},"message":"fix(coding-agent): refresh title after extension session rename\n\ncloses #3686\n","tree":"3f3ab0f207781d77a38abcf864df42d0887aac0f"}},{"name":"3688-tree-cancel-compacting.test.ts","mode":"0100644","size":1202,"lastCommit":{"hash":"a363b668ac930f11412de09450c847c1351c0d03","oid":"a363b668ac930f11412de09450c847c1351c0d03","parents":["3e7ffff184e805930e23c7440fa9571407a485ee"],"author":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-04-25T17:03:09+02:00"},"committer":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-04-25T17:03:09+02:00"},"message":"fix(coding-agent): clear tree navigation compaction state\n\ncloses #3688\n","tree":"e7620a8aaa456b43841776c8188401b380147664"}},{"name":"3885-subagent-runtime-host.test.ts","mode":"0100644","size":8491,"lastCommit":{"hash":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","oid":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","parents":["78a0e05d595e3c70ab44be61ad0d92c71a6fd5a6"],"author":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"committer":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"message":"complete guarded RLM results and background completion wakeups\n","tree":"27f93d672adc2bdf84f6b7810e6d33f18f04ba38"}},{"name":"3982-message-end-cost-override.test.ts","mode":"0100644","size":1668,"lastCommit":{"hash":"3e5ad67e0f325d4888f82f9b82966218eb4407f5","oid":"3e5ad67e0f325d4888f82f9b82966218eb4407f5","parents":["801db80b65210b25462bce1700675e073fe3dbe5"],"author":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-05-07T15:59:42+02:00"},"committer":{"name":"Mario Zechner","email":"badlogicgames@gmail.com","when":"2026-05-07T15:59:42+02:00"},"message":"chore: migrate pi packages to earendil works scope\n","tree":"e9426bc02876b5d4e3bbfbe07a1567300bc8a931"}},{"name":"4167-thinking-toggle-pending-tool-render.test.ts","mode":"0100644","size":6192,"lastCommit":{"hash":"e751ad727decef619d6bb427e1a27868285f4ee1","oid":"e751ad727decef619d6bb427e1a27868285f4ee1","parents":["3065f5a07b9423cf4bce2a9a6288348aa6bed9e9"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-07-18T00:40:49+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-17T15:40:49-07:00"},"message":"fix(tui): show compact fullscreen image fallbacks (#437)\n\n* fix(tui): compact fullscreen image fallbacks\n\n* fix(coding-agent): show replayed image fallbacks\n\n* fix(coding-agent): include image fallback dimensions\n\n* fix(coding-agent): indent image fallback rows\n\n* test(coding-agent): update image fallback expectation\n\n* test(coding-agent): avoid fallback presentation coupling\n\n* fix(coding-agent): tighten image fallback spacing\n\n* fix(coding-agent): avoid duplicate image fallbacks\n\n* fix(tui): use image metadata in terminal\n\nfixes #437\n\n* fix(tui): preserve image metadata fallbacks\n\nfixes #437\n\n* fix(coding-agent): expose image metadata setting\n\nfixes #437\n\n* fix(coding-agent): avoid duplicate image fallbacks\n\nfixes #437\n\n---------\n\nCo-authored-by: Kevin Thomas ","tree":"ce1be73fdebc0ac211157150d688c0879a6661b8"}},{"name":"4257-update-restart-resume.test.ts","mode":"0100644","size":50862,"lastCommit":{"hash":"b030f3938463c2a9f5767c93e861a2d5d57b5d92","oid":"b030f3938463c2a9f5767c93e861a2d5d57b5d92","parents":["d93b3cbe0bca3e9fcbe85a78b3c3be89f96cedde"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-05T04:46:52+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-05T04:46:52+02:00"},"message":"feat(coding-agent): intra-tree child session passivation (#589)\n\n* feat(coding-agent): intra-tree child session passivation\n\nTrack A PR 7 (final) of the recursive-agent-harness plan (D5, shape 2):\n\n- idle child sessions inside a LIVE worker passivate individually: graceful\n closeSession (kernel snapshot + JSONL flush + lease release), sessions-map\n removal, registry/catalog rows preserved - the child becomes exactly a\n lazy-hydration passive row (attach/message/observe/list all work)\n- pure canPassivateSession() beside canEvictWorker(), sharing its per-\n session clauses; additionally requires a parent edge, no non-passive\n descendants, and no mid-hydration descendant (passive children's\n sessionFiles checked against openingSessions - hydration blocks parent\n passivation); roots remain shape-1 territory; passivation never cascades\n- complete-then-rehydrate: touches mid-passivation join the passivation\n promise (keyed by resolved sessionFile - stable across sessions-map\n removal) then flow through the normal hydration machinery; deterministic\n gated race tests for a2a delivery and grandchild hydration\n- supervisor sweep extension: capped worker command (2 children/worker/\n sweep), one snapshot per state per sweep, fresh-snapshot fence recheck\n before dispose; whole-tree-evictable workers excluded (owned by shape 1)\n- same idleEvictionMinutes setting governs both shapes; #548 doctrine\n inversion deferred (prompts out of scope this run)\n\n* fix(coding-agent): harden passivation against new admission fences and reap dedupe\n\nPost-rebase semantic fixes after moving the stack onto the hardened\nscheduler base (cb8f53e15):\n\n- passivation predicate treats admission-in-flight as busy: agent-message\n accepting/preparing/target-lock states and AgentSession's pending\n admission-fence waiters (70aeb9c49/2d97dbb4f made prompt paths await the\n direct-turn admission fence before any session action exists, so a target\n mid-admission looked idle to the sweep); deterministic gated-admission\n regression test\n- deleteRlmSubagentRuntime cancels scheduled jobs by session file even when\n its close joins an in-flight passivation close via closingSessions (the\n joined 'shutdown' close skipped 'killed'-close job cleanup; #547 reap race)\n\n* fix(coding-agent): harden passive-child hydration, resolution, and deletion races\n\n- Finding 0: heartbeat restore could return a concurrently hydrating child before binding; fence resident fallback with waitForBoundSession and treat unavailable binding as a skipped dispatch. origin: PR #583\n- Finding 1: supervisor child lookup accepted only exact selectors after worker suffix matching; add the same session-ID suffix fallback within the selected worker. origin: PR #583\n- Finding 3: passive create hydration skipped explicit name and client environment bookkeeping; apply both before returning the hydrated state. origin: PR #583\n- Finding 4: concurrent passive deletions raced through asynchronous resolution and started duplicate host deletes; defer deletion behind an atomic in-flight map check and coalesce callers. origin: PR #583\n- Finding 5: concurrent hydration could make a passive lookup stale for advertised IDs and paths; retry normal bound-session resolution before rethrowing the original unknown-session error. origin: PR #583\n- Finding 6: ambiguous live selectors fell through to passive lookup and could misroute; introduce a dedicated ambiguity error and rethrow it before passive resolution. origin: PR #583\n- Finding 7: passive open skipped name and client-env bookkeeping (cron rebinding already occurred in addRuntime); apply only the missing bookkeeping. origin: PR #583\n- Finding 30: rlmChildId traffic treated a resident passivating child as closing; join passivation and rehydrate in both bound lookup and direct message hydration branches. origin: PR #589\n\n* fix(coding-agent): restore attach/catch-up ordering invariants and sweep snapshot atomicity\n\n- Finding 22: async snapshot creation exposed clients before attach initialization; publish client attachment only after the snapshot resolves. origin: PR #587\n- Finding 23: catch-up validity was checked only before async snapshot creation; revalidate session and client attachment after the await. origin: PR #587\n- Finding 25: deterministic ambiguous selectors entered the 30-second remote-send retry loop; fail fast for Ambiguous errors. origin: PR #588\n- Finding 28: active rows ignored stable file-keyed schedule pins during active-id rebinding; consult both id- and file-keyed heartbeat/cron sets. origin: PR #588\n- Finding 29: passivation sampled activity before an asynchronous passive-registry walk; complete the walk before atomically sampling summary and admission markers. origin: PR #589\n\n* fix(coding-agent): correct rlmDepth semantics on reference edges, env parsing, and legacy fallbacks\n\n- Finding 8: new-session parent links were deriving spawn depth; copy the source header depth across the reference edge and add a runtime regression test (origin: PR #584).\n- Finding 9: first-entry forks of legacy sessions discarded effective runtime depth; fall back to session.rlmDepth in persisted and in-memory branches and test both (origin: PR #584).\n- Finding 10: root RLM_DEPTH parsing accepted malformed and unsafe values; require decimal digits and a valid safe non-negative integer, with probe cases as tests (origin: PR #584).\n- Finding 11: child-depth derivation could overflow MAX_SAFE_INTEGER; guard the increment and test the boundary (origin: PR #584).\n- Finding 12: daemon children of in-memory parents skipped explicit depth persistence; always create the child header with explicit depth and test --no-session ancestry (origin: PR #584).\n- Finding 13: legacy completed subagents rehydrated at root depth; restore the depth-one fallback and test a registry/header pair without depth (origin: PR #584).\n\n* fix(coding-agent): make /rlm-max-depth persistence honest and unblock stale kernel gate\n\n- /rlm-max-depth --global could claim persistence after deferred settings write failures; drain and surface global errors before reporting success (origin: PR #585)\n- /rlm-max-depth mutated live state before chat persistence and left failed entries indexed; persist first through rollback-safe custom-entry append, then mutate state and prompt (origin: PR #585)\n- invalid persisted global rlmMaxDepth could abort branch navigation after the leaf moved; ignore invalid global reads and fall through to env/default (origin: PR #585)\n- the kernel-side recursion pre-filter used stale one-shot RLM_MAX_DEPTH and blocked raises before the authoritative host gate; remove the duplicated Python gate (origin: PR #585)\n\n* fix(coding-agent): agents-view scope stability, crash-path backSession, summary refresh, pulse, and settings cycling\n\n- Finding 18: stale saved-catalog readiness could destructively drop scope during refresh; reset readiness when refresh starts. origin: PR #586\n- Finding 19: resolved scope roots were lost across view remounts, swallowing early Left navigation; persist and restore the root summary. origin: PR #586\n- Finding 20: post-attach crashes left backSession pointing at the prior session; assign the opened summary before interactive mode runs. origin: PR #586\n- Findings 21 and 24: startup seeding could leave subagent counts stale and background subagents drove an unused render pulse; refresh every seed and pulse only while streaming. origin: PR #587\n- Finding 27: custom idle-eviction values cycled directly to off; include custom numeric values in the sorted cycle. origin: PR #588\n\n* fix(coding-agent): attach reservation vs passivation, binding join on retry, hydration env, settings error scoping, fractional eviction values\n\n- reserve in-flight attaches and revalidate session liveness before attachment (origin: round-1 fix a342ca23d)\n- join concurrent child binding on the final passive resolution retry (origin: round-1 fix ae3ed4571)\n- adopt create-command client env before passive child hydration (origin: round-1 fix ae3ed4571)\n- isolate max-depth write errors while preserving project diagnostics (origin: round-1 fix 9e738f38f)\n- preserve fractional idle eviction values through settings cycling (origin: round-1 fix 721f45b59; stack commit aa98c9aca)\n\n* fix(coding-agent): post-rebase hardening of passive hydration, snapshots, and depth ingestion\n\n- preserve daemon routable IDs for passive children (origin: PR #583)\n- recheck guarded passive hydration and heartbeat restores (origin: PR #583)\n- repair wrong-kind pending hydration joins (origin: PR #583)\n- fence passive hydration during update restart preparation (origin: PR #583)\n- validate persisted RLM depth before constructor ingestion (origin: PR #584)\n- retry attach child snapshots across session replacement (origin: PR #587)\n- retain effective depth for legacy parented new sessions (origin: PR #589)\n- coordinate parent passivation with child hydration publication (origin: PR #589)\n\n* fix(coding-agent): leave shared passive hydration resident on guard cancellation\n\nThe ownership-blind close closed shared hydrations out from under concurrent wakes (both interleavings); the idle sweep is the ownership-free arbiter.\n\norigin: round-4 fix b95640046 / PR #583\n\n* fix(coding-agent): prefer persisted header depth for legacy rehydration entries\n\nThe legacy-entry rehydration fallback (entry.rlmDepth ?? 1) is passed as\nconfig, which outranks the opened transcript header in AgentSession — so a\nnested legacy child whose header carried a deeper persisted depth woke at\ndepth 1, weakening the host recursion gate. Registry depth stays\nauthoritative when present; otherwise the validated header depth wins and 1\nremains the last-resort default for fully legacy children.\n\norigin: PR #584 fallback restored in round-1 triage; surfaced by post-rebase\nbot review of PR #589.\n\n* fix(coding-agent): fence chain hydration against parent passivation; invalidate stale scope roots\n\n* fix(coding-agent): bound the session snapshot stabilization loop\n\n* fix(coding-agent): restore child event forwarder when passivation close fails\n\nPassivation teardown invoked the retained child's event-forwarder\nunsubscribe before closing the session. When the close failed and the\nchild was re-adopted, the forwarder was gone, so a still-resident child\nstopped emitting rlm_child_update to its parent. Teardown now returns\nthe unsubscribe so the passivation path only invokes it after a\nsuccessful close and restores it on the failed-close re-adopt path.\n\n* fix(coding-agent): close child passivation races\n\n- Keep snapshot messages aligned with the final runtime session summary after stabilization exhaustion.\n- Retry passive child hydration when the child starts passivating inside the hydration window.\n- Apply archive and scheduled-job cancellation when kill joins a resume-preserving close.\n\n* fix(coding-agent): upgrade cascading close reasons\n\n- Track the applied close reason and resident descendant states through cascading teardown.\n- Apply stronger joined close effects uniformly to parents and captured descendants.\n- Cover shutdown-to-killed descendant cleanup and completed-to-killed idempotency.\n\n* fix(coding-agent): preserve passive child id on hydration retry\n\n- Forward the restored active-session ID when retrying after a mismatched pending open.\n- Cover the pending-open race through passive-child hydration.\n\n* fix(coding-agent): recover passivation waiters\n\n- Treat failed passivation settlement as a join signal before retrying resident sessions.\n- Cover concurrent open, message delivery, and hydration after passivation rejection.\n\n* fix(coding-agent): harden passivation close races\n\n- Preserve stronger close-reason upgrades when the joined close fails.\n- Run child passivation outside the supervisor-wide eviction fence.\n- Complete reason-upgrade persistence across targets and record the stronger reason before propagating errors.\n\n* fix(coding-agent): preserve passive opener state across races\n\n- Defer root parent client env adoption until passive hydration and its open guard succeed.\n- Join opening or resident passive targets when parent-change restart resolution races hydration.","tree":"4726a5cfd80482f3088cea12d58430cc74872c6b"}},{"name":"4428-remove-legacy-pi-mono-tools.test.ts","mode":"0100644","size":5577,"lastCommit":{"hash":"61eb64748eb077e2a084432db92d101a2a83e146","oid":"61eb64748eb077e2a084432db92d101a2a83e146","parents":["0940833b771fbaf5144451988604b310a96722fd"],"author":{"name":"Sebastian Müller","email":"32787133+sethkarten@users.noreply.github.com","when":"2026-08-27T00:24:10+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-26T15:24:10-07:00"},"message":"Minimal CPython REPL runtime (rlm.repl) (#1685)\n\n* feat(coding-agent): add async-by-default bash() to the kernel runtime\n\n* chore(coding-agent): tighten bash() comments and changelog fragment\n\n* feat(coding-agent): add a standalone CPython REPL runtime speaking JSON lines over stdio\n\n* chore(coding-agent): tighten REPL runtime comments\n\n* feat(coding-agent): run the kernel on the REPL runtime over stdio\n\n* fix(coding-agent): reject pending host requests on kernel teardown\n\nThe runtime now fails pending host_request futures when stdin hits EOF or\na shutdown request arrives, so a cell awaiting a host reply can no longer\nblock _serve from consuming the shutdown and wedge the process. Startup\nand busy-kernel messages plus the ipython tool description now say Python\nkernel, matching the default REPL runtime client.