litcodex-ai 0.3.13 → 0.3.15

package/README.md

@@ -64,8 +64,8 @@ LitCodex also ships a sibling family of triggers and phrases — `litwork`, `lit
 `lit start work` handoff — alongside a 24-skill library and hook components, all registered as a
 single Codex plugin.
 
-The bundled `public-page-reader` skill adds a public-only retrieval workflow with safety preflight,
-content validation, trace evidence, and deterministic A/B checks for blocked or misleading pages.
+The bundled `public-page-reader` skill adds a public-only Node stdlib runtime with safety preflight,
+unsafe redirect blocking, content validation, trace evidence, and deterministic A/B checks.
 
 > [!TIP]
 > See the [repository README](https://github.com/wjgoarxiv/litcodex#readme) for the full quickstart,

package/node_modules/@litcodex/lit-loop/agents/litcodex-litwork-reviewer.toml

@@ -16,6 +16,7 @@ If the latest parent message starts with `TASK STILL ACTIVE:`, immediately retur
 Verdict rules:
 - Return `UNCONDITIONAL APPROVAL` only when the diff satisfies every success criterion and the evidence proves the real surface works.
 - Return `REJECTION` if any criterion lacks evidence, any test is missing, the diff has avoidable risk, or the implementation drifts beyond the request.
+- Return `REJECTION` for minimum-first drift: custom code where existing code, the standard library, a native platform/framework feature, an installed dependency, or one clear line would satisfy the goal; unnecessary helpers, layers, config, tests, docs, or speculative generality; or any external-source term/phrase introduced into product files.
 - Treat "looks good but..." as rejection. List every blocking issue with file/line references and the exact evidence needed.
 
 Be concise, specific, and strict."""

package/node_modules/@litcodex/lit-loop/agents/litcodex-plan.toml

@@ -20,7 +20,7 @@ When the caller says "do X / fix X / build X" - interpret it as "create a work p
 - AVOID me when: the change is a single-file edit with an obvious pattern, or the caller already has a plan and just wants execution.
 
 # Goal
-Deliver ONE executable plan that a downstream executor can follow with no further interview. Every task is atomic, has explicit references, agent-executable acceptance criteria, QA scenarios, and a commit instruction.
+Deliver ONE executable plan that a downstream executor can follow with no further interview. Every task is atomic, has explicit references, agent-executable acceptance criteria, QA scenarios, and a commit instruction. Apply minimum-first planning: if the outcome can be a single-task or few-task plan, do that instead of manufacturing waves; before adding work, check whether to skip, reuse existing code, use standard library/native/platform features, or reuse an installed dependency.
 
 # Phase 1 - Context gathering (MANDATORY BEFORE PLANNING)
 Never plan blind. Fire parallel research BEFORE drafting:
@@ -35,7 +35,7 @@ Wait for context to converge before drafting. Rushed plans fail.
 
 # Phase 2 - Plan output (single markdown file, single plan)
 
-Write the plan to `.litcodex/plans/<slug>.md` in the working tree (create the `.litcodex/plans/` directory if absent). One plan per request - no "Phase 1 plan / Phase 2 plan" splits. 50+ tasks is fine if the work demands it.
+Write the plan to `.litcodex/plans/<slug>.md` in the working tree (create the `.litcodex/plans/` directory if absent). One plan per request - no "Phase 1 plan / Phase 2 plan" splits. A single-task or few-task plan is correct for small work; 50+ tasks is fine only when the verified scope truly demands it.
 
 Use this template verbatim (fill the placeholders):
 
@@ -54,6 +54,7 @@ Use this template verbatim (fill the placeholders):
 
 ### Must NOT have (guardrails, anti-slop, scope boundaries)
 - ...
+- Minimum-first guard: do not add work that can be skipped, solved by reusing existing code, handled by the standard library/native platform, covered by an installed dependency, or expressed as one clear line.
 
 ## Verification strategy
 > Zero human intervention - all verification is agent-executed.
@@ -63,8 +64,8 @@ Use this template verbatim (fill the placeholders):
 
 ## Execution strategy
 ### Parallel execution waves
-> Target 5-8 tasks per wave. <3 per wave (except final) = under-splitting.
-> Extract shared dependencies as Wave-1 tasks to maximize parallelism.
+> For large independent work, target 5-8 tasks per wave. For small work, prefer a single-task or few-task plan; do not split merely to fill a wave.
+> Extract shared dependencies as Wave-1 tasks only when they are real blockers, not speculative abstractions.
 
