7 Commits

Author SHA1 Message Date
kami aee2e67c66 refactor(detekt): extract magic-number constants, wrap long lines, drop legit suppressions
Mechanical detekt cleanup across apps/core/infrastructure (behavior-preserving):
- MagicNumber 62->10: named constants + removed 'legit' MagicNumber suppressions
  (Tier level from ordinal, ReplayInferenceProvider CHARS_PER_TOKEN, ConfigLoader
  DEFAULT_* consts, capability scores, HTTP ranges, column widths, etc.)
- MaxLineLength cut to ~0 in production modules (line wraps, no logic change)
- Dropped one dead parameter (ConfigLoader.parseArray lineNum)

Structural findings (ReturnCount/LongMethod/Complexity/LargeClass) left for a
deliberate decomposition pass. Full build + detekt gate green.
2026-07-12 23:12:28 +04:00
kami da7fe61b77 perf(talkie): fold idea board once, keep live via subscribeAll (#55)
IdeaReader folded eventStore.allEvents() on every activeIdeas()/capturedOf()
call — a full deserializing log scan per CHAT context build. Now folds once at
construction and stays current incrementally via subscribeAll(); the fold is
idempotent so seed/live overlap needs no dedupe.
2026-07-12 13:12:35 +04:00
kami 15248cae8a feat(recovery,context): tier-2 intent-holder arbiter + remaining-delta pinning + surfaced signal events
- recovery: two-tier repair ladder — owner then arbiter (recovery stage recast
  as intent-holder, holds initial intent, reconciles cross-file contract disputes)
  with independent INTENT_ROUTE_BUDGET; RecoveryRoutingTest coverage
- context: remaining-delta checklist pinning (RemainingDelta{Pinning,Entry}Test)
- surface write-only events (session name, quality signals) into stats/browse
- parseToolArguments lenient-Json fallback for bare-key drift
- tools: ChildProcess seam
2026-07-11 23:56:52 +04:00
kami 24f3b843bb fix(talkie): label narration actions 'in this run', not 'this stage'
The actions line is session-wide, but the old 'Actions taken this stage' label
made a literal narrator (Qwen2.5-1.5B) contradict itself ('no files read this
stage'). Relabel to match reality.
2026-07-03 14:33:02 +04:00
kami bc5fedf99b fix(talkie): surface narration actions in the user turn, session-wide
Live run showed the actions were in the prompt but the 1.2B narrator ignored
them: they sat in a system-role entry (small models under-weight system context)
and were stage-scoped to the pausing stage, which usually isn't the one that ran
the tools. Fold the recent actions into the USER trigger instruction instead, and
take the last N tool calls across the whole run rather than per-stage. Narration
now names the concrete actions ("reviewing server directories and reading the
specified file") instead of generic filler.
2026-07-03 14:03:24 +04:00
kami 1c027e8189 feat(talkie): ground narration in the stage's actual tool actions
Narration was generic ("Stage X completed. Summarise.") because nothing about
what the stage actually did reached the narrator — the L2 summary is a
placeholder and StageCompletedEvent carries no output. narrate() now reads the
stage's ToolInvocationRequested events from the log and feeds the narrator a
concrete 'Actions taken this stage: file_read(path), ...' entry, and the system
prompt asks it to prefer those concrete actions over restating the stage name.
2026-07-03 13:40:00 +04:00
kami 595ec187bc refactor: rename the router subsystem to Talkie
The 'router' name was misleading — it's the always-on conversational front-end
(CHAT triage + STEERING into a running workflow), not a routing layer, and it's
distinct from InferenceRouter. Rename core:router -> core:talkie, package
com.correx.core.router -> com.correx.core.talkie, and RouterFacade/Config/State/
Repository/ContextBuilder/Projector/Reducer/Response -> Talkie*. Config section
[router] -> [talkie] (legacy [router] still read as fallback).

Persisted wire formats are preserved: ChatTurnRole.ROUTER and the
RouterNarrationEvent @SerialName("RouterNarration") stay, so existing event
logs still replay. RouterNarrationEvent the class is now TalkieNarrationEvent.
2026-07-03 13:26:00 +04:00