\n\n* chore(coding-agent): describe the kernel-heavy test tag client-neutrally\n\n* feat(coding-agent): make the REPL runtime the only kernel\n\nRemoves the Jupyter/ipykernel/ZMQ kernel client, the fork server, the\nPRIME_AGENT_KERNEL escape hatch, and the %%bash/%cd/%env cell rewriting.\nMagic-style cells (%/%%/!) return a one-line error naming the Python or\nbash() replacement. The kernel venv no longer installs ipykernel;\nexisting venvs are rebuilt once via the bootstrap schema bump. Old\nsnapshot artifacts still restore through the runtime's pickle compat.\n\n* fix(coding-agent): close MCP transports in REPL shutdown\n\n* fix(coding-agent): address bash() review findings — exact tail retention, foreground-status lifecycle with group anchoring, post-kill forkserver reap, Windows start-id parity, executor-free await\n\n* fix(coding-agent): tree-kill bash() process trees on Windows and make running reflect group liveness\n\n* fix(runtime): address repl runtime review findings\n\n- revalidate targeted interrupts through SIGINT delivery so a stale signal\n cannot cancel a later request\n- preserve a parked untargeted interrupt while another request is inflight\n- reject non-string interrupt ids and validate snapshot options\n (prune_oversized bool, max_bytes/max_variable_bytes present => int)\n- guard str(exc) in error/skip/fail reasons so a broken __str__ cannot\n kill the runtime\n- fail the snapshot when the manifest write fails (before any pruning)\n- report 'snapshot not found' reason on restore of a missing path\n- wait unbounded for the output-pump drain marker so done never precedes\n captured output and marker bytes never leak\n- document that aggregate-cap skips are not pruned\n\n* fix(coding-agent): carry bash() status pipe as stdin so strict-POSIX shells accept single-digit fd redirections\n\n* fix(coding-agent): address host-swap review findings — runtime-neutral kernel wording, %cd/%env rewrite fidelity, linear-time magic regexes, restart supersession guard\n\n* fix(coding-agent): reject stale column-0 line magics on any cell line, not just the first\n\n* fix(coding-agent): close status fds when wake-pipe creation fails and gate bash() commands on orphan-journal registration\n\n* fix(coding-agent): strip quoted %cd targets, use UTF-16-safe %env parsing, and expand $var/${var} values PEP-215-style\n\n* fix(coding-agent): fail rlm.run fast outside a live kernel so vitest workers cannot hang on a comm that never replies\n\n* fix(coding-agent): clear the active cell id before terminal events so late background output is never tagged with a finished cell\n\n* fix(coding-agent): update legacy IPython-era tests to assert cutover behavior\n\n* fix(coding-agent): describe the column-0 magic scan without referencing the removed rewrite backend\n\n* fix(coding-agent): consume parked interrupts on compile failures and survive user-closed stdio in the drain path\n\n* fix(coding-agent): redact bare %env listings, prefer '=' in %env parsing, echo %cd targets, and keep graceful shutdowns owning their cleanup\n\n* fix(coding-agent): reject kernel startup promptly on spawn errors and commit %cd previous-dir tracking only after chdir succeeds\n\n* fix(coding-agent): trim ParsedIpythonBashCell to the body field its callers use\n\n* fix(coding-agent): kill full process trees in the Windows orphan reaper via taskkill /T\n\n* fix(coding-agent): survive compile-phase crashes and fd-reuse drain hangs in the REPL runtime\n\n* fix(coding-agent): shield snapshot prune deletions from interrupts and pin the host comm probe to its real seam\n\n* fix(coding-agent): route list_names through the per-request backstop and skip non-string namespace keys\n\n* fix(coding-agent): reject snapshot requests whose manifest path aliases the payload path\n\n* fix(coding-agent): reject negative snapshot size caps that would prune every user variable\n\n* fix(coding-agent): kill one-shot await bash() on cancel, resolve Windows helpers via System32, retry taskkill after reap, and fail closed on orphan-journal enrollment\n\n* fix(coding-agent): attribute REPL stream output at write time so raw fd and user-thread bytes never carry another cell's id\n\n* fix(coding-agent): surface unattributed REPL stream output as separate background output instead of dropping or merging it\n\n* fix(coding-agent): confirm group exit before a cancelled one-shot bash() await propagates and complete-write orphan-journal records\n\n* fix(coding-agent): expose a working sys.stdout.buffer on the tagged REPL writer routing bytes through the null-attributed raw channel\n\n* fix(coding-agent): mark between-cell background output truncated when the pending buffer cap is hit\n\n* fix(coding-agent): shield the cancelled-await bash() confirm-exit from re-cancellation, fail clearly without bash on Windows, and fence slow pumps out of result assembly\n\n* fix(coding-agent): survive hostile protocol lines in the REPL reader thread and interrupt without pthread_kill on Windows\n\n* fix(coding-agent): send the protocol shutdown from dispose() so the runtime closes MCP servers and kills live bash groups before the hard kill\n\n* fix(coding-agent): flag the pump's read-to-commit window so the bash() drain fence cannot miss an in-flight chunk\n\n* fix(coding-agent): guard the whole REPL request line against hostile input, reject duplicate in-flight ids, complete short buffer-pipe writes, and clean the snapshot temp file on KeyboardInterrupt\n\n* fix(coding-agent): drop stale between-cell background output on kernel teardown so it cannot surface after a restart\n\n* fix(coding-agent): assert the tagged channel only in the large buffer-write REPL test since cross-channel ordering is not guaranteed\n\n* fix(coding-agent): resolve taskkill via absolute System32 path in the host orphan reaper\n\n* fix(coding-agent): write the inactive orphan-journal record only after a delivered kill so undelivered signals leave the host reaper in charge\n\n* fix(coding-agent): keep a REPL request interrupt-targetable through its trailing-expression repr and output drain until done is emitted\n\n* fix(coding-agent): count an already-exited leader as delivered in the Windows bash() reap so clean exits still journal inactive\n\n* fix(coding-agent): reject NaN and Infinity in emit() payloads before they corrupt REPL protocol framing\n\n* chore(coding-agent): correct the stale ipykernel requirement on the python override doc\n\n* chore(coding-agent): drop migration-era wording from kernel comments\n\n* fix(coding-agent): resolve trusted absolute shell host-side and close Windows journal/reap gaps\n\n* fix(coding-agent): best-effort-kill pid-only orphan records in daemon force-stop and recovery reaps\n\n* refactor(coding-agent): drop the magic-cell rejection gate\n\n%-prefixed and !-prefixed cells now reach CPython and fail with its own\nSyntaxError, which names the offending line. The rejection layer guarded\nagainst model-produced IPython syntax, but with the shipped prompt fresh\nsessions do not produce it, and the plain SyntaxError is protection enough.\nparseIpythonBashCell stays: transcripts from ipykernel-era sessions render\n%%bash cells with shell highlighting forever.\n\n* fix(coding-agent): report a committed destructive snapshot as success even when an interrupt was parked\n\n* chore(ai): drop stray live-regen drift in models.generated.ts\n\nad657d7ec accidentally committed generate-models output produced by a local\nbuild; the catalog belongs to its own regen PRs.\n\n* test(coding-agent): expect a plain SyntaxError for legacy %%bash cells after the magic-rejection gate removal\n\n* fix(coding-agent): consume a finishing-targeted interrupt after a completed state request instead of failing the done\n\n* fix(coding-agent): exit the REPL runtime when its owner dies even during a busy cell\n\n* fix(coding-agent): resolve the kernel bash shell only from trusted absolute paths on Windows\n\n* fix(coding-agent): contain Windows bash children with kill-on-close job objects\n\n* test(coding-agent): cover owner death during a non-yielding REPL cell\n\n* fix(coding-agent): skip concurrently deleted names during snapshot instead of aborting\n\n* fix(coding-agent): fall back to taskkill when job termination fails\n\n* fix(coding-agent): stop telling REPL-default users they need ipykernel\n\n* fix(coding-agent): clear the SIGINT target when its request finishes\n\n* test(coding-agent): drop migration-era wording from the %%bash rejection comment\n\n* fix(coding-agent): start Windows bash children suspended and fail closed when job containment cannot be established\n\n* fix(coding-agent): re-assert the kernel SIGINT handler between cells so a cell rebinding SIGINT cannot break interrupts\n\n* fix(coding-agent): kill the whole tree for enriched orphan records on Windows force-stop\n\nstopTrackedProcess signals only the shell pid on Windows; use killOrphanProcess (taskkill /T) after the identity check, matching the owned-session-worker and daemon-supervisor reapers.\n\n* docs(coding-agent): describe current magic-cell behavior in release notes\n\nMagic-style cells fail with a plain SyntaxError; the migration error and %cd/%env rewrites were removed, so the notes stop claiming them.\n\n* fix(coding-agent): skip the liveness check when the orphan identity is stale\n\nA reused pid looked like a failed kill after the identity re-check skipped taskkill, blocking worker cleanup with a spurious failure.\n\n* fix(coding-agent): journal Windows bash() children before job assignment so a kernel kill mid-spawn cannot leak an unjournaled suspended process\n\n* fix(coding-agent): pre-create the Windows bash() job before spawn and contain the child before the journal start-id query\n\n* fix(coding-agent): create Windows bash() children atomically inside the kill-on-close job via PROC_THREAD_ATTRIBUTE_JOB_LIST, closing the Popen-to-assignment leak window\n\n* chore(coding-agent): compress the atomic-job-association comments to one-line rationale\n\n* fix(coding-agent): send duplicate-id protocol errors outside the interrupt lock and reject int payloads in the captured stdout buffer\n\n* docs(coding-agent): update the kernel provisioner docstring for the REPL/IPython split\n\n* fix(coding-agent): retain the Windows bash() process handle through job cleanup and taskkill fallbacks so a recycled pid can never be killed\n\n* fix(coding-agent): serialize Windows bash() abort cleanup under the kill lock so shutdown taskkill can never race the process-handle close\n\n* fix(coding-agent): commit REPL snapshot payload and manifest atomically via unique temp files with guaranteed cleanup and parked-SIGINT restore\n\n* fix(coding-agent): stage REPL restore before an interrupt-parked apply and recover committed snapshot/restore results from protocol interrupts so a committed operation is never misreported as failed\n\n* chore(coding-agent): compress restore-shield rationale comments to one line each\n\n* fix(coding-agent): surface unattributed background output in IPython cell details and render it after the traceback in the expanded cell view\n\n* docs(coding-agent): replace stale Jupyter comm vocabulary in rlm-runtime failure modes and focused validation with stdio-transport equivalents\n\n* docs(coding-agent): describe the REPL trust boundary and runtime-bootstrap failure in stdio terms and drop the removed TokenUsage export\n\n* fix(runtime): address REPL review findings\n\n* fix(runtime): preserve near-cap snapshots\n\n---------\n\nCo-authored-by: Seth ","tree":"a251ca47e114be10eb5c23cfb1de655c8aeeb954"}},{"name":"4435-auth-error-login-guidance.test.ts","mode":"0100644","size":1764,"lastCommit":{"hash":"f3130cc518dada33e4933e2c14d9ebbb940009d5","oid":"f3130cc518dada33e4933e2c14d9ebbb940009d5","parents":["a3b241a1222a22f847766e3df78df72a051d0ca2"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-08T11:50:59-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-08T11:50:59-07:00"},"message":"mark stale provider auth after repeated failures (#335)\n\n* fix stale provider auth after repeated failures\n\n* fix stale auth source fallbacks\n\n* fix stale auth review edge cases\n\n* fix stale auth login display\n\n* fix stale auth retry edge cases\n\n* fix stale auth source fingerprints\n\n* fix stale auth source tracking\n\n* fix stale models json key rotation\n\n* fix stale auth final guidance\n\n* fix auth guidance regression test\n\n* fix stale auth login ordering\n\n* fix auth stale retry cancellation","tree":"d8b48c8b7930f3e0629e5c1d39aec14458133234"}},{"name":"4482-heartbeat-injected-prompt.test.ts","mode":"0100644","size":22146,"lastCommit":{"hash":"3b2d1f227556ea7dbb33dd394e9ba3990cd0f320","oid":"3b2d1f227556ea7dbb33dd394e9ba3990cd0f320","parents":["941576dbec6d388de6b9f3cb61bce90cce3f55c4"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-03T09:56:38+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-03T09:56:38+02:00"},"message":"refactor(coding-agent): harden session action races (#576)\n\n* refactor(coding-agent): harden session action races\n\n* fix(coding-agent): revalidate turn batches after commit fence acquisition\n\n* fix(coding-agent): reschedule pump after batch revalidation deferral\n\n* fix(coding-agent): restore cross-lane queue-key coalescing and compaction pending checks\n\nThe underlying bugs originate in PR #573, but this fix lands at the stack head in PR #576 to avoid rebasing three dependent PRs immediately before release.\n\n* refactor(coding-agent): delete compensating scheduler state\n\n* fix(coding-agent): count only pending successors after compaction\n\n* fix(coding-agent): honor prompt abort during fence wait and fix compaction test await\n\n* test(coding-agent): remove flaky post-compaction continue regression\n\nThe fake-timer event-await combination never completes under CI timing.\nThe production change it covered (pending-successor counting after\nthreshold compaction, 697fcf474) remains covered by the passing\n'resumes after threshold compaction when only agent-level queued\nmessages exist' test exercising the same projection.\n\n* fix(coding-agent): reject fence waiters on session disposal\n\n* fix(coding-agent): restore settlement, ordering, and idle guards\n\nSeveral fixes originate in #574/#575 but land at the stack head to avoid rebasing the whole chain.\n\n* fix(coding-agent): serialize injected admission with the commit fence\n\n* fix(coding-agent): release fence on admission failure and unify pause-aware admission\n\n* fix(coding-agent): stabilize waitForIdle event-queue wait and drop dead queue-key probe\n\n* fix(coding-agent): preserve batched action message order (fixes #576)\n\n* fix(coding-agent): revalidate commands after commit fence (fixes #576)\n\n---------\n\nCo-authored-by: Alex Zhang ","tree":"424d958905333635c45fb3fb7fbc885bb4bbc905"}},{"name":"4491-provider-stale-after-401.test.ts","mode":"0100644","size":9553,"lastCommit":{"hash":"645f5147e617dffbc4536371aab31310cecd2204","oid":"645f5147e617dffbc4536371aab31310cecd2204","parents":["a952e011590350a183662f1486b7ee50d7ab75cd"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-08T15:57:24-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-08T15:57:24-07:00"},"message":"retry provider errors before surfacing them (#347)\n\n* fix retrying provider errors\n\n* fix(coding-agent): bound permanent provider retries\n\n* fix(coding-agent): preserve retry budget across compaction\n\n* fix(coding-agent): cancel compaction retry continuation\n\n* fix(coding-agent): skip faux queue retry\n\n* fix(coding-agent): skip lifecycle failures in retry\n\n* fix retrying provider errors\n\n* fix(coding-agent): bound permanent provider retries\n\n* fix(coding-agent): preserve retry budget across compaction\n\n* fix(coding-agent): cancel compaction retry continuation\n\n* fix(coding-agent): skip faux queue retry\n\n* fix(coding-agent): skip lifecycle failures in retry\n\n* fix(coding-agent): restore raw queued text on clear\n\n* fix(coding-agent): cap structured auth retries\n\n* fix(coding-agent): await exhausted auth retry cleanup","tree":"6de27881a68086acf1f4e1171fd20c735fd2e1b1"}},{"name":"4509-side-questions.test.ts","mode":"0100644","size":47194,"lastCommit":{"hash":"bab124212fd5451beb071a884b5771ac7c1a8e1a","oid":"bab124212fd5451beb071a884b5771ac7c1a8e1a","parents":["ee8fd699617e8b66cb4bf36c97872c8fe52192e3"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-29T10:52:17+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-29T10:52:17+02:00"},"message":"fix(coding-agent): single-source the interactive queue state (#1842)\n\n* fix(coding-agent): single-source the interactive queue state\n\n* fix(coding-agent): close queue-state races around rebind, moves, and failed edits\n\n- rebindCurrentSession: re-sync sessionActions after resubscribing; a\n session_action_update fired in the unsubscribed gap was lost forever.\n- browseQueueSelection: block browsing while a queue move RPC is pending,\n matching the pendingQueueEdit guard, so the move response cannot reselect\n the original item under newly browsed editor text.\n- moveQueueSelection: when the applied move's session_action_update has not\n landed yet (sessionActions reference unchanged), mirror the swap locally so\n the moved selection is not dropped against the pre-move snapshot; reconcile\n the selection in the error path.