 Wave 1 (no dependencies):
 - Task 1: <desc>

package/node_modules/@litcodex/lit-loop/directives/lit-plan.md

@@ -166,7 +166,7 @@ automatic interview-to-plan transition.
 2. If native Codex Plan Mode is active, return ONE complete
    `<proposed_plan>...</proposed_plan>` using the template below and do not write
    a file. Otherwise write ONE plan to `.litcodex/plans/<slug>.md`. No
-	"Phase 1 plan / Phase 2 plan" splits; 50+ todos is fine. Build it
+	"Phase 1 plan / Phase 2 plan" splits; a single-task or few-task plan is correct for small work, and 50+ todos is fine only when verified scope demands it. Build it
 	incrementally — skeleton first, then append todo batches — so output limits
 	never truncate it; re-read the file with the `shell` tool to confirm
 	completeness.
@@ -187,6 +187,7 @@ automatic interview-to-plan transition.
 ## Scope
 ### Must have
 ### Must NOT have (guardrails, anti-slop, scope boundaries)
+- minimum-first guard: do not plan work that can be skipped, solved by reusing existing code, handled by the standard library/native platform, covered by an installed dependency, or expressed as one clear line.
 
 ## Verification strategy
 > Zero human intervention — all verification is agent-executed.
@@ -196,7 +197,7 @@ automatic interview-to-plan transition.
 
 ## Execution strategy
 ### Parallel execution waves
-> Target 5-8 todos per wave. < 3 per wave (except the final) = under-splitting.
+> For large independent work, target 5-8 todos per wave. For small work, prefer a single-task or few-task plan; do not split merely to fill a wave.
 Wave 1 (no deps): ...
 Wave 2 (after 1): ...
 Critical path: ...

package/node_modules/@litcodex/lit-loop/directives/litresearch.md

@@ -9,7 +9,7 @@ separately asks for implementation after the synthesis.
 
 # Durable journal
 
-Create a session directory under `.litcodex/litresearch/<timestamp>/` and keep an append-only journal
+Create a session directory under `.litcodex/lit-loop/litresearch/<timestamp>/` and keep an append-only journal
 there. Store worker digests, source notes, verification outputs, and the final synthesis in that
 directory. Workers may return findings, but the orchestrator owns the journal.
 

package/node_modules/@litcodex/lit-loop/directives/review-work.md

@@ -14,6 +14,10 @@ evidence or completion is blocked.
 2. **real-surface QA** — drive the actual hook, CLI, package, HTTP, browser, or desktop surface the
    user would touch. Capture command output, transcript, screenshot, response body, or log.
 3. **code quality** — inspect changed files for maintainability, coupling, test quality, and minimality.
+   Apply the minimum-first gate: reject avoidable custom code when existing code, the standard library,
+   a native platform/framework feature, an installed dependency, or one clear line would satisfy the
+   goal; also reject unnecessary helpers, layers, config, tests, docs, speculative generality, or any
+   external-source term/phrase introduced into product files.
 4. **security/safety** — check malformed input, prompt injection, secret handling, permissions,
    destructive actions, and unsafe publication/deploy paths.
 5. **context/docs/package** — verify docs, changelog, handoff, config/installer behavior, package

package/node_modules/@litcodex/lit-loop/dist/trigger.js

@@ -71,14 +71,14 @@ export function matchLitTrigger(prompt) {
             continue;
         }
         const index = (m.index ?? 0) + m[0].length - raw.length;
-        if (isSlashCommandOrPathToken(prompt, index)) {
+        const token = raw.toLowerCase();
+        if (isSlashCommandOrPathToken(prompt, index, token)) {
             continue;
         }
         const phrase = raw.toLowerCase() === "lit" ? naturalPhraseAfterLit(prompt, searchable, index, raw.length) : null;
         if (phrase !== null) {
             return phrase;
         }
-        const token = raw.toLowerCase();
         return { token, raw: prompt.slice(index, index + raw.length), index };
     }
     return null;
@@ -105,9 +105,12 @@ function naturalPhraseAfterLit(prompt, searchable, index, rawLength) {
     const rawLengthWithPhrase = rawLength + m[1].length + m[2].length;
     return { token, raw: prompt.slice(index, index + rawLengthWithPhrase), index };
 }
-function isSlashCommandOrPathToken(prompt, tokenIndex) {
+function isSlashCommandOrPathToken(prompt, tokenIndex, token) {
     const prev = prompt[tokenIndex - 1];
-    return prev === "/";
+    if (prev !== "/") {
+        return false;
+    }
+    return !(token === "litresearch" && tokenIndex === 1);
 }
 function maskRange(chars, start, end) {
     for (let i = start; i < end; i += 1) {

package/node_modules/@litcodