@christiandoxa/prodex 0.210.0 → 0.212.0

package/README.md

@@ -739,6 +739,16 @@ Use `prodex s expose` when you need to reach the live Super terminal from a brow
 
 Super's built-in optimization stack is deliberately local and deterministic. It preloads Caveman, exposes a Prodex overlay `rtk` PATH wrapper plus RTK auto-wrappers for common noisy commands when RTK is installed, auto-registers built-in `prodex-inspect` plus discovered `sqz-mcp` and `token-savior` MCP servers, exposes `sqz` and `claw-compactor` wrapper commands when those commands/checkouts are discoverable, invokes a trusted one-shot `prodex-claw-compactor-sessionstart` SessionStart benchmark probe when Claw-Compactor is available, falls back to a temporary shadow `MEMORY.md` when the workspace has no Markdown memory files, then uses Smart Context Autopilot through a dedicated runtime proxy for lower-token request shaping. The probe delegates to `prodex-claw-compactor-auto "$(pwd)"` and uses a marker under `CODEX_HOME` so Codex conversation restarts do not replay it. Presidio redaction and prodex-memory are added only when you opt in. Prodex routes optional-tool state under `PRODEX_HOME` (default `~/.prodex`), including SQZ XDG state, token-savior cache/stats, claw-compactor HOME/XDG state, RTK analytics paths, and local memory, so compatible optimizer metadata stays out of worktrees.
 
+Smart Context treats protocol and continuation metadata as exact control-plane data while allowing independent context payload segments to remain eligible for deterministic lossless or artifact-backed rewriting. Explicit exact mode still makes the complete request pass through. Missing artifact references are handled as segment-local rehydration failures: the dependent reference is preserved and recorded, budgets tighten, and unrelated payload segments may still be optimized when validation proves continuation identifiers, tool-call structure, critical signals, and JSON integrity are intact.
+
+Smart Context budgeting is model-relative: it calculates pressure from effective used tokens against the usable context window after output reserve, records pressure bands and estimator confidence, and tightens behavior when runtime token accounting is uncertain. Context window selection prefers explicit launch config, then a versioned provider/model registry, then observed runtime accounting and conservative fallback behavior.
+
+Smart Context rollout controls are local environment flags. `PRODEX_SMART_CONTEXT_CANARY_PERCENT=N` deterministically applies rewriting only for the selected percentage of requests, while canary-out requests pass through unchanged and log `rollout_canary_out`. `PRODEX_SMART_CONTEXT_SHADOW=1` computes Smart Context diagnostics and telemetry while returning the original request upstream. Explicit exact mode still bypasses rollout and remains full pass-through.
+
+Smart Context replay evaluation is modeled in the runtime proxy so saved JSON corpora can be scored deterministically against the rollout gate: median token reduction, long-session coverage, success regression, continuation/tool/critical-signal integrity, unresolved mandatory artifact references, JSON corruption, rewrite overhead, and full-request fallback rate.
+
+See [`docs/smart-context.md`](docs/smart-context.md) for the safety model, telemetry fields, rollout flags, migration note, and current replay benchmark report.
+
 Super instructs Codex to use the available local optimizer stack where it fits the task, not just RTK:
 
 - RTK works upstream/input-side. Use visible `rtk <cmd>` for noisy terminal commands before their output enters the model context, such as `git diff`, `cargo test`, `npm test`, build logs, and package-manager output. Prodex also auto-wraps common noisy commands as a fallback when RTK is installed, but that fallback does not make the TUI show an `rtk` prefix.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@christiandoxa/prodex",
-  "version": "0.210.0",
+  "version": "0.212.0",
   "description": "Multi-provider Codex wrapper with OpenAI quota-aware routing and Claude Code support",
   "license": "Apache-2.0",
   "bin": {
@@ -16,12 +16,12 @@
     "@openai/codex": "latest"
   },
   "optionalDependencies": {
-    "@christiandoxa/prodex-linux-x64": "0.210.0",
-    "@christiandoxa/prodex-linux-arm64": "0.210.0",
-    "@christiandoxa/prodex-darwin-x64": "0.210.0",
-    "@christiandoxa/prodex-darwin-arm64": "0.210.0",
-    "@christiandoxa/prodex-win32-x64": "0.210.0",
-    "@christiandoxa/prodex-win32-arm64": "0.210.0",
+    "@christiandoxa/prodex-linux-x64": "0.212.0",
+    "@christiandoxa/prodex-linux-arm64": "0.212.0",
+    "@christiandoxa/prodex-darwin-x64": "0.212.0",
+    "@christiandoxa/prodex-darwin-arm64": "0.212.0",
+    "@christiandoxa/prodex-win32-x64": "0.212.0",
+    "@christiandoxa/prodex-win32-arm64": "0.212.0",
     "@openai/codex-linux-x64": "npm:@openai/codex@linux-x64",
     "@openai/codex-linux-arm64": "npm:@openai/codex@linux-arm64",
     "@openai/codex-darwin-x64": "npm:@openai/codex@darwin-x64",