\n- applyQueueSelection: reconcile the selection after the pending-edit flag\n clears, so a rejected/failed edit no longer leaves Enter targeting a row\n that was removed while events were suppressed.","tree":"52746c80198390bf73b8c68244b982f42389ace9"}},{"name":"4519-heartbeat-rebirth.test.ts","mode":"0100644","size":7231,"lastCommit":{"hash":"ceb418049dd929676beb13f77a6d697bcd52f854","oid":"ceb418049dd929676beb13f77a6d697bcd52f854","parents":["809027134a1fb2064fe152507abffcfc5610e486"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-28T17:09:00+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-28T17:09:00+02:00"},"message":"refactor(coding-agent): centralize agent-message admission in AgentSession (#1861)\n\n* refactor(coding-agent): query agent peers on demand instead of broadcasting mirrors\n\n* refactor(coding-agent): centralize agent-message admission in AgentSession\n\n* fix(coding-agent): respond to unknown worker commands instead of dropping them\n\nLegacy worker_sync_agent_peers commands from an older supervisor fell\nthrough handleWorkerCommand without a response, forcing the requester\nto wait out its full 5s timeout on every peer sync. A default case now\nwrites an immediate failure for any unhandled worker command.\n\n* fix(daemon): re-check cron job runnability after prompt admission fence\n\nrunCronJob snapshotted the runnable job before promptHeartbeat/\npromptUntilAccepted, which can wait on the session admission fence. A job\ncancelled or completed during that wait was still delivered. Re-check via\nthe admissionCommitted hook and skip when the job is no longer runnable.\n\n* fix(daemon): skip cron delivery when the job content changed during admission\n\nupdateRlmHeartbeat mutates prompt/deliveryMode in place under the same job\nid, so the existence-only admissionCommitted re-check still delivered the\nstale snapshot captured before the admission fence wait. Compare the\nrefreshed job's prompt and deliveryMode and skip on mismatch; the skip\nreschedules nextRunAt so the updated instruction is delivered next cycle.\n\n* fix(coding-agent): re-check prompt admission after async input normalization\n\n_prompt ran admissionCommitted before _normalizeSubmission, but async\nextension input handlers are awaited between that check and\n_admitSessionInput, so a cron job cancelled or updated during the await\nstill delivered its stale prompt. Re-run the callback after the awaited\nnormalization so invalidated content is not admitted.","tree":"01c8e55a80bbbc750ae8d927b1ee91fcc5b4aad0"}},{"name":"4527-worker-heartbeat-scheduling.test.ts","mode":"0100644","size":2817,"lastCommit":{"hash":"4d19005d4a25b10ce6d90fdd4961ed374c64ea17","oid":"4d19005d4a25b10ce6d90fdd4961ed374c64ea17","parents":["461bae098e0eec5cd03c3d63453ddd86222ed03a"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-13T17:47:15-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-13T17:47:15-07:00"},"message":"isolate daemon sessions in worker processes (#383)\n\n* perf(coding-agent): add large daemon attach benchmark\n\n* feat(coding-agent): isolate session execution in workers\n\n* fix(coding-agent): reconnect after supervisor replacement\n\n* fix(tui): preserve input across fullscreen handoff\n\n* fix(coding-agent): prevent archived heartbeat revival\n\n* fix(coding-agent): cancel orphan heartbeat sessions\n\n* fix(tui): preserve drafts across daemon refreshes\n\n* fix(coding-agent): separate daemon resyncs from replacements\n\n* fix(coding-agent): stabilize daemon streaming ui\n\n* refactor(coding-agent): remove obsolete subagent tree\n\n* feat(coding-agent): show subagent recaps inline\n\n* fix(coding-agent): refine subagent summary spacing\n\n* fix(coding-agent): preserve full subagent row selection\n\n* fix(coding-agent): align subagent summary rows\n\n* fix(coding-agent): preserve reasoning during daemon resync\n\n* fix(coding-agent): isolate heartbeat scheduling per worker (ENG-4527)\n\n* fix(coding-agent): retry partial daemon reconnects\n\n* fix(coding-agent): harden isolated daemon recovery\n\n* fix(coding-agent): close daemon recovery races\n\n* fix(coding-agent): validate daemon recovery state\n\n* fix(coding-agent): close isolated worker recovery gaps\n\n* fix(coding-agent): verify orphan process identity\n\n* fix(coding-agent): isolate worker client capabilities\n\n* fix(coding-agent): preserve daemon terminal ordering\n\n* fix(coding-agent): serialize durable daemon state\n\n* fix(coding-agent): avoid duplicate worker recovery\n\n* fix(coding-agent): isolate peer sync failures\n\n* fix(coding-agent): fail unanswered rpc commands\n\n* fix(coding-agent): distinguish lease contention","tree":"a3a976aeaaad976da0a455ac277039862d2c6da8"}},{"name":"4529-leading-newline-bash-cell.test.ts","mode":"0100644","size":2541,"lastCommit":{"hash":"61eb64748eb077e2a084432db92d101a2a83e146","oid":"61eb64748eb077e2a084432db92d101a2a83e146","parents":["0940833b771fbaf5144451988604b310a96722fd"],"author":{"name":"Sebastian Müller","email":"32787133+sethkarten@users.noreply.github.com","when":"2026-08-27T00:24:10+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-26T15:24:10-07:00"},"message":"Minimal CPython REPL runtime (rlm.repl) (#1685)\n\n* feat(coding-agent): add async-by-default bash() to the kernel runtime\n\n* chore(coding-agent): tighten bash() comments and changelog fragment\n\n* feat(coding-agent): add a standalone CPython REPL runtime speaking JSON lines over stdio\n\n* chore(coding-agent): tighten REPL runtime comments\n\n* feat(coding-agent): run the kernel on the REPL runtime over stdio\n\n* fix(coding-agent): reject pending host requests on kernel teardown\n\nThe runtime now fails pending host_request futures when stdin hits EOF or\na shutdown request arrives, so a cell awaiting a host reply can no longer\nblock _serve from consuming the shutdown and wedge the process. Startup\nand busy-kernel messages plus the ipython tool description now say Python\nkernel, matching the default REPL runtime client.\n\n* chore(coding-agent): describe the kernel-heavy test tag client-neutrally\n\n* feat(coding-agent): make the REPL runtime the only kernel\n\nRemoves the Jupyter/ipykernel/ZMQ kernel client, the fork server, the\nPRIME_AGENT_KERNEL escape hatch, and the %%bash/%cd/%env cell rewriting.\nMagic-style cells (%/%%/!) return a one-line error naming the Python or\nbash() replacement. The kernel venv no longer installs ipykernel;\nexisting venvs are rebuilt once via the bootstrap schema bump. Old\nsnapshot artifacts still restore through the runtime's pickle compat.\n\n* fix(coding-agent): close MCP transports in REPL shutdown\n\n* fix(coding-agent): address bash() review findings — exact tail retention, foreground-status lifecycle with group anchoring, post-kill forkserver reap, Windows start-id parity, executor-free await\n\n* fix(coding-agent): tree-kill bash() process trees on Windows and make running reflect group liveness\n\n* fix(runtime): address repl runtime review findings\n\n- revalidate targeted interrupts through SIGINT delivery so a stale signal\n cannot cancel a later request\n- preserve a parked untargeted interrupt while another request is inflight\n- reject non-string interrupt ids and validate snapshot options\n (prune_oversized bool, max_bytes/max_variable_bytes present => int)\n- guard str(exc) in error/skip/fail reasons so a broken __str__ cannot\n kill the runtime\n- fail the snapshot when the manifest write fails (before any pruning)\n- report 'snapshot not found' reason on restore of a missing path\n- wait unbounded for the output-pump drain marker so done never precedes\n captured output and marker bytes never leak\n- document that aggregate-cap skips are not pruned\n\n* fix(coding-agent): carry bash() status pipe as stdin so strict-POSIX shells accept single-digit fd redirections\n\n* fix(coding-agent): address host-swap review findings — runtime-neutral kernel wording, %cd/%env rewrite fidelity, linear-time magic regexes, restart supersession guard\n\n* fix(coding-agent): reject stale column-0 line magics on any cell line, not just the first\n\n* fix(coding-agent): close status fds when wake-pipe creation fails and gate bash() commands on orphan-journal registration\n\n* fix(coding-agent): strip quoted %cd targets, use UTF-16-safe %env parsing, and expand $var/${var} values PEP-215-style\n\n* fix(coding-agent): fail rlm.run fast outside a live kernel so vitest workers cannot hang on a comm that never replies\n\n* fix(coding-agent): clear the active cell id before terminal events so late background output is never tagged with a finished cell\n\n* fix(coding-agent): update legacy IPython-era tests to assert cutover behavior\n\n* fix(coding-agent): describe the column-0 magic scan without referencing the removed rewrite backend\n\n* fix(coding-agent): consume parked interrupts on compile failures and survive user-closed stdio in the drain path\n\n* fix(coding-agent): redact bare %env listings, prefer '=' in %env parsing, echo %cd targets, and keep graceful shutdowns owning their cleanup\n\n* fix(coding-agent): reject kernel startup promptly on spawn errors and commit %cd previous-dir tracking only after chdir succeeds\n\n* fix(coding-agent): trim ParsedIpythonBashCell to the body field its callers use\n\n* fix(coding-agent): kill full process trees in the Windows orphan reaper via taskkill /T\n\n* fix(coding-agent): survive compile-phase crashes and fd-reuse drain hangs in the REPL runtime\n\n* fix(coding-agent): shield snapshot prune deletions from interrupts and pin the host comm probe to its real seam\n\n* fix(coding-agent): route list_names through the per-request backstop and skip non-string namespace keys\n\n* fix(coding-agent): reject snapshot requests whose manifest path aliases the payload path\n\n* fix(coding-agent): reject negative snapshot size caps that would prune every user variable\n\n* fix(coding-agent): kill one-shot await bash() on cancel, resolve Windows helpers via System32, retry taskkill after reap, and fail closed on orphan-journal enrollment\n\n* fix(coding-agent): attribute REPL stream output at write time so raw fd and user-thread bytes never carry another cell's id\n\n* fix(coding-agent): surface unattributed REPL stream output as separate background output instead of dropping or merging it\n\n* fix(coding-agent): confirm group exit before a cancelled one-shot bash() await propagates and complete-write orphan-journal records\n\n* fix(coding-agent): expose a working sys.stdout.buffer on the tagged REPL writer routing bytes through the null-attributed raw channel\n\n* fix(coding-agent): mark between-cell background output truncated when the pending buffer cap is hit\n\n* fix(coding-agent): shield the cancelled-await bash() confirm-exit from re-cancellation, fail clearly without bash on Windows, and fence slow pumps out of result assembly\n\n* fix(coding-agent): survive hostile protocol lines in the REPL reader thread and interrupt without pthread_kill on Windows\n\n* fix(coding-agent): send the protocol shutdown from dispose() so the runtime closes MCP servers and kills live bash groups before the hard kill\n\n* fix(coding-agent): flag the pump's read-to-commit window so the bash() drain fence cannot miss an in-flight chunk\n\n* fix(coding-agent): guard the whole REPL request line against hostile input, reject duplicate in-flight ids, complete short buffer-pipe writes, and clean the snapshot temp file on KeyboardInterrupt\n\n* fix(coding-agent): drop stale between-cell background output on kernel teardown so it cannot surface after a restart\n\n* fix(coding-agent): assert the tagged channel only in the large buffer-write REPL test since cross-channel ordering is not guaranteed\n\n* fix(coding-agent): resolve taskkill via absolute System32 path in the host orphan reaper\n\n* fix(coding-agent): write the inactive orphan-journal record only after a delivered kill so undelivered signals leave the host reaper in charge\n\n* fix(coding-agent): keep a REPL request interrupt-targetable through its trailing-expression repr and output drain until done is emitted\n\n* fix(coding-agent): count an already-exited leader as delivered in the Windows bash() reap so clean exits still journal inactive\n\n* fix(coding-agent): reject NaN and Infinity in emit() payloads before they corrupt REPL protocol framing\n\n* chore(coding-agent): correct the stale ipykernel requirement on the python override doc\n\n* chore(coding-agent): drop migration-era wording from kernel comments\n\n* fix(coding-agent): resolve trusted absolute shell host-side and close Windows journal/reap gaps\n\n* fix(coding-agent): best-effort-kill pid-only orphan records in daemon force-stop and recovery reaps\n\n* refactor(coding-agent): drop the magic-cell rejection gate\n\n%-prefixed and !-prefixed cells now reach CPython and fail with its own\nSyntaxError, which names the offending line. The rejection layer guarded\nagainst model-produced IPython syntax, but with the shipped prompt fresh\nsessions do not produce it, and the plain SyntaxError is protection enough.\nparseIpythonBashCell stays: transcripts from ipykernel-era sessions render\n%%bash cells with shell highlighting forever.\n\n* fix(coding-agent): report a committed destructive snapshot as success even when an interrupt was parked\n\n* chore(ai): drop stray live-regen drift in models.generated.ts\n\nad657d7ec accidentally committed generate-models output produced by a local\nbuild; the catalog belongs to its own regen PRs.\n\n* test(coding-agent): expect a plain SyntaxError for legacy %%bash cells after the magic-rejection gate removal\n\n* fix(coding-agent): consume a finishing-targeted interrupt after a completed state request instead of failing the done\n\n* fix(coding-agent): exit the REPL runtime when its owner dies even during a busy cell\n\n* fix(coding-agent): resolve the kernel bash shell only from trusted absolute paths on Windows\n\n* fix(coding-agent): contain Windows bash children with kill-on-close job objects\n\n* test(coding-agent): cover owner death during a non-yielding REPL cell\n\n* fix(coding-agent): skip concurrently deleted names during snapshot instead of aborting\n\n* fix(coding-agent): fall back to taskkill when job termination fails\n\n* fix(coding-agent): stop telling REPL-default users they need ipykernel\n\n* fix(coding-agent): clear the SIGINT target when its request finishes\n\n* test(coding-agent): drop migration-era wording from the %%bash rejection comment\n\n* fix(coding-agent): start Windows bash children suspended and fail closed when job containment cannot be established\n\n* fix(coding-agent): re-assert the kernel SIGINT handler between cells so a cell rebinding SIGINT cannot break interrupts\n\n* fix(coding-agent): kill the whole tree for enriched orphan records on Windows force-stop\n\nstopTrackedProcess signals only the shell pid on Windows; use killOrphanProcess (taskkill /T) after the identity check, matching the owned-session-worker and daemon-supervisor reapers.\n\n* docs(coding-agent): describe current magic-cell behavior in release notes\n\nMagic-style cells fail with a plain SyntaxError; the migration error and %cd/%env rewrites were removed, so the notes stop claiming them.\n\n* fix(coding-agent): skip the liveness check when the orphan identity is stale\n\nA reused pid looked like a failed kill after the identity re-check skipped taskkill, blocking worker cleanup with a spurious failure.