Issues

rust mode: /ctx-wrapup after a host restart says "Retry in a moment (MC-C09)", but retrying never works until the session takes a model turn

#529

· iceteaSA opened

on Sep 24, 2026

rust mode: a session that ran under TS after an earlier rust run is served raw on every later rust pass (retained boundary never reappears, so pending_rewrite never clears)

#527

· iceteaSA opened

on Sep 24, 2026

OMP: accept role aliases (@role) in historian/dreamer model config, including fallback_models

#526

· Qiiks opened

on Sep 24, 2026

[Pi] typebox should be peerDependencies — as a runtime dependency the plugin both installs and bundles a second copy next to Pi's pinned 1.3.27

#525

· trim21 opened

on Sep 24, 2026

rust mode: historian reattach after a module restart waits the producer's 600 s default instead of the configured historian_timeout_ms (residual of #507)

#522

· iceteaSA opened

on Sep 24, 2026

rust mode: long-lived module state has no retention bound (session maps never evicted, mc_changefeed never pruned)

#521

· iceteaSA opened

on Sep 24, 2026

rust mode: module-served classify-memories records 0 tokens and no model in subagent_invocations (module omits usage, host drops the model it does get)

#520

· iceteaSA opened

on Sep 24, 2026

ctx_reduce availability ignores OpenCode agent/session permissions, so a session that can't call ctx_reduce still gets §N§ prefixes and ctx_reduce nudges

#519

· iceteaSA opened

on Sep 24, 2026

rust mode: the module's on-disk model-chain fallback reads keys the plugin schema doesn't declare, so it is empty on every schema-valid config (and dreamer tasks read historian keys)

#505

· iceteaSA opened

on Sep 22, 2026

rust mode: module manifest omits `broca` from `consumes`, leaving the historian producer's route an undeclared cross-module edge

#502

· iceteaSA opened

on Sep 22, 2026

Conflicting worktree schedules can continually postpone Dreamer tasks

design-approved

#498

· DivyamTalwar opened

on Sep 21, 2026

History compression could not finish this turn. It will retry automatically. (MC-H01)

#495

· Tahmid-kabir-addin opened

on Sep 21, 2026

Navigation Menu

All issues

rust mode: /ctx-wrapup after a host restart says "Retry in a moment (MC-C09)", but retrying never works until the session takes a model turn

rust mode: a session that ran under TS after an earlier rust run is served raw on every later rust pass (retained boundary never reappears, so pending_rewrite never clears)

OMP: accept role aliases (@role) in historian/dreamer model config, including fallback_models

[Pi] typebox should be peerDependencies — as a runtime dependency the plugin both installs and bundles a second copy next to Pi's pinned 1.3.27

rust mode: historian reattach after a module restart waits the producer's 600 s default instead of the configured historian_timeout_ms (residual of #507)

rust mode: long-lived module state has no retention bound (session maps never evicted, mc_changefeed never pruned)

rust mode: module-served classify-memories records 0 tokens and no model in subagent_invocations (module omits usage, host drops the model it does get)

ctx_reduce availability ignores OpenCode agent/session permissions, so a session that can't call ctx_reduce still gets §N§ prefixes and ctx_reduce nudges

rust mode: the module's on-disk model-chain fallback reads keys the plugin schema doesn't declare, so it is empty on every schema-valid config (and dreamer tasks read historian keys)

rust mode: module manifest omits `broca` from `consumes`, leaving the historian producer's route an undeclared cross-module edge

Conflicting worktree schedules can continually postpone Dreamer tasks

History compression could not finish this turn. It will retry automatically. (MC-H01)

Search results