@cortexkit/magic-context 0.44.0 → 0.44.1

package/dist/index.js

@@ -21541,7 +21541,7 @@ var init_magic_context = __esm(() => {
     smart_notes: object({
       retina_handoff: boolean2().default(false).describe("When true, dreamer skips smart notes whose surface conditions compiled to retina provider configs at authoring time. Default false keeps both paths active until the retina consumer is deployed.")
     }).default({ retina_handoff: false }).describe("Smart-note ownership transition controls."),
-    cache_ttl: union([string2(), object({ default: string2() }).catchall(string2())]).default("5m").describe(`How long Magic Context assumes the provider's cached prefix stays valid. This is MC's own deferral gate — it does not change the provider's actual cache lifetime. String (e.g. "5m", "1h", "30s") or per-model object ({ default: "5m", "provider/model": "1h", "provider/*": "never" }); keys resolve most-specific first (exact provider/model, bare model ID, shorter dash-prefixes, then the provider/* wildcard, then default). Set to "never" to mean MC never assumes expiry (for lanes kept warm externally by a cache-keep tool) — disables the idle-TTL heuristic so MC never initiates a rebuild based on elapsed time. Provider-side extended TTL is a separate request-level concern (cache_control: { ttl } in the request body).`),
+    cache_ttl: union([string2(), object({ default: string2() }).catchall(string2())]).default("5m").describe(`How long Magic Context assumes the provider's cached prefix stays valid. This is MC's own deferral gate — it does not change the provider's actual cache lifetime. String (e.g. "5m", "1h", "30s") or per-model object ({ default: "5m", "provider/model": "1h", "provider/*": "never" }); keys resolve most-specific first (exact provider/model, bare model ID, shorter dash-prefixes, then the provider/* wildcard). Explicit per-model entries win; otherwise GPT-5.6 and later (including gpt-6*, through any provider prefix) use a built-in 30m lifetime before the object default or 5m fallback. An unset or global "5m" opts into built-in defaults; any other global string is an explicit policy and wins. Policy is frozen per session, including across restarts; a model switch resolves against that frozen policy. /ctx-status shows the effective value and source. OpenAI documents at least 30 minutes since the latest write or reuse: https://developers.openai.com/api/docs/guides/prompt-caching (Cache lifetime and Summary of model differences). Set to "never" to mean MC never assumes expiry (for lanes kept warm externally by a cache-keep tool) — disables the idle-TTL heuristic so MC never initiates a rebuild based on elapsed time. Provider-side extended TTL is a separate request-level concern (cache_control: { ttl } in the request body).`),
     prompt_surface: PromptSurfaceConfigSchema.default({ default: "full" }).describe("Prompt-surface presets: default is full; models use bare model IDs, provider/model, or provider/* routing keys. Guidance and tool-description overrides are user-level only. OpenCode 1.x, Pi, and OMP register tool descriptions once per process (they follow the default preset). OpenCode 2 rewrites the five ctx_* descriptions per request from the draft model."),
     output_reserve: union([
       number2().min(0),
@@ -21600,9 +21600,9 @@ var init_magic_context = __esm(() => {
       enabled: boolean2().default(true).describe("When false, Magic Context stops managing the context window and keeps its knowledge layer: memory and docs/user-profile/key-files injection through additive m[0]/m[1], raw-message FTS indexing, dreamer, notes, ctx_search, ctx_expand, ctx_memory, and /ctx-embed remain available. MC's historian/compartment preparation, tagging, markers, pruning, folding, drops, strips, splicing, synthetic context-management todos, temporal markers, nudges, and fail-closed blocking stop; ctx_expand remains a knowledge-surface tool. fail_closed_blocking is inert: a transform failure passes the input messages through without blocking or cancelling. This setting does not enable native compaction: OpenCode's compaction.auto / compaction.prune or Pi's equivalent owns the window, or nothing does. MC's compaction.enabled in magic-context.jsonc is distinct from OpenCode's compaction.auto / compaction.prune in opencode.jsonc; they are