\n\n* fix(coding-agent): journal Windows bash() children before job assignment so a kernel kill mid-spawn cannot leak an unjournaled suspended process\n\n* fix(coding-agent): pre-create the Windows bash() job before spawn and contain the child before the journal start-id query\n\n* fix(coding-agent): create Windows bash() children atomically inside the kill-on-close job via PROC_THREAD_ATTRIBUTE_JOB_LIST, closing the Popen-to-assignment leak window\n\n* chore(coding-agent): compress the atomic-job-association comments to one-line rationale\n\n* fix(coding-agent): send duplicate-id protocol errors outside the interrupt lock and reject int payloads in the captured stdout buffer\n\n* docs(coding-agent): update the kernel provisioner docstring for the REPL/IPython split\n\n* fix(coding-agent): retain the Windows bash() process handle through job cleanup and taskkill fallbacks so a recycled pid can never be killed\n\n* fix(coding-agent): serialize Windows bash() abort cleanup under the kill lock so shutdown taskkill can never race the process-handle close\n\n* fix(coding-agent): commit REPL snapshot payload and manifest atomically via unique temp files with guaranteed cleanup and parked-SIGINT restore\n\n* fix(coding-agent): stage REPL restore before an interrupt-parked apply and recover committed snapshot/restore results from protocol interrupts so a committed operation is never misreported as failed\n\n* chore(coding-agent): compress restore-shield rationale comments to one line each\n\n* fix(coding-agent): surface unattributed background output in IPython cell details and render it after the traceback in the expanded cell view\n\n* docs(coding-agent): replace stale Jupyter comm vocabulary in rlm-runtime failure modes and focused validation with stdio-transport equivalents\n\n* docs(coding-agent): describe the REPL trust boundary and runtime-bootstrap failure in stdio terms and drop the removed TokenUsage export\n\n* fix(runtime): address REPL review findings\n\n* fix(runtime): preserve near-cap snapshots\n\n---------\n\nCo-authored-by: Seth ","tree":"a251ca47e114be10eb5c23cfb1de655c8aeeb954"}},{"name":"4530-ipython-state-restore-message.test.ts","mode":"0100644","size":6476,"lastCommit":{"hash":"61eb64748eb077e2a084432db92d101a2a83e146","oid":"61eb64748eb077e2a084432db92d101a2a83e146","parents":["0940833b771fbaf5144451988604b310a96722fd"],"author":{"name":"Sebastian Müller","email":"32787133+sethkarten@users.noreply.github.com","when":"2026-08-27T00:24:10+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-26T15:24:10-07:00"},"message":"Minimal CPython REPL runtime (rlm.repl) (#1685)\n\n* feat(coding-agent): add async-by-default bash() to the kernel runtime\n\n* chore(coding-agent): tighten bash() comments and changelog fragment\n\n* feat(coding-agent): add a standalone CPython REPL runtime speaking JSON lines over stdio\n\n* chore(coding-agent): tighten REPL runtime comments\n\n* feat(coding-agent): run the kernel on the REPL runtime over stdio\n\n* fix(coding-agent): reject pending host requests on kernel teardown\n\nThe runtime now fails pending host_request futures when stdin hits EOF or\na shutdown request arrives, so a cell awaiting a host reply can no longer\nblock _serve from consuming the shutdown and wedge the process. Startup\nand busy-kernel messages plus the ipython tool description now say Python\nkernel, matching the default REPL runtime client.\n\n* chore(coding-agent): describe the kernel-heavy test tag client-neutrally\n\n* feat(coding-agent): make the REPL runtime the only kernel\n\nRemoves the Jupyter/ipykernel/ZMQ kernel client, the fork server, the\nPRIME_AGENT_KERNEL escape hatch, and the %%bash/%cd/%env cell rewriting.\nMagic-style cells (%/%%/!) return a one-line error naming the Python or\nbash() replacement. The kernel venv no longer installs ipykernel;\nexisting venvs are rebuilt once via the bootstrap schema bump. Old\nsnapshot artifacts still restore through the runtime's pickle compat.\n\n* fix(coding-agent): close MCP transports in REPL shutdown\n\n* fix(coding-agent): address bash() review findings — exact tail retention, foreground-status lifecycle with group anchoring, post-kill forkserver reap, Windows start-id parity, executor-free await\n\n* fix(coding-agent): tree-kill bash() process trees on Windows and make running reflect group liveness\n\n* fix(runtime): address repl runtime review findings\n\n- revalidate targeted interrupts through SIGINT delivery so a stale signal\n cannot cancel a later request\n- preserve a parked untargeted interrupt while another request is inflight\n- reject non-string interrupt ids and validate snapshot options\n (prune_oversized bool, max_bytes/max_variable_bytes present => int)\n- guard str(exc) in error/skip/fail reasons so a broken __str__ cannot\n kill the runtime\n- fail the snapshot when the manifest write fails (before any pruning)\n- report 'snapshot not found' reason on restore of a missing path\n- wait unbounded for the output-pump drain marker so done never precedes\n captured output and marker bytes never leak\n- document that aggregate-cap skips are not pruned\n\n* fix(coding-agent): carry bash() status pipe as stdin so strict-POSIX shells accept single-digit fd redirections\n\n* fix(coding-agent): address host-swap review findings — runtime-neutral kernel wording, %cd/%env rewrite fidelity, linear-time magic regexes, restart supersession guard\n\n* fix(coding-agent): reject stale column-0 line magics on any cell line, not just the first\n\n* fix(coding-agent): close status fds when wake-pipe creation fails and gate bash() commands on orphan-journal registration\n\n* fix(coding-agent): strip quoted %cd targets, use UTF-16-safe %env parsing, and expand $var/${var} values PEP-215-style\n\n* fix(coding-agent): fail rlm.run fast outside a live kernel so vitest workers cannot hang on a comm that never replies\n\n* fix(coding-agent): clear the active cell id before terminal events so late background output is never tagged with a finished cell\n\n* fix(coding-agent): update legacy IPython-era tests to assert cutover behavior\n\n* fix(coding-agent): describe the column-0 magic scan without referencing the removed rewrite backend\n\n* fix(coding-agent): consume parked interrupts on compile failures and survive user-closed stdio in the drain path\n\n* fix(coding-agent): redact bare %env listings, prefer '=' in %env parsing, echo %cd targets, and keep graceful shutdowns owning their cleanup\n\n* fix(coding-agent): reject kernel startup promptly on spawn errors and commit %cd previous-dir tracking only after chdir succeeds\n\n* fix(coding-agent): trim ParsedIpythonBashCell to the body field its callers use\n\n* fix(coding-agent): kill full process trees in the Windows orphan reaper via taskkill /T\n\n* fix(coding-agent): survive compile-phase crashes and fd-reuse drain hangs in the REPL runtime\n\n* fix(coding-agent): shield snapshot prune deletions from interrupts and pin the host comm probe to its real seam\n\n* fix(coding-agent): route list_names through the per-request backstop and skip non-string namespace keys\n\n* fix(coding-agent): reject snapshot requests whose manifest path aliases the payload path\n\n* fix(coding-agent): reject negative snapshot size caps that would prune every user variable\n\n* fix(coding-agent): kill one-shot await bash() on cancel, resolve Windows helpers via System32, retry taskkill after reap, and fail closed on orphan-journal enrollment\n\n* fix(coding-agent): attribute REPL stream output at write time so raw fd and user-thread bytes never carry another cell's id\n\n* fix(coding-agent): surface unattributed REPL stream output as separate background output instead of dropping or merging it\n\n* fix(coding-agent): confirm group exit before a cancelled one-shot bash() await propagates and complete-write orphan-journal records\n\n* fix(coding-agent): expose a working sys.stdout.buffer on the tagged REPL writer routing bytes through the null-attributed raw channel\n\n* fix(coding-agent): mark between-cell background output truncated when the pending buffer cap is hit\n\n* fix(coding-agent): shield the cancelled-await bash() confirm-exit from re-cancellation, fail clearly without bash on Windows, and fence slow pumps out of result assembly\n\n* fix(coding-agent): survive hostile protocol lines in the REPL reader thread and interrupt without pthread_kill on Windows\n\n* fix(coding-agent): send the protocol shutdown from dispose() so the runtime closes MCP servers and kills live bash groups before the hard kill\n\n* fix(coding-agent): flag the pump's read-to-commit window so the bash() drain fence cannot miss an in-flight chunk\n\n* fix(coding-agent): guard the whole REPL request line against hostile input, reject duplicate in-flight ids, complete short buffer-pipe writes, and clean the snapshot temp file on KeyboardInterrupt\n\n* fix(coding-agent): drop stale between-cell background output on kernel teardown so it cannot surface after a restart\n\n* fix(coding-agent): assert the tagged channel only in the large buffer-write REPL test since cross-channel ordering is not guaranteed\n\n* fix(coding-agent): resolve taskkill via absolute System32 path in the host orphan reaper\n\n* fix(coding-agent): write the inactive orphan-journal record only after a delivered kill so undelivered signals leave the host reaper in charge\n\n* fix(coding-agent): keep a REPL request interrupt-targetable through its trailing-expression repr and output drain until done is emitted\n\n* fix(coding-agent): count an already-exited leader as delivered in the Windows bash() reap so clean exits still journal inactive\n\n* fix(coding-agent): reject NaN and Infinity in emit() payloads before they corrupt REPL protocol framing\n\n* chore(coding-agent): correct the stale ipykernel requirement on the python override doc\n\n* chore(coding-agent): drop migration-era wording from kernel comments\n\n* fix(coding-agent): resolve trusted absolute shell host-side and close Windows journal/reap gaps\n\n* fix(coding-agent): best-effort-kill pid-only orphan records in daemon force-stop and recovery reaps\n\n* refactor(coding-agent): drop the magic-cell rejection gate\n\n%-prefixed and !-prefixed cells now reach CPython and fail with its own\nSyntaxError, which names the offending line. The rejection layer guarded\nagainst model-produced IPython syntax, but with the shipped prompt fresh\nsessions do not produce it, and the plain SyntaxError is protection enough.\nparseIpythonBashCell stays: transcripts from ipykernel-era sessions render\n%%bash cells with shell highlighting forever.\n\n* fix(coding-agent): report a committed destructive snapshot as success even when an interrupt was parked\n\n* chore(ai): drop stray live-regen drift in models.generated.ts\n\nad657d7ec accidentally committed generate-models output produced by a local\nbuild; the catalog belongs to its own regen PRs.\n\n* test(coding-agent): expect a plain SyntaxError for legacy %%bash cells after the magic-rejection gate removal\n\n* fix(coding-agent): consume a finishing-targeted interrupt after a completed state request instead of failing the done\n\n* fix(coding-agent): exit the REPL runtime when its owner dies even during a busy cell\n\n* fix(coding-agent): resolve the kernel bash shell only from trusted absolute paths on Windows\n\n* fix(coding-agent): contain Windows bash children with kill-on-close job objects\n\n* test(coding-agent): cover owner death during a non-yielding REPL cell\n\n* fix(coding-agent): skip concurrently deleted names during snapshot instead of aborting\n\n* fix(coding-agent): fall back to taskkill when job termination fails\n\n* fix(coding-agent): stop telling REPL-default users they need ipykernel\n\n* fix(coding-agent): clear the SIGINT target when its request finishes\n\n* test(coding-agent): drop migration-era wording from the %%bash rejection comment\n\n* fix(coding-agent): start Windows bash children suspended and fail closed when job containment cannot be established\n\n* fix(coding-agent): re-assert the kernel SIGINT handler between cells so a cell rebinding SIGINT cannot break interrupts\n\n* fix(coding-agent): kill the whole tree for enriched orphan records on Windows force-stop\n\nstopTrackedProcess signals only the shell pid on Windows; use killOrphanProcess (taskkill /T) after the identity check, matching the owned-session-worker and daemon-supervisor reapers.\n\n* docs(coding-agent): describe current magic-cell behavior in release notes\n\nMagic-style cells fail with a plain SyntaxError; the migration error and %cd/%env rewrites were removed, so the notes stop claiming them.\n\n* fix(coding-agent): skip the liveness check when the orphan identity is stale\n\nA reused pid looked like a failed kill after the identity re-check skipped taskkill, blocking worker cleanup with a spurious failure.\n\n* fix(coding-agent): journal Windows bash() children before job assignment so a kernel kill mid-spawn cannot leak an unjournaled suspended process\n\n* fix(coding-agent): pre-create the Windows bash() job before spawn and contain the child before the journal start-id query\n\n* fix(coding-agent): create Windows bash() children atomically inside the kill-on-close job via PROC_THREAD_ATTRIBUTE_JOB_LIST, closing the Popen-to-assignment leak window\n\n* chore(coding-agent): compress the atomic-job-association comments to one-line rationale\n\n* fix(coding-agent): send duplicate-id protocol errors outside the interrupt lock and reject int payloads in the captured stdout buffer\n\n* docs(coding-agent): update the kernel provisioner docstring for the REPL/IPython split\n\n* fix(coding-agent): retain the Windows bash() process handle through job cleanup and taskkill fallbacks so a recycled pid can never be killed\n\n* fix(coding-agent): serialize Windows bash() abort cleanup under the kill lock so shutdown taskkill can never race the process-handle close\n\n* fix(coding-agent): commit REPL snapshot payload and manifest atomically via unique temp files with guaranteed cleanup and parked-SIGINT restore\n\n* fix(coding-agent): stage REPL restore before an interrupt-parked apply and recover committed snapshot/restore results from protocol interrupts so a committed operation is never misreported as failed\n\n* chore(coding-agent): compress restore-shield rationale comments to one line each\n\n* fix(coding-agent): surface unattributed background output in IPython cell details and render it after the traceback in the expanded cell view\n\n* docs(coding-agent): replace stale Jupyter comm vocabulary in rlm-runtime failure modes and focused validation with stdio-transport equivalents\n\n* docs(coding-agent): describe the REPL trust boundary and runtime-bootstrap failure in stdio terms and drop the removed TokenUsage export\n\n* fix(runtime): address REPL review findings\n\n* fix(runtime): preserve near-cap snapshots\n\n---------\n\nCo-authored-by: Seth ","tree":"a251ca47e114be10eb5c23cfb1de655c8aeeb954"}},{"name":"4531-agent-message-ui.test.ts","mode":"0100644","size":26083,"lastCommit":{"hash":"f8d73abe1f8b55e416f91286ea6c8729becd941a","oid":"f8d73abe1f8b55e416f91286ea6c8729becd941a","parents":["8598dedad5632a9b64e1be4167df19e2d1f5f036"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-14T00:22:03+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-13T15:22:03-07:00"},"message":"Make Ctrl+P toggle sent agent messages too (#1281)\n\n* fix(coding-agent): make ctrl+p toggle sent agent message expansion alongside received\n\n* chore(coding-agent): remove redundant expansion comment\n\n---------\n\nCo-authored-by: Seth ","tree":"8d746954bff766b5ccdd70317df64e6ca80a6af0"}},{"name":"4533-preserve-recap.test.ts","mode":"0100644","size":4209,"lastCommit":{"hash":"0f6a388544df538d6b31ec54e53d1455f7b5a9de","oid":"0f6a388544df538d6b31ec54e53d1455f7b5a9de","parents":["378e32d5813087768ec3f34ed32901813a36744c"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-28T14:15:25+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-28T14:15:25+02:00"},"message":"refactor(coding-agent): read messageCount instead of a shadow flag (#1852)","tree":"ef31d935f0b71cf4adb2adae2f8228c5c44d5f1b"}},{"name":"4536-heartbeat-observability.test.ts","mode":"0100644","size":4293,"lastCommit":{"hash":"90b841996aba818c5ba9b89f64a351d54312d61d","oid":"90b841996aba818c5ba9b89f64a351d54312d61d","parents":["10ef94a7583f0acba130493fe77c555d482fa835"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-16T12:25:49-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-16T12:25:49-07:00"},"message":"add heartbeat observability and management (#425)\n\n* feat(coding-agent): add heartbeat observability (ENG-4536)\n\n* fix(coding-agent): keep heartbeat controls in ipython (ENG-4536)\n\n* fix(coding-agent): refine heartbeat controls (ENG-4536)\n\n* fix(coding-agent): tighten heartbeat navigation (ENG-4536)\n\n* fix(coding-agent): simplify heartbeat stopping (ENG-4536)\n\n* fix(coding-agent): polish heartbeat menu (ENG-4536)\n\n* fix(coding-agent): address heartbeat review feedback (fixes #425)\n\n* fix(coding-agent): cache worker heartbeat catalogs (fixes #425)\n\n* fix(coding-agent): limit heartbeat catalog invalidation (fixes #425)\n\n* fix(coding-agent): keep heartbeat management live (fixes #425)\n\n* fix(coding-agent): refresh stale heartbeat catalogs (fixes #425)\n\n* fix(coding-agent): preserve heartbeat action success (fixes #425)","tree":"49dea5c07a055690bbfbe54627b44b0a1cb888ae"}},{"name":"4537-nonblocking-onboarding.test.ts","mode":"0100644","size":1238,"lastCommit":{"hash":"1ec948118ec93ec60d9fd3eecbbcdbe340b3b455","oid":"1ec948118ec93ec60d9fd3eecbbcdbe340b3b455","parents":["43c20e68cc97c89e346079501efe7c5e0f7a5867"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-10T15:47:49-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-10T15:47:49-07:00"},"message":"stop onboarding from gating normal tui use (#377)\n\n* fix(coding-agent): stop onboarding from gating tui use (ENG-4537)\n\n* fix(coding-agent): retain deferred initial prompts\n\n* style(coding-agent): remove redundant onboarding comments","tree":"e92b1f2d5f135e7caaf1c88e6ff25ee8f7472bc5"}},{"name":"4573-prime-inference-login-default.test.ts","mode":"0100644","size":4370,"lastCommit":{"hash":"ecc2660c25837ffc4fbdefe8862feeb116c71da6","oid":"ecc2660c25837ffc4fbdefe8862feeb116c71da6","parents":["ebb7fd5f6f3ebeb6c0d9dd17266cb2026940d9e0"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-17T17:11:36-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-17T17:11:36-07:00"},"message":"show public models and authenticate on selection (#454)\n\n* fix model authentication in selector (ENG-4575)\n\n* fix stale model auth and autocomplete (ENG-4575)\n\n* fix selector navigation (ENG-4575)\n\n* fix configuration menu navigation (ENG-4575)\n\n* fix scoped model navigation (ENG-4575)\n\n* fix post-login model catalog state (ENG-4575)\n\n* update post-login model regression (ENG-4575)\n\n* sync agents view models after auth (ENG-4575)\n\n* keep model menu open on switch failure (ENG-4575)\n\n* restore model menu after switch failure (ENG-4575)\n\n* fix(coding-agent): reconcile selector auth state\n\nfixes #454\n\n* test(coding-agent): complete selector registry fixture\n\nfixes #454\n\n* fix(coding-agent): align model auth gating\n\nfixes #454\n\n* fix(coding-agent): expose full scoped model catalog\n\nfixes #454","tree":"787f078423eccf4921c60f916882561397f2c1b1"}},{"name":"4575-model-auth-selection.test.ts","mode":"0100644","size":8716,"lastCommit":{"hash":"d90062b608009db4b7062201417ea50481a1cd73","oid":"d90062b608009db4b7062201417ea50481a1cd73","parents":["0f6a388544df538d6b31ec54e53d1455f7b5a9de"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-28T14:15:34+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-28T14:15:34+02:00"},"message":"refactor(coding-agent): derive available connection models on read (#1853)","tree":"bfc94dcb013cdb908289e9bbb120586ee0323d92"}},{"name":"4583-latest-tool-expand-hint.test.ts","mode":"0100644","size":2867,"lastCommit":{"hash":"e751ad727decef619d6bb427e1a27868285f4ee1","oid":"e751ad727decef619d6bb427e1a27868285f4ee1","parents":["3065f5a07b9423cf4bce2a9a6288348aa6bed9e9"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-07-18T00:40:49+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-17T15:40:49-07:00"},"message":"fix(tui): show compact fullscreen image fallbacks (#437)\n\n* fix(tui): compact fullscreen image fallbacks\n\n* fix(coding-agent): show replayed image fallbacks\n\n* fix(coding-agent): include image fallback dimensions\n\n* fix(coding-agent): indent image fallback rows\n\n* test(coding-agent): update image fallback expectation\n\n* test(coding-agent): avoid fallback presentation coupling\n\n* fix(coding-agent): tighten image fallback spacing\n\n* fix(coding-agent): avoid duplicate image fallbacks\n\n* fix(tui): use image metadata in terminal\n\nfixes #437\n\n* fix(tui): preserve image metadata fallbacks\n\nfixes #437\n\n* fix(coding-agent): expose image metadata setting\n\nfixes #437\n\n* fix(coding-agent): avoid duplicate image fallbacks\n\nfixes #437\n\n---------\n\nCo-authored-by: Kevin Thomas ","tree":"ce1be73fdebc0ac211157150d688c0879a6661b8"}},{"name":"4600-supervisor-singleton.test.ts","mode":"0100644","size":44060,"lastCommit":{"hash":"e551b30e3ea400ce27f37c1c238eff7a4f71ca87","oid":"e551b30e3ea400ce27f37c1c238eff7a4f71ca87","parents":["276b6404e6e7bb71786a3bf91ca73c1e8c5f9679"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-04T13:52:03+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-04T13:52:03+02:00"},"message":"fix(coding-agent): reclaim stray supervisor owner dirs (#607)","tree":"f9196433f251cd0d40800d8e8a10a0a4f72a12e2"}},{"name":"4601-worker-snapshot-cache.test.ts","mode":"0100644","size":16532,"lastCommit":{"hash":"941576dbec6d388de6b9f3cb61bce90cce3f55c4","oid":"941576dbec6d388de6b9f3cb61bce90cce3f55c4","parents":["9808aa7fa5dbe9bc855e2f84ca936c9a69c8332c"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-03T09:56:37+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-03T09:56:37+02:00"},"message":"refactor(coding-agent): publish session action protocol (#575)\n\n* refactor(coding-agent): publish session action protocol\n\n* fix(coding-agent): restore queue projection guards and recovery validation\n\n* fix(coding-agent): repair test migrations for session action snapshots\n\n* correcting when multiple messages are sent, how it's counted\n\n* fix(coding-agent): await update supervisor teardown (fixes #575)\n\n---------\n\nCo-authored-by: Alex Zhang ","tree":"81546c387f4627eb678183955565f1596d53e0ce"}},{"name":"4602-snapshot-transfer-idempotency.test.ts","mode":"0100644","size":26825,"lastCommit":{"hash":"ceb418049dd929676beb13f77a6d697bcd52f854","oid":"ceb418049dd929676beb13f77a6d697bcd52f854","parents":["809027134a1fb2064fe152507abffcfc5610e486"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-28T17:09:00+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-28T17:09:00+02:00"},"message":"refactor(coding-agent): centralize agent-message admission in AgentSession (#1861)\n\n* refactor(coding-agent): query agent peers on demand instead of broadcasting mirrors\n\n* refactor(coding-agent): centralize agent-message admission in AgentSession\n\n* fix(coding-agent): respond to unknown worker commands instead of dropping them\n\nLegacy worker_sync_agent_peers commands from an older supervisor fell\nthrough handleWorkerCommand without a response, forcing the requester\nto wait out its full 5s timeout on every peer sync. A default case now\nwrites an immediate failure for any unhandled worker command.\n\n* fix(daemon): re-check cron job runnability after prompt admission fence\n\nrunCronJob snapshotted the runnable job before promptHeartbeat/\npromptUntilAccepted, which can wait on the session admission fence. A job\ncancelled or completed during that wait was still delivered. Re-check via\nthe admissionCommitted hook and skip when the job is no longer runnable.\n\n* fix(daemon): skip cron delivery when the job content changed during admission\n\nupdateRlmHeartbeat mutates prompt/deliveryMode in place under the same job\nid, so the existence-only admissionCommitted re-check still delivered the\nstale snapshot captured before the admission fence wait. Compare the\nrefreshed job's prompt and deliveryMode and skip on mismatch; the skip\nreschedules nextRunAt so the updated instruction is delivered next cycle.\n\n* fix(coding-agent): re-check prompt admission after async input normalization\n\n_prompt ran admissionCommitted before _normalizeSubmission, but async\nextension input handlers are awaited between that check and\n_admitSessionInput, so a cron job cancelled or updated during the await\nstill delivered its stale prompt. Re-run the callback after the awaited\nnormalization so invalidated content is not admitted.","tree":"01c8e55a80bbbc750ae8d927b1ee91fcc5b4aad0"}},{"name":"4603-worker-recovery.test.ts","mode":"0100644","size":41316,"lastCommit":{"hash":"d98d0762c0dea0e4d176233c03965dc05a8b33bf","oid":"d98d0762c0dea0e4d176233c03965dc05a8b33bf","parents":["af0b8e00b9f704e834787fd321065ca78281f2aa"],"author":{"name":"Seth Karten","email":"32787133+sethkarten@users.noreply.github.com","when":"2026-08-20T04:52:30-04:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-20T10:52:30+02:00"},"message":"feat(acp): harden resident session lifecycle (#1494)\n\n* feat(acp): harden resident session lifecycle\n\n* test(daemon): align recovery fixtures with durable context\n\n* fix(acp): validate durable host settings\n\n* fix(daemon): clean up failed resident resources\n\n* fix(daemon): recover owned workers from fresh context\n\n* fix(acp): verify authoritative completion state\n\n* fix(daemon): refresh requested child roster\n\n* fix(acp): read child roster without reattaching\n\n* fix(daemon): preserve telemetry opt-out on recovery\n\n* fix(daemon): scope resident path conflicts\n\n* test(acp): remove runtime publish hook\n\n* fix(acp): drain admitted updates on close\n\n* fix(daemon): merge fresh supervisor defaults\n\n* fix(acp): await autonomous lifecycle settlement\n\n* fix(acp): preserve daemon input fences\n\n* fix(acp): serialize terminal lifecycle turns\n\n* fix(acp): reacquire daemon fences after reconnect\n\n* fix(acp): fail closed across abort cuts\n\n* fix(acp): resume queued input after pause\n\n* fix(acp): invalidate pending pumps on pause\n\n* fix(acp): preserve pause ownership through supervisor\n\n* fix(acp): fail closed on pause cleanup loss\n\n* test(daemon): initialize pause ownership harness\n\n* fix(acp): fence detach pause cleanup\n\n* fix(daemon): preserve detach-all cleanup\n\n* test(daemon): initialize worker pause registry\n\n* fix(daemon): reacquire pauses across release\n\n* fix(daemon): clear stable detach selectors\n\n* fix(daemon): retain detach fences on attach failure\n\n* refactor(daemon): keep descriptor validation private\n\n* docs(changelog): describe ACP lifecycle fencing\n\n* fix(acp): settle restart and failed close lifecycle\n\n* fix(acp): serialize cancel after failed close\n\n* fix(acp): preserve lifecycle reconciliation ordering\n\n* fix(acp): settle deleted child runtimes\n\n* test(acp): consolidate child deletion regressions\n\n* fix(acp): rearm settled child deletion\n\n* fix(acp): preserve recursive terminal settlement\n\n* test(acp): update terminal notice regression","tree":"c2221d32cc071b1d0dc260c1fa1956003b64ece4"}},{"name":"4606-update-restart-coordinator.test.ts","mode":"0100644","size":15149,"lastCommit":{"hash":"941576dbec6d388de6b9f3cb61bce90cce3f55c4","oid":"941576dbec6d388de6b9f3cb61bce90cce3f55c4","parents":["9808aa7fa5dbe9bc855e2f84ca936c9a69c8332c"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-03T09:56:37+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-03T09:56:37+02:00"},"message":"refactor(coding-agent): publish session action protocol (#575)\n\n* refactor(coding-agent): publish session action protocol\n\n* fix(coding-agent): restore queue projection guards and recovery validation\n\n* fix(coding-agent): repair test migrations for session action snapshots\n\n* correcting when multiple messages are sent, how it's counted\n\n* fix(coding-agent): await update supervisor teardown (fixes #575)\n\n---------\n\nCo-authored-by: Alex Zhang ","tree":"81546c387f4627eb678183955565f1596d53e0ce"}},{"name":"4620-fast-mode-child-agents.test.ts","mode":"0100644","size":3924,"lastCommit":{"hash":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","oid":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","parents":["78a0e05d595e3c70ab44be61ad0d92c71a6fd5a6"],"author":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"committer":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"message":"complete guarded RLM results and background completion wakeups\n","tree":"27f93d672adc2bdf84f6b7810e6d33f18f04ba38"}},{"name":"4620-fast-mode-empty-resume.test.ts","mode":"0100644","size":1745,"lastCommit":{"hash":"fd1bd875dc20628b2acd1b46d401ed223c3bcf4d","oid":"fd1bd875dc20628b2acd1b46d401ed223c3bcf4d","parents":["16e97e6dea79e0caf2e8b93e2316910298312da7"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-15T16:23:39-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-15T16:23:39-07:00"},"message":"add openai fast mode (#414)\n\n* feat: add OpenAI fast mode (ENG-4620)\n\n* fix: preserve fast mode on empty resume (ENG-4620)\n\n* fix: serialize fast mode toggles (ENG-4620)\n\n* fix: bump daemon protocol for fast mode (ENG-4620)\n\n* fix: keep fast mode in child agents (ENG-4620)\n\n* fix: route fast mode through daemon (ENG-4620)\n\n* fix: persist fast mode preference (ENG-4620)\n\n* fix: bind fast toggle to session (ENG-4620)\n\n* fix: sync fast mode after model switch (ENG-4620)\n\n* fix: preserve fast mode during tree navigation (ENG-4620)\n\n* fix: preserve fast mode preference on resume (ENG-4620)\n\n* fix: preserve daemon envelope compatibility (ENG-4620)\n\n* fix: render fast mode session metadata (ENG-4620)\n\n* fix: sync effective fast mode state (ENG-4620)\n\n* fix: preserve fast mode preference (ENG-4620)","tree":"7edf160a230308776b77f0ca4b08a1d9e267a1bd"}},{"name":"4620-fast-mode-settings.test.ts","mode":"0100644","size":7014,"lastCommit":{"hash":"848081edb1f9a4f4d643cdb1cc01e1d99bc61cfd","oid":"848081edb1f9a4f4d643cdb1cc01e1d99bc61cfd","parents":["bb3ac37fb7d6d4b59040b84d3c1222d7b406ecf2"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-21T16:08:23+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-21T16:08:23+02:00"},"message":"Support /fast with OpenAI API-key authentication (#1609)\n\n* feat(coding-agent): support /fast with OpenAI API-key authentication (ENG-5425)\n\nWidens supportsFastMode() to admit GPT-5.4/GPT-5.5/GPT-5.6 on the openai\nprovider (openai-responses API) in addition to ChatGPT auth, corrects the\nGPT-5.6 fast-pricing multiplier from 2.5x to 2x per OpenAI's current\npricing table, and updates the /fast unavailable message.\n\nResolves discussion #1595.\n\n* docs(ai): trim pricing comments to source reference only\n\n* chore: drop research scratch file from the branch\n\n* chore: restore package-lock.json from main (unrelated npm churn)\n\n* test: update fast-mode unavailable message assertion","tree":"2cd2f6d4f6043fb57222d008591b9138577c686e"}},{"name":"4645-internal-glm.test.ts","mode":"0100644","size":9829,"lastCommit":{"hash":"2f218e15130904568a805ac8d1920927747d7791","oid":"2f218e15130904568a805ac8d1920927747d7791","parents":["3fc0ac54fad747871c0d2797bce5b21530aecffc"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-07-30T17:38:20+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-30T17:38:20+02:00"},"message":"feat: unified agents and resume view (#541)\n\n* feat(coding-agent): unify searchable session view\n\n* fix(tui): keep session durations stable\n\n* test(daemon): tolerate partial session manager fixtures\n\n* test(tui): narrow session view race coverage\n\n* fix(tui): stabilize unified session catalogs\n\n* fix(tui): preserve session view lifecycle\n\n* fix(tui): preserve compact session view layout\n\n* test(tui): align cumulative session fixtures\n\n* fix(tui): preserve unified session identity and drafts\n\n* feat(tui): color recognized slash commands\n\n* fix(tui): keep view cancels and subagent matches local\n\n* test(tui): avoid platform-specific markdown styling\n\n* fix(tui): align session view status, reselect, and local resume flows\n\n* test(tui): consolidate slash command rendering coverage\n\n* test(tui): cover session view exit shutdown from chat\n\n* fix(tui): preserve dynamic command presentation\n\n* test(coding-agent): deadline-wait the create dedup race\n\n* test(coding-agent): align stacked fixtures\n\n* fix(tui): show seconds for sub-minute heartbeat countdowns\n\n* test(coding-agent): align cumulative session behavior\n\n* fix(coding-agent): flush child traces regardless of retention\n\n* fix(tui): single-own replacement catalog refresh\n\n* fix(tui): preserve drafts and completed child traces\n\n* fix(coding-agent): align template argument whitespace\n\n* fix(tui): restore saved sessions after reconnect\n\n* test(coding-agent): consolidate command presentation coverage\n\n* feat(tui): resume saved sessions from the reply composer\n\n* fix(tui): require heartbeat reconnect probe\n\n* test(coding-agent): align cumulative admission errors\n\n* fix(tui): schedule resumed replies from the resume summary\n\n* test(tui): align lifecycle stash handoff result\n\n* test(coding-agent): preserve unique lifecycle coverage\n\n* fix(tui): preserve inactive reply state on failures\n\n* fix(tui): route local agents view startup\n\n* refactor(tui): single-owner command catalog refresh\n\n* fix(tui): preserve selection after saved resume\n\n* test(tui): align startup lifecycle handoff\n\n* test(tui): resolve cumulative submit fixture\n\n* fix(tui): preserve in-flight reply drafts\n\n* test(tui): align owned startup exit shape\n\n* test(daemon): align delivery waiter contract\n\n* fix(tui): refresh resumed reply failures\n\n* fix(tui): preserve search selection\n\n* style(test): format cumulative prompt coverage\n\n* fix(agents-view): refresh reply target before send\n\n* fix(tui): complete onboarding before sessions\n\n* fix(tui): fence resync rendering by generation\n\n* refactor(coding-agent): consolidate prompt-admission cancellation\n\nExtract one shared waitForPromptAdmission helper and typed\nPromptAdmissionCancelledError into core/prompt-admission.ts, replacing\nthree near-identical copies in agent-session, daemon-mode, and\ndaemon-supervisor along with their copy-paste tests and the supervisor's\nstringly cancelled-status cast.\n\nAlso:\n- make _steeringStopPending a derived getter instead of a cached field\n manually re-synced at 15 call sites\n- surface genuine handoff errors in _isDeferredSessionInputError instead\n of silently requeueing them when the session is coincidentally busy\n- remove the production-dead pauseQueuedWork shim and narrow\n resumeQueuedWork to pump-suspension recovery only\n\n* test(coding-agent): deterministic waits and shared test helpers\n\n- replace the 50ms sleep proving no queued turn starts after\n abortForUpdateRestart with waitForSessionInputIdle\n- replace the 300ms sleep proving no prompt retry after an uncertain\n admission failure with a bounded microtask drain\n- use the shared createDeferred from suite/scheduling.ts instead of two\n local reimplementations\n- guard Reflect-based private access in the agents-view and supervisor\n harnesses so renamed members fail with explicit messages, and document\n why the constructor-bypass supervisor harness exists\n\n* chore(coding-agent): trim redundant comments from recent refactors\n\n* fix(coding-agent): guard session-input error surfacing against listener throws\n\nA throwing extension error listener could escape _surfaceSessionInputError\ninside _isDeferredSessionInputError before the pump requeued undelivered\nprompts, dropping them. Surfacing is now best-effort.