different files and different owners. On the first turn after disabling, a long session may trigger one native compaction cycle; MC removes only its own marker boundary, leaves native boundaries and stored compartments intact, and does no pre-trimming mitigation. Marker cleanup is lazy per session, so an unresumed session is cleaned when it is next resumed. If compaction is enabled again, run /ctx-wrapup when the historian is runnable to catch up. OpenCode peer verification against v1.18.4 confirms native compaction covers child sessions: subagents receive additive memory/docs injection and no MC reclaim in this mode, so keep subagent tasks small or leave compaction.enabled on for long subagent runs. This is boot-resolved and requires a process restart; project-tier compaction.enabled is stripped so a cloned repository cannot disable the user's setting. The sidebar reports raw usage as Context: <pct>% · native compaction or Context: <pct>% · no active compaction and does not show an MC execute-threshold fill. /ctx-wrapup, /ctx-recomp, and /ctx-flush refuse without context-management side effects; /ctx-embed remains functional. Raw content hidden by a native boundary before Magic Context's first pass is not retroactively indexed.")
     }).default({ enabled: true }).describe("Compaction-off mode gate. Default true (MC manages the context window as today). Set compaction.enabled=false to keep the knowledge layer while letting native compaction (or nothing) own the window. Boot-resolved; requires a restart to change."),
     todowrite: object({
-      enabled: boolean2().default(true).describe("Pi only: register Magic Context's todowrite task-list tool. Disable if you use your own todo extension. OpenCode ships its own built-in todowrite; this setting has no effect there."),
+      enabled: boolean2().default(false).describe("Pi only: off by default. Set todowrite.enabled=true to register Magic Context's todowrite task-list tool and /todos command. OpenCode ships its own built-in todowrite; this setting has no effect there."),
       overlay: boolean2().default(true).describe("Pi only: show the persistent todo overlay above the editor while tasks are active.")
-    }).default({ enabled: true, overlay: true }).describe("Pi-only todowrite tool and overlay controls. Pi registers tools and widgets at extension boot, so changing this after /cd requires /reload or restart."),
+    }).default({ enabled: false, overlay: true }).describe("Pi-only todowrite tool and overlay controls. Pi registers tools and widgets at extension boot, so changing this after /cd requires /reload or restart."),
     pi: PiConfigSchema.describe("Pi-only child-process extension controls. This setting is user-level only; project configuration cannot choose which extensions a user's subagent children load."),
     smart_drops: boolean2().default(false).describe("Content-aware reclaim of provably-superseded tool output, layered on the existing execute-pass auto-drop. When on: superseded todowrite (keep newest 1), spent ctx_reduce (keep newest 3), and zero-value meta (bash_status, bash_kill, ctx_note read/dismiss) outputs are dropped; older edits to a file are compressed to a filePath-preserving marker while the newest edit per file stays full. Only acts on passes already busting the cache, so it never originates a cache bust. Honors the protected-tag reserve. Experimental: opt-in, default off until cache stability is proven; when off the wire is byte-identical to the positional-only reclaim. Requires a restart."),
     caveman_text_compression: object({
@@ -21651,10 +21651,12 @@ var init_magic_context = __esm(() => {
     "historian.omp.fallback_models",
     "historian.omp.thinking_level",
     "historian.two_pass",
+    "historian.maxTokens",
     "historian_timeout_ms",
     "commit_cluster_trigger.enabled",
     "commit_cluster_trigger.min_clusters",
     "memory.auto_promote",
+    "dreamer.maxTokens",
     "dreamer.opencode.model",
     "dreamer.opencode.fallback_models",
     "dreamer.opencode.variant",

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@cortexkit/magic-context",
-    "version": "0.44.0",
+    "version": "0.44.1",
     "description": "Unified CLI for Magic Context — setup, doctor, and migration across OpenCode, Pi, and OMP",
     "keywords": [
         "opencode",