\n\n* chore(coding-agent): tighten fix comment\n\n* fix(tui): keep the selection anchor across fallback unblocking\n\nResolving a missing anchor no longer overwrites the persisted anchor\nidentities with the visible fallback row, and typing while the anchor is\npending no longer claims the fallback either, so a late poll that\ndelivers the intended session re-anchors selection instead of opening\nthe wrong session.\n\n* fix(tui): open the unified session view on back navigation in local chats\n\nThe left-arrow back gesture only worked for daemon-backed sessions;\nprocess-local chats could reach the same unified view only via /resume.\nBack navigation now routes through requestAgentsView, which opens the\nlocal session view in place for process-local sessions.\n\n* fix(tui): preserve reply statuses across post-reply catalog refreshes\n\nThe refreshes triggered after a reply send or a failed resumed send used\ndefault error handling, so a failing catalog refresh could overwrite the\nsticky cwd-fallback notice or the send-failure message. Both refreshes\nnow preserve the current status on error.\n\n* chore(tui): drop redundant back-navigation comment\n\n* chore(tui): tighten reply-status comments\n\n* feat(tui): new session shortcut and steer/queue reply delivery\n\nctrl+n (app.agents.new) creates a fresh daemon session from the agents\nview and opens it. In the reply composer, Enter now steers a streaming\nagent and alt+enter (app.message.followUp) queues the reply as a\nfollow-up. While the composer is armed the hint line switches to\ncomposer hints: steer/send/resume & send, queue once text is typed, and\nesc to cancel.\n\n* feat(tui): session-owned slash commands in the reply composer\n\n/compact, /refine, /goal, and /autonomous pass through the daemon\nprompt path from the agents-view reply composer, with slash\nautocomplete active only while a reply target is armed. Other built-in\ncommands are rejected with guidance instead of being sent to the model\nas plain text.\n\n* feat(tui): view commands in the agents view\n\n/new, /fork, /name, and /kill run from the search editor against the\nselected row and from the armed reply composer against its target,\nwith autocomplete in both contexts. /fork forks at the current leaf via\nthe existing daemon fork RPC, resuming saved rows first; /name renames\nactive or saved sessions; /kill stops a running agent. Unknown or\nsession-only commands are rejected with guidance and plain text remains\na search query. The search hints now advertise \"/ commands\".\n\n* fix(tui): harden new-session shortcut and follow-up delivery\n\nctrl+n no longer fires while the reply composer is armed, so an unsent\ndraft cannot be discarded by opening a new session. Alt+Enter now\nexpands paste markers like Enter does. A session created after the view\nalready finished is killed instead of orphaned in the agents list.\n\n* fix(tui): preserve rejected drafts and bind completions to the target cwd\n\nA rejected command no longer loses the typed text (submitValue clears\nthe buffer before onSubmit; the rejection path now restores it unless\nnewer input arrived). The composer autocomplete provider is rebuilt\nwhen a target is armed, so @-file completions resolve in the target\nsession's cwd instead of the view's startup directory.\n\n* fix(tui): harden view commands against races, stale composers, and cancels\n\nAdapter-mode search no longer suggests view commands it will not run.\nArmed view commands cannot double-run (the buffer is already clear\nduring the RPC) and a failed command restores the typed draft in both\nthe composer and the search editor, without clobbering newer input.\nComposer disarm after /kill and /fork is guarded against a composer\nre-armed mid-command, and a fork cancelled by an extension is reported\nas cancelled instead of success.\n\n* fix(tui): report new-session outcome to callers\n\ncreateNewSession returns whether a session was created and opened, so\ncommand callers can restore a cleared draft on failure.\n\n* fix(tui): refresh after failed resumed forks and propagate /new outcome\n\nA saved row resumed for a fork that then fails, cancels, or has nothing\nto fork now refreshes the catalog so the newly live session appears\nimmediately. /new propagates createNewSession's outcome so a failed\ncreate restores the cleared draft.\n\n* fix(tui): enable @-path completion in the reply composer\n\nThe composer provider was built without an fd path, so @ fuzzy file\nsearch always returned empty. The view now resolves fd once and rebinds\nan armed provider when it becomes available.\n\n* fix(tui): create sessions over a dedicated connection\n\nfinish() closes the shared client, which rejected an in-flight create\nand made its session unkillable; a missing client also threw before the\nguard reset, permanently disabling the shortcut. Session creation now\nruns on its own short-lived connection inside the guarded try, so the\norphan-kill path works even after the view finished.\n\n* fix(tui): harden view commands against stale targets and filter churn\n\nSlash input in the search editor no longer filters the list, which\ncould swap the selected row before Enter ran the command on it. The\narmed composer re-resolves its captured summary before dispatch so\n/kill, /name, and /fork act on the current runtime, and rejects view\ncommands under the local adapter instead of sending them as prompt\ntext. A session resumed only to serve a fork is stopped again when the\nfork fails or is cancelled.\n\n* docs(tui): move the dedicated-connection rationale to its helper\n\n* fix(tui): drop submitted view commands from the persisted query\n\nsubmitValue clears the editor without queryChanged, so a successful\nsearch-editor command stayed in persistentState.query and a remount\nrestored it where Enter could re-run it on an arbitrary row. Failed\ncommands restore the draft through setSearchQuery so the persisted\nquery stays in sync.\n\n* fix(tui): only freeze the search filter for recognized command input\n\nUnknown slash-prefixed terms like /foo stayed unfiltered because any\nleading slash suppressed the query. The filter now freezes only while\nthe input is a view command or a prefix that can still extend into one,\nso ordinary slash search terms keep filtering.\n\n* fix(tui): warn on view commands in the adapter search editor\n\nAdapter sessions fell through to openSelected() when a view command was\ntyped, opening an unrelated row. The search branch now rejects them\nwith the same unavailable-command warning the reply composer shows.\n\n* test: consolidate overlapping reply-composer tests\n\n* test: fold command-classification cases into one test\n\n* test: consolidate overlapping view-command tests\n\n* refactor(tui): drop the /fork view command\n\nThe in-place daemon fork semantics (runtime rebind at the current leaf,\nresume-then-rollback for saved rows) carried a third of the view-command\ncomplexity for a command whose behavior we already flagged as awkward\nuntil isolated forking lands. /new, /name, and /kill remain.\n\n* fix(tui): restore the draft when the adapter search rejects a command\n\nsubmitValue had already cleared the buffer, so the warning silently ate\nthe typed command; it now comes back through setSearchQuery like other\nfailed search-editor commands.\n\n* test: fold sendReply delivery and follow-up keybinding cases together\n\n* test: fold draft-restore rejection cases together\n\n* docs(tui): tighten create-session comments\n\n* docs(tui): tighten the fd-rebind comment\n\n* test: fold overlapping composer tests; tighten comments\n\n* fix(tui): ctrl+c cancels the armed composer as its hint advertises\n\napp.clear ran first and started the exit flow, so a second ctrl+c could\nexit the view and discard the draft.\n\n* fix(tui): refresh the saved catalog after a live /name rename\n\nOnly the live list was refreshed, so the stale saved entry resurfaced\nthe old name once the agent was killed. Mirrors confirmRename.\n\n* fix(tui): gate search autocomplete on command input; refresh both catalogs after /kill\n\nAbsolute-path queries like /tmp/ fell through CombinedAutocompleteProvider\nto filesystem completions; the search editor now uses the same\nisAgentsViewCommandInput predicate as the filter freeze. Catalog\nrefreshes after rename and kill go through a shared refreshBothCatalogs\nso a killed agent reliably reappears under Inactive.\n\n* refactor(tui): share one renameSession path between rename mode and /name\n\n/name reimplemented the rename separately: it reported success before\nthe refresh and missed the older-daemon restart hint. Both entry points\nnow use the same rename/refresh/report sequence.\n\n* fix(tui): tolerate an already-finished agent in /kill\n\ndeactivatePendingAgent treats \"Unknown active session\" as already\nstopped; /kill surfaced the same race as a raw error.\n\n* docs(tui): drop comments that restate adjacent code\n\n* refactor(tui): search-only search bar; retire /resume and the local session view\n\nThe agents-view search bar no longer parses commands: /name and /kill\nlive only in the armed reply composer (their target is captured\nexplicitly), and new-session stays on its keybinding. This deletes the\nsearch-command autocomplete, the filter-freeze machinery, and the\npersisted-query replay handling that command input required.\n\nSession browsing is daemon-only: /resume and bare --resume are removed\nalong with the process-local SessionViewAdapter and every adapter\nbranch in the view. --resume still resumes directly;\nnon-daemon `agents` warns and opens a chat. The chat hint now reads\n\"agents/resume\".\n\n* test: port #502 saved-catalog regressions off the removed adapter seam\n\nThe adapter layer was removed with /resume, so refreshSavedSessions now\nstreams list_saved_sessions through the daemon client and confirmRename\ndelegates to the shared renameSession path. The #502 regression harnesses\nstill faked options.adapter, so three tests failed (and two more passed\nonly because the missing client stub produced the expected false). Rebuild\nthem against client.request with onProgress streaming and the renameSession\ndelegate; behavior under test is unchanged.\n\n* chore: drop orphaned JSDoc for the removed bare --resume option","tree":"4ed05829ead2641fe83c832c098c3d1379ca93ef"}},{"name":"4649-subagent-model-selection.test.ts","mode":"0100644","size":17487,"lastCommit":{"hash":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","oid":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","parents":["78a0e05d595e3c70ab44be61ad0d92c71a6fd5a6"],"author":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"committer":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"message":"complete guarded RLM results and background completion wakeups\n","tree":"27f93d672adc2bdf84f6b7810e6d33f18f04ba38"}},{"name":"4653-queued-steer-after-agent-end.test.ts","mode":"0100644","size":2823,"lastCommit":{"hash":"941576dbec6d388de6b9f3cb61bce90cce3f55c4","oid":"941576dbec6d388de6b9f3cb61bce90cce3f55c4","parents":["9808aa7fa5dbe9bc855e2f84ca936c9a69c8332c"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-03T09:56:37+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-03T09:56:37+02:00"},"message":"refactor(coding-agent): publish session action protocol (#575)\n\n* refactor(coding-agent): publish session action protocol\n\n* fix(coding-agent): restore queue projection guards and recovery validation\n\n* fix(coding-agent): repair test migrations for session action snapshots\n\n* correcting when multiple messages are sent, how it's counted\n\n* fix(coding-agent): await update supervisor teardown (fixes #575)\n\n---------\n\nCo-authored-by: Alex Zhang ","tree":"81546c387f4627eb678183955565f1596d53e0ce"}},{"name":"4656-resume-active-session.test.ts","mode":"0100644","size":11072,"lastCommit":{"hash":"941576dbec6d388de6b9f3cb61bce90cce3f55c4","oid":"941576dbec6d388de6b9f3cb61bce90cce3f55c4","parents":["9808aa7fa5dbe9bc855e2f84ca936c9a69c8332c"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-03T09:56:37+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-03T09:56:37+02:00"},"message":"refactor(coding-agent): publish session action protocol (#575)\n\n* refactor(coding-agent): publish session action protocol\n\n* fix(coding-agent): restore queue projection guards and recovery validation\n\n* fix(coding-agent): repair test migrations for session action snapshots\n\n* correcting when multiple messages are sent, how it's counted\n\n* fix(coding-agent): await update supervisor teardown (fixes #575)\n\n---------\n\nCo-authored-by: Alex Zhang ","tree":"81546c387f4627eb678183955565f1596d53e0ce"}},{"name":"4657-update-heartbeat-recovery.test.ts","mode":"0100644","size":3774,"lastCommit":{"hash":"b030f3938463c2a9f5767c93e861a2d5d57b5d92","oid":"b030f3938463c2a9f5767c93e861a2d5d57b5d92","parents":["d93b3cbe0bca3e9fcbe85a78b3c3be89f96cedde"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-05T04:46:52+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-05T04:46:52+02:00"},"message":"feat(coding-agent): intra-tree child session passivation (#589)\n\n* feat(coding-agent): intra-tree child session passivation\n\nTrack A PR 7 (final) of the recursive-agent-harness plan (D5, shape 2):\n\n- idle child sessions inside a LIVE worker passivate individually: graceful\n closeSession (kernel snapshot + JSONL flush + lease release), sessions-map\n removal, registry/catalog rows preserved - the child becomes exactly a\n lazy-hydration passive row (attach/message/observe/list all work)\n- pure canPassivateSession() beside canEvictWorker(), sharing its per-\n session clauses; additionally requires a parent edge, no non-passive\n descendants, and no mid-hydration descendant (passive children's\n sessionFiles checked against openingSessions - hydration blocks parent\n passivation); roots remain shape-1 territory; passivation never cascades\n- complete-then-rehydrate: touches mid-passivation join the passivation\n promise (keyed by resolved sessionFile - stable across sessions-map\n removal) then flow through the normal hydration machinery; deterministic\n gated race tests for a2a delivery and grandchild hydration\n- supervisor sweep extension: capped worker command (2 children/worker/\n sweep), one snapshot per state per sweep, fresh-snapshot fence recheck\n before dispose; whole-tree-evictable workers excluded (owned by shape 1)\n- same idleEvictionMinutes setting governs both shapes; #548 doctrine\n inversion deferred (prompts out of scope this run)\n\n* fix(coding-agent): harden passivation against new admission fences and reap dedupe\n\nPost-rebase semantic fixes after moving the stack onto the hardened\nscheduler base (cb8f53e15):\n\n- passivation predicate treats admission-in-flight as busy: agent-message\n accepting/preparing/target-lock states and AgentSession's pending\n admission-fence waiters (70aeb9c49/2d97dbb4f made prompt paths await the\n direct-turn admission fence before any session action exists, so a target\n mid-admission looked idle to the sweep); deterministic gated-admission\n regression test\n- deleteRlmSubagentRuntime cancels scheduled jobs by session file even when\n its close joins an in-flight passivation close via closingSessions (the\n joined 'shutdown' close skipped 'killed'-close job cleanup; #547 reap race)\n\n* fix(coding-agent): harden passive-child hydration, resolution, and deletion races\n\n- Finding 0: heartbeat restore could return a concurrently hydrating child before binding; fence resident fallback with waitForBoundSession and treat unavailable binding as a skipped dispatch. origin: PR #583\n- Finding 1: supervisor child lookup accepted only exact selectors after worker suffix matching; add the same session-ID suffix fallback within the selected worker. origin: PR #583\n- Finding 3: passive create hydration skipped explicit name and client environment bookkeeping; apply both before returning the hydrated state. origin: PR #583\n- Finding 4: concurrent passive deletions raced through asynchronous resolution and started duplicate host deletes; defer deletion behind an atomic in-flight map check and coalesce callers. origin: PR #583\n- Finding 5: concurrent hydration could make a passive lookup stale for advertised IDs and paths; retry normal bound-session resolution before rethrowing the original unknown-session error. origin: PR #583\n- Finding 6: ambiguous live selectors fell through to passive lookup and could misroute; introduce a dedicated ambiguity error and rethrow it before passive resolution. origin: PR #583\n- Finding 7: passive open skipped name and client-env bookkeeping (cron rebinding already occurred in addRuntime); apply only the missing bookkeeping. origin: PR #583\n- Finding 30: rlmChildId traffic treated a resident passivating child as closing; join passivation and rehydrate in both bound lookup and direct message hydration branches. origin: PR #589\n\n* fix(coding-agent): restore attach/catch-up ordering invariants and sweep snapshot atomicity\n\n- Finding 22: async snapshot creation exposed clients before attach initialization; publish client attachment only after the snapshot resolves. origin: PR #587\n- Finding 23: catch-up validity was checked only before async snapshot creation; revalidate session and client attachment after the await. origin: PR #587\n- Finding 25: deterministic ambiguous selectors entered the 30-second remote-send retry loop; fail fast for Ambiguous errors. origin: PR #588\n- Finding 28: active rows ignored stable file-keyed schedule pins during active-id rebinding; consult both id- and file-keyed heartbeat/cron sets. origin: PR #588\n- Finding 29: passivation sampled activity before an asynchronous passive-registry walk; complete the walk before atomically sampling summary and admission markers. origin: PR #589\n\n* fix(coding-agent): correct rlmDepth semantics on reference edges, env parsing, and legacy fallbacks\n\n- Finding 8: new-session parent links were deriving spawn depth; copy the source header depth across the reference edge and add a runtime regression test (origin: PR #584).\n- Finding 9: first-entry forks of legacy sessions discarded effective runtime depth; fall back to session.rlmDepth in persisted and in-memory branches and test both (origin: PR #584).\n- Finding 10: root RLM_DEPTH parsing accepted malformed and unsafe values; require decimal digits and a valid safe non-negative integer, with probe cases as tests (origin: PR #584).\n- Finding 11: child-depth derivation could overflow MAX_SAFE_INTEGER; guard the increment and test the boundary (origin: PR #584).\n- Finding 12: daemon children of in-memory parents skipped explicit depth persistence; always create the child header with explicit depth and test --no-session ancestry (origin: PR #584).\n- Finding 13: legacy completed subagents rehydrated at root depth; restore the depth-one fallback and test a registry/header pair without depth (origin: PR #584).\n\n* fix(coding-agent): make /rlm-max-depth persistence honest and unblock stale kernel gate\n\n- /rlm-max-depth --global could claim persistence after deferred settings write failures; drain and surface global errors before reporting success (origin: PR #585)\n- /rlm-max-depth mutated live state before chat persistence and left failed entries indexed; persist first through rollback-safe custom-entry append, then mutate state and prompt (origin: PR #585)\n- invalid persisted global rlmMaxDepth could abort branch navigation after the leaf moved; ignore invalid global reads and fall through to env/default (origin: PR #585)\n- the kernel-side recursion pre-filter used stale one-shot RLM_MAX_DEPTH and blocked raises before the authoritative host gate; remove the duplicated Python gate (origin: PR #585)\n\n* fix(coding-agent): agents-view scope stability, crash-path backSession, summary refresh, pulse, and settings cycling\n\n- Finding 18: stale saved-catalog readiness could destructively drop scope during refresh; reset readiness when refresh starts. origin: PR #586\n- Finding 19: resolved scope roots were lost across view remounts, swallowing early Left navigation; persist and restore the root summary. origin: PR #586\n- Finding 20: post-attach crashes left backSession pointing at the prior session; assign the opened summary before interactive mode runs. origin: PR #586\n- Findings 21 and 24: startup seeding could leave subagent counts stale and background subagents drove an unused render pulse; refresh every seed and pulse only while streaming. origin: PR #587\n- Finding 27: custom idle-eviction values cycled directly to off; include custom numeric values in the sorted cycle. origin: PR #588\n\n* fix(coding-agent): attach reservation vs passivation, binding join on retry, hydration env, settings error scoping, fractional eviction values\n\n- reserve in-flight attaches and revalidate session liveness before attachment (origin: round-1 fix a342ca23d)\n- join concurrent child binding on the final passive resolution retry (origin: round-1 fix ae3ed4571)\n- adopt create-command client env before passive child hydration (origin: round-1 fix ae3ed4571)\n- isolate max-depth write errors while preserving project diagnostics (origin: round-1 fix 9e738f38f)\n- preserve fractional idle eviction values through settings cycling (origin: round-1 fix 721f45b59; stack commit aa98c9aca)\n\n* fix(coding-agent): post-rebase hardening of passive hydration, snapshots, and depth ingestion\n\n- preserve daemon routable IDs for passive children (origin: PR #583)\n- recheck guarded passive hydration and heartbeat restores (origin: PR #583)\n- repair wrong-kind pending hydration joins (origin: PR #583)\n- fence passive hydration during update restart preparation (origin: PR #583)\n- validate persisted RLM depth before constructor ingestion (origin: PR #584)\n- retry attach child snapshots across session replacement (origin: PR #587)\n- retain effective depth for legacy parented new sessions (origin: PR #589)\n- coordinate parent passivation with child hydration publication (origin: PR #589)\n\n* fix(coding-agent): leave shared passive hydration resident on guard cancellation\n\nThe ownership-blind close closed shared hydrations out from under concurrent wakes (both interleavings); the idle sweep is the ownership-free arbiter.\n\norigin: round-4 fix b95640046 / PR #583\n\n* fix(coding-agent): prefer persisted header depth for legacy rehydration entries\n\nThe legacy-entry rehydration fallback (entry.rlmDepth ?? 1) is passed as\nconfig, which outranks the opened transcript header in AgentSession — so a\nnested legacy child whose header carried a deeper persisted depth woke at\ndepth 1, weakening the host recursion gate. Registry depth stays\nauthoritative when present; otherwise the validated header depth wins and 1\nremains the last-resort default for fully legacy children.\n\norigin: PR #584 fallback restored in round-1 triage; surfaced by post-rebase\nbot review of PR #589.\n\n* fix(coding-agent): fence chain hydration against parent passivation; invalidate stale scope roots\n\n* fix(coding-agent): bound the session snapshot stabilization loop\n\n* fix(coding-agent): restore child event forwarder when passivation close fails\n\nPassivation teardown invoked the retained child's event-forwarder\nunsubscribe before closing the session. When the close failed and the\nchild was re-adopted, the forwarder was gone, so a still-resident child\nstopped emitting rlm_child_update to its parent. Teardown now returns\nthe unsubscribe so the passivation path only invokes it after a\nsuccessful close and restores it on the failed-close re-adopt path.\n\n* fix(coding-agent): close child passivation races\n\n- Keep snapshot messages aligned with the final runtime session summary after stabilization exhaustion.\n- Retry passive child hydration when the child starts passivating inside the hydration window.\n- Apply archive and scheduled-job cancellation when kill joins a resume-preserving close.\n\n* fix(coding-agent): upgrade cascading close reasons\n\n- Track the applied close reason and resident descendant states through cascading teardown.\n- Apply stronger joined close effects uniformly to parents and captured descendants.\n- Cover shutdown-to-killed descendant cleanup and completed-to-killed idempotency.\n\n* fix(coding-agent): preserve passive child id on hydration retry\n\n- Forward the restored active-session ID when retrying after a mismatched pending open.\n- Cover the pending-open race through passive-child hydration.\n\n* fix(coding-agent): recover passivation waiters\n\n- Treat failed passivation settlement as a join signal before retrying resident sessions.\n- Cover concurrent open, message delivery, and hydration after passivation rejection.\n\n* fix(coding-agent): harden passivation close races\n\n- Preserve stronger close-reason upgrades when the joined close fails.\n- Run child passivation outside the supervisor-wide eviction fence.\n- Complete reason-upgrade persistence across targets and record the stronger reason before propagating errors.\n\n* fix(coding-agent): preserve passive opener state across races\n\n- Defer root parent client env adoption until passive hydration and its open guard succeed.\n- Join opening or resident passive targets when parent-change restart resolution races hydration.","tree":"4726a5cfd80482f3088cea12d58430cc74872c6b"}},{"name":"4658-onboarding-transitions.test.ts","mode":"0100644","size":6439,"lastCommit":{"hash":"d02d98da8a3054f2c2bb3e1c07dda9c88de62eca","oid":"d02d98da8a3054f2c2bb3e1c07dda9c88de62eca","parents":["990025d3535f156e4a3c8066a90eebd9e2e82e76"],"author":{"name":"kt","email":"kevin.jt2007@gmail.com","when":"2026-07-16T14:46:13-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-16T14:46:13-07:00"},"message":"fix onboarding login and model selector flow (#445)\n\n* fix: stabilize onboarding flow\n\nFixes ENG-4658\n\n* fix: preserve onboarding focus\n\nFixes ENG-4658","tree":"89ac0458f0d762d596377dae8f4ac6ee5f37cf43"}},{"name":"4677-snapshot-catchup-replacement.test.ts","mode":"0100644","size":28597,"lastCommit":{"hash":"2857e23469d0348be6bba7b31f8a2c2e29d6a77b","oid":"2857e23469d0348be6bba7b31f8a2c2e29d6a77b","parents":["71ca6cfd1a2f7205ca0ec1baa65d10d0ed88f6e8"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-11T10:02:52+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-11T10:02:52+02:00"},"message":"fix(coding-agent): report accurate worker lifecycle and hide stopping workers (#850)\n\n* fix(coding-agent): report accurate worker lifecycle and hide stopping workers\n\nA worker with a durable stop intent is now reported as \"stopping\" and a\ndisconnected worker is never reported as \"ready\". Stopping workers are\nexcluded from live session lists and daemon-wide fan-out commands.\n\n* fix(coding-agent): keep stopping workers listed for busy-daemon safety checks\n\nThe list response feeds shutdownStaleDaemonIfNotBusy and\nprobeRunningDaemonSessions, so hiding stopping workers made a\ntombstoned-but-running worker look idle and let a stale-daemon replace\nterminate it silently. Stopping workers stay listed with an honest\n\"stopping\" workerState; command fan-outs still skip them.\n\n* chore(coding-agent): bump daemon schema revision for honest worker states\n\nRevision 14 records the workerState wire-semantics change (\"stopping\"\nstate; disconnected workers no longer report \"ready\") so version probes\ncan tell old and new daemons apart. The field stays optional and\nbackward-tolerant, so no capability gate is needed.\n\n* fix(coding-agent): reject unavailable worker routing\n\n* test(coding-agent): align snapshot fixtures with worker lifecycle\n\n---------\n\nCo-authored-by: Alex Zhang ","tree":"fb131f9eb2487fcae915d425f6739797e39c5c61"}},{"name":"4685-daemon-client-modes.test.ts","mode":"0100644","size":19239,"lastCommit":{"hash":"ceb418049dd929676beb13f77a6d697bcd52f854","oid":"ceb418049dd929676beb13f77a6d697bcd52f854","parents":["809027134a1fb2064fe152507abffcfc5610e486"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-28T17:09:00+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-28T17:09:00+02:00"},"message":"refactor(coding-agent): centralize agent-message admission in AgentSession (#1861)\n\n* refactor(coding-agent): query agent peers on demand instead of broadcasting mirrors\n\n* refactor(coding-agent): centralize agent-message admission in AgentSession\n\n* fix(coding-agent): respond to unknown worker commands instead of dropping them\n\nLegacy worker_sync_agent_peers commands from an older supervisor fell\nthrough handleWorkerCommand without a response, forcing the requester\nto wait out its full 5s timeout on every peer sync. A default case now\nwrites an immediate failure for any unhandled worker command.\n\n* fix(daemon): re-check cron job runnability after prompt admission fence\n\nrunCronJob snapshotted the runnable job before promptHeartbeat/\npromptUntilAccepted, which can wait on the session admission fence. A job\ncancelled or completed during that wait was still delivered. Re-check via\nthe admissionCommitted hook and skip when the job is no longer runnable.\n\n* fix(daemon): skip cron delivery when the job content changed during admission\n\nupdateRlmHeartbeat mutates prompt/deliveryMode in place under the same job\nid, so the existence-only admissionCommitted re-check still delivered the\nstale snapshot captured before the admission fence wait. Compare the\nrefreshed job's prompt and deliveryMode and skip on mismatch; the skip\nreschedules nextRunAt so the updated instruction is delivered next cycle.\n\n* fix(coding-agent): re-check prompt admission after async input normalization\n\n_prompt ran admissionCommitted before _normalizeSubmission, but async\nextension input handlers are awaited between that check and\n_admitSessionInput, so a cron job cancelled or updated during the await\nstill delivered its stale prompt. Re-run the callback after the awaited\nnormalization so invalidated content is not admitted.","tree":"01c8e55a80bbbc750ae8d927b1ee91fcc5b4aad0"}},{"name":"4722-invalid-resume-selector.test.ts","mode":"0100644","size":3849,"lastCommit":{"hash":"2f218e15130904568a805ac8d1920927747d7791","oid":"2f218e15130904568a805ac8d1920927747d7791","parents":["3fc0ac54fad747871c0d2797bce5b21530aecffc"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-07-30T17:38:20+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-07-30T17:38:20+02:00"},"message":"feat: unified agents and resume view (#541)\n\n* feat(coding-agent): unify searchable session view\n\n* fix(tui): keep session durations stable\n\n* test(daemon): tolerate partial session manager fixtures\n\n* test(tui): narrow session view race coverage\n\n* fix(tui): stabilize unified session catalogs\n\n* fix(tui): preserve session view lifecycle\n\n* fix(tui): preserve compact session view layout\n\n* test(tui): align cumulative session fixtures\n\n* fix(tui): preserve unified session identity and drafts\n\n* feat(tui): color recognized slash commands\n\n* fix(tui): keep view cancels and subagent matches local\n\n* test(tui): avoid platform-specific markdown styling\n\n* fix(tui): align session view status, reselect, and local resume flows\n\n* test(tui): consolidate slash command rendering coverage\n\n* test(tui): cover session view exit shutdown from chat\n\n* fix(tui): preserve dynamic command presentation\n\n* test(coding-agent): deadline-wait the create dedup race\n\n* test(coding-agent): align stacked fixtures\n\n* fix(tui): show seconds for sub-minute heartbeat countdowns\n\n* test(coding-agent): align cumulative session behavior\n\n* fix(coding-agent): flush child traces regardless of retention\n\n* fix(tui): single-own replacement catalog refresh\n\n* fix(tui): preserve drafts and completed child traces\n\n* fix(coding-agent): align template argument whitespace\n\n* fix(tui): restore saved sessions after reconnect\n\n* test(coding-agent): consolidate command presentation coverage\n\n* feat(tui): resume saved sessions from the reply composer\n\n* fix(tui): require heartbeat reconnect probe\n\n* test(coding-agent): align cumulative admission errors\n\n* fix(tui): schedule resumed replies from the resume summary\n\n* test(tui): align lifecycle stash handoff result\n\n* test(coding-agent): preserve unique lifecycle coverage\n\n* fix(tui): preserve inactive reply state on failures\n\n* fix(tui): route local agents view startup\n\n* refactor(tui): single-owner command catalog refresh\n\n* fix(tui): preserve selection after saved resume\n\n* test(tui): align startup lifecycle handoff\n\n* test(tui): resolve cumulative submit fixture\n\n* fix(tui): preserve in-flight reply drafts\n\n* test(tui): align owned startup exit shape\n\n* test(daemon): align delivery waiter contract\n\n* fix(tui): refresh resumed reply failures\n\n* fix(tui): preserve search selection\n\n* style(test): format cumulative prompt coverage\n\n* fix(agents-view): refresh reply target before send\n\n* fix(tui): complete onboarding before sessions\n\n* fix(tui): fence resync rendering by generation\n\n* refactor(coding-agent): consolidate prompt-admission cancellation\n\nExtract one shared waitForPromptAdmission helper and typed\nPromptAdmissionCancelledError into core/prompt-admission.ts, replacing\nthree near-identical copies in agent-session, daemon-mode, and\ndaemon-supervisor along with their copy-paste tests and the supervisor's\nstringly cancelled-status cast.\n\nAlso:\n- make _steeringStopPending a derived getter instead of a cached field\n manually re-synced at 15 call sites\n- surface genuine handoff errors in _isDeferredSessionInputError instead\n of silently requeueing them when the session is coincidentally busy\n- remove the production-dead pauseQueuedWork shim and narrow\n resumeQueuedWork to pump-suspension recovery only\n\n* test(coding-agent): deterministic waits and shared test helpers\n\n- replace the 50ms sleep proving no queued turn starts after\n abortForUpdateRestart with waitForSessionInputIdle\n- replace the 300ms sleep proving no prompt retry after an uncertain\n admission failure with a bounded microtask drain\n- use the shared createDeferred from suite/scheduling.ts instead of two\n local reimplementations\n- guard Reflect-based private access in the agents-view and supervisor\n harnesses so renamed members fail with explicit messages, and document\n why the constructor-bypass supervisor harness exists\n\n* chore(coding-agent): trim redundant comments from recent refactors\n\n* fix(coding-agent): guard session-input error surfacing against listener throws\n\nA throwing extension error listener could escape _surfaceSessionInputError\ninside _isDeferredSessionInputError before the pump requeued undelivered\nprompts, dropping them. Surfacing is now best-effort.\n\n* chore(coding-agent): tighten fix comment\n\n* fix(tui): keep the selection anchor across fallback unblocking\n\nResolving a missing anchor no longer overwrites the persisted anchor\nidentities with the visible fallback row, and typing while the anchor is\npending no longer claims the fallback either, so a late poll that\ndelivers the intended session re-anchors selection instead of opening\nthe wrong session.\n\n* fix(tui): open the unified session view on back navigation in local chats\n\nThe left-arrow back gesture only worked for daemon-backed sessions;\nprocess-local chats could reach the same unified view only via /resume.\nBack navigation now routes through requestAgentsView, which opens the\nlocal session view in place for process-local sessions.\n\n* fix(tui): preserve reply statuses across post-reply catalog refreshes\n\nThe refreshes triggered after a reply send or a failed resumed send used\ndefault error handling, so a failing catalog refresh could overwrite the\nsticky cwd-fallback notice or the send-failure message. Both refreshes\nnow preserve the current status on error.\n\n* chore(tui): drop redundant back-navigation comment\n\n* chore(tui): tighten reply-status comments\n\n* feat(tui): new session shortcut and steer/queue reply delivery\n\nctrl+n (app.agents.new) creates a fresh daemon session from the agents\nview and opens it. In the reply composer, Enter now steers a streaming\nagent and alt+enter (app.message.followUp) queues the reply as a\nfollow-up. While the composer is armed the hint line switches to\ncomposer hints: steer/send/resume & send, queue once text is typed, and\nesc to cancel.\n\n* feat(tui): session-owned slash commands in the reply composer\n\n/compact, /refine, /goal, and /autonomous pass through the daemon\nprompt path from the agents-view reply composer, with slash\nautocomplete active only while a reply target is armed. Other built-in\ncommands are rejected with guidance instead of being sent to the model\nas plain text.\n\n* feat(tui): view commands in the agents view\n\n/new, /fork, /name, and /kill run from the search editor against the\nselected row and from the armed reply composer against its target,\nwith autocomplete in both contexts. /fork forks at the current leaf via\nthe existing daemon fork RPC, resuming saved rows first; /name renames\nactive or saved sessions; /kill stops a running agent. Unknown or\nsession-only commands are rejected with guidance and plain text remains\na search query. The search hints now advertise \"/ commands\".\n\n* fix(tui): harden new-session shortcut and follow-up delivery\n\nctrl+n no longer fires while the reply composer is armed, so an unsent\ndraft cannot be discarded by opening a new session. Alt+Enter now\nexpands paste markers like Enter does. A session created after the view\nalready finished is killed instead of orphaned in the agents list.\n\n* fix(tui): preserve rejected drafts and bind completions to the target cwd\n\nA rejected command no longer loses the typed text (submitValue clears\nthe buffer before onSubmit; the rejection path now restores it unless\nnewer input arrived). The composer autocomplete provider is rebuilt\nwhen a target is armed, so @-file completions resolve in the target\nsession's cwd instead of the view's startup directory.\n\n* fix(tui): harden view commands against races, stale composers, and cancels\n\nAdapter-mode search no longer suggests view commands it will not run.\nArmed view commands cannot double-run (the buffer is already clear\nduring the RPC) and a failed command restores the typed draft in both\nthe composer and the search editor, without clobbering newer input.\nComposer disarm after /kill and /fork is guarded against a composer\nre-armed mid-command, and a fork cancelled by an extension is reported\nas cancelled instead of success.\n\n* fix(tui): report new-session outcome to callers\n\ncreateNewSession returns whether a session was created and opened, so\ncommand callers can restore a cleared draft on failure.\n\n* fix(tui): refresh after failed resumed forks and propagate /new outcome\n\nA saved row resumed for a fork that then fails, cancels, or has nothing\nto fork now refreshes the catalog so the newly live session appears\nimmediately. /new propagates createNewSession's outcome so a failed\ncreate restores the cleared draft.\n\n* fix(tui): enable @-path completion in the reply composer\n\nThe composer provider was built without an fd path, so @ fuzzy file\nsearch always returned empty. The view now resolves fd once and rebinds\nan armed provider when it becomes available.\n\n* fix(tui): create sessions over a dedicated connection\n\nfinish() closes the shared client, which rejected an in-flight create\nand made its session unkillable; a missing client also threw before the\nguard reset, permanently disabling the shortcut. Session creation now\nruns on its own short-lived connection inside the guarded try, so the\norphan-kill path works even after the view finished.\n\n* fix(tui): harden view commands against stale targets and filter churn\n\nSlash input in the search editor no longer filters the list, which\ncould swap the selected row before Enter ran the command on it. The\narmed composer re-resolves its captured summary before dispatch so\n/kill, /name, and /fork act on the current runtime, and rejects view\ncommands under the local adapter instead of sending them as prompt\ntext. A session resumed only to serve a fork is stopped again when the\nfork fails or is cancelled.\n\n* docs(tui): move the dedicated-connection rationale to its helper\n\n* fix(tui): drop submitted view commands from the persisted query\n\nsubmitValue clears the editor without queryChanged, so a successful\nsearch-editor command stayed in persistentState.query and a remount\nrestored it where Enter could re-run it on an arbitrary row. Failed\ncommands restore the draft through setSearchQuery so the persisted\nquery stays in sync.\n\n* fix(tui): only freeze the search filter for recognized command input\n\nUnknown slash-prefixed terms like /foo stayed unfiltered because any\nleading slash suppressed the query. The filter now freezes only while\nthe input is a view command or a prefix that can still extend into one,\nso ordinary slash search terms keep filtering.\n\n* fix(tui): warn on view commands in the adapter search editor\n\nAdapter sessions fell through to openSelected() when a view command was\ntyped, opening an unrelated row. The search branch now rejects them\nwith the same unavailable-command warning the reply composer shows.\n\n* test: consolidate overlapping reply-composer tests\n\n* test: fold command-classification cases into one test\n\n* test: consolidate overlapping view-command tests\n\n* refactor(tui): drop the /fork view command\n\nThe in-place daemon fork semantics (runtime rebind at the current leaf,\nresume-then-rollback for saved rows) carried a third of the view-command\ncomplexity for a command whose behavior we already flagged as awkward\nuntil isolated forking lands. /new, /name, and /kill remain.\n\n* fix(tui): restore the draft when the adapter search rejects a command\n\nsubmitValue had already cleared the buffer, so the warning silently ate\nthe typed command; it now comes back through setSearchQuery like other\nfailed search-editor commands.\n\n* test: fold sendReply delivery and follow-up keybinding cases together\n\n* test: fold draft-restore rejection cases together\n\n* docs(tui): tighten create-session comments\n\n* docs(tui): tighten the fd-rebind comment\n\n* test: fold overlapping composer tests; tighten comments\n\n* fix(tui): ctrl+c cancels the armed composer as its hint advertises\n\napp.clear ran first and started the exit flow, so a second ctrl+c could\nexit the view and discard the draft.\n\n* fix(tui): refresh the saved catalog after a live /name rename\n\nOnly the live list was refreshed, so the stale saved entry resurfaced\nthe old name once the agent was killed. Mirrors confirmRename.\n\n* fix(tui): gate search autocomplete on command input; refresh both catalogs after /kill\n\nAbsolute-path queries like /tmp/ fell through CombinedAutocompleteProvider\nto filesystem completions; the search editor now uses the same\nisAgentsViewCommandInput predicate as the filter freeze. Catalog\nrefreshes after rename and kill go through a shared refreshBothCatalogs\nso a killed agent reliably reappears under Inactive.\n\n* refactor(tui): share one renameSession path between rename mode and /name\n\n/name reimplemented the rename separately: it reported success before\nthe refresh and missed the older-daemon restart hint. Both entry points\nnow use the same rename/refresh/report sequence.\n\n* fix(tui): tolerate an already-finished agent in /kill\n\ndeactivatePendingAgent treats \"Unknown active session\" as already\nstopped; /kill surfaced the same race as a raw error.\n\n* docs(tui): drop comments that restate adjacent code\n\n* refactor(tui): search-only search bar; retire /resume and the local session view\n\nThe agents-view search bar no longer parses commands: /name and /kill\nlive only in the armed reply composer (their target is captured\nexplicitly), and new-session stays on its keybinding. This deletes the\nsearch-command autocomplete, the filter-freeze machinery, and the\npersisted-query replay handling that command input required.\n\nSession browsing is daemon-only: /resume and bare --resume are removed\nalong with the process-local SessionViewAdapter and every adapter\nbranch in the view. --resume still resumes directly;\nnon-daemon `agents` warns and opens a chat. The chat hint now reads\n\"agents/resume\".\n\n* test: port #502 saved-catalog regressions off the removed adapter seam\n\nThe adapter layer was removed with /resume, so refreshSavedSessions now\nstreams list_saved_sessions through the daemon client and confirmRename\ndelegates to the shared renameSession path. The #502 regression harnesses\nstill faked options.adapter, so three tests failed (and two more passed\nonly because the missing client stub produced the expected false). Rebuild\nthem against client.request with onProgress streaming and the renameSession\ndelegate; behavior under test is unchanged.\n\n* chore: drop orphaned JSDoc for the removed bare --resume option","tree":"4ed05829ead2641fe83c832c098c3d1379ca93ef"}},{"name":"4741-hint-placement.test.ts","mode":"0100644","size":5487,"lastCommit":{"hash":"bab124212fd5451beb071a884b5771ac7c1a8e1a","oid":"bab124212fd5451beb071a884b5771ac7c1a8e1a","parents":["ee8fd699617e8b66cb4bf36c97872c8fe52192e3"],"author":{"name":"Sebastian Müller","email":"sebastian@primeintellect.ai","when":"2026-08-29T10:52:17+02:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-29T10:52:17+02:00"},"message":"fix(coding-agent): single-source the interactive queue state (#1842)\n\n* fix(coding-agent): single-source the interactive queue state\n\n* fix(coding-agent): close queue-state races around rebind, moves, and failed edits\n\n- rebindCurrentSession: re-sync sessionActions after resubscribing; a\n session_action_update fired in the unsubscribed gap was lost forever.\n- browseQueueSelection: block browsing while a queue move RPC is pending,\n matching the pendingQueueEdit guard, so the move response cannot reselect\n the original item under newly browsed editor text.\n- moveQueueSelection: when the applied move's session_action_update has not\n landed yet (sessionActions reference unchanged), mirror the swap locally so\n the moved selection is not dropped against the pre-move snapshot; reconcile\n the selection in the error path.\n- applyQueueSelection: reconcile the selection after the pending-edit flag\n clears, so a rejected/failed edit no longer leaves Enter targeting a row\n that was removed while events were suppressed.","tree":"52746c80198390bf73b8c68244b982f42389ace9"}},{"name":"502-unified-session-view.test.ts","mode":"0100644","size":19507,"lastCommit":{"hash":"35f37ed063c02e2542cf396d78216e9b0dcee409","oid":"35f37ed063c02e2542cf396d78216e9b0dcee409","parents":["a9a8655037b009036c1fbcc4bb66aed65afcb532"],"author":{"name":"Seth Karten","email":"32787133+sethkarten@users.noreply.github.com","when":"2026-08-17T14:54:50-04:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-17T11:54:50-07:00"},"message":"feat(coding-agent): show subagent model and effort in agents view (#1479)\n\n* Show subagent reasoning effort in agents view\n\n* Fix scoped subagent effort labels\n\n* Fix agents view effort regression coverage\n\n* Hide disabled subagent effort labels\n\n* Prioritize subagent model in agents view\n\n* Preserve legacy subagent effort labels","tree":"45571013df905ddb813a7f7aacf6bcb7e98001f6"}},{"name":"617-subagent-terminal-agent-message.test.ts","mode":"0100644","size":3948,"lastCommit":{"hash":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","oid":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","parents":["78a0e05d595e3c70ab44be61ad0d92c71a6fd5a6"],"author":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"committer":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"message":"complete guarded RLM results and background completion wakeups\n","tree":"27f93d672adc2bdf84f6b7810e6d33f18f04ba38"}},{"name":"622-global-options-before-command.test.ts","mode":"0100644","size":1482,"lastCommit":{"hash":"954decda6c389926f40d86a52c69c214d9670bf5","oid":"954decda6c389926f40d86a52c69c214d9670bf5","parents":["cf9043e519450da6289bc59df4a4b62a6b080e7e"],"author":{"name":"Seth Karten","email":"32787133+sethkarten@users.noreply.github.com","when":"2026-08-05T00:15:13-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-05T00:15:13-07:00"},"message":"fix(coding-agent): dispatch socket-prefixed commands (#627)\n\n* fix(coding-agent): dispatch socket-prefixed commands (fixes #622)\n\n* fix(coding-agent): limit leading socket flag (fixes #622)\n\n---------\n\nCo-authored-by: Prime Intellect ","tree":"349a06622069fc65400cd38941a3a4f5f55daf7c"}},{"name":"623-acp-canonical-cwd.test.ts","mode":"0100644","size":4870,"lastCommit":{"hash":"2afb8855311924825a7921216902a65cce039b8e","oid":"2afb8855311924825a7921216902a65cce039b8e","parents":["cea90f81d90053f2943a69569d487075bed82b2a"],"author":{"name":"Seth Karten","email":"32787133+sethkarten@users.noreply.github.com","when":"2026-08-05T07:28:42-07:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-05T07:28:42-07:00"},"message":"fix(coding-agent): canonicalize ACP cwd comparison (#628)\n\n* fix(coding-agent): canonicalize ACP cwd comparison (fixes #623)\n\n* fix(coding-agent): preserve Windows cwd component case (fixes #623)\n\n* fix(coding-agent): compare ACP cwd filesystem identity (fixes #623)\n\n* test(coding-agent): assert cwd identity precondition (fixes #623)\n\n* fix(coding-agent): distrust a cwd identity when either dev or ino is zero\n\nThe guard required both halves to be zero, so a stat reporting dev 0 with a real\nino passed the device check and the comparison collapsed to inode only. Windows\npath-based stat does exactly that, and Windows file IDs are volume-local, so two\ndirectories on different drives could compare equal and suppress a real cwd\nmismatch. Treats either half being zero as untrustworthy instead.\n\n---------\n\nCo-authored-by: Prime Intellect ","tree":"ced1bc89a6e97c75662e26b71742ba0094e0ddb2"}},{"name":"702-codex-client-version.test.ts","mode":"0100644","size":2893,"lastCommit":{"hash":"324298a27e902ddb39b6fd1610f079c800ee81e6","oid":"324298a27e902ddb39b6fd1610f079c800ee81e6","parents":["7787f07415d843b9a800f6a4720e0c739bd608e5"],"author":{"name":"bilelrais","email":"contact@bilelrais.com","when":"2026-08-13T22:37:19+01:00"},"committer":{"name":"GitHub","email":"noreply@github.com","when":"2026-08-13T14:37:19-07:00"},"message":"fix(coding-agent): report a supported Codex client version for model discovery (#1375)\n\nUse the current Codex CLI compatibility version for authenticated model discovery so Codex-only users can discover and spawn native rlm subagents.\n\nFixes #702","tree":"7842b1e02966f7c7ba1a163a195c2bd108bead37"}}],"lastCommit":{"hash":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","oid":"7e70aea03dcf78c97aa65cc2a8e1aeb2a068e5fe","parents":["78a0e05d595e3c70ab44be61ad0d92c71a6fd5a6"],"author":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"committer":{"name":"dawn","email":"90008@klbr.net","when":"2026-08-31T22:05:28+09:00"},"message":"complete guarded RLM results and background completion wakeups\n","tree":"27f93d672adc2bdf84f6b7810e6d33f18f04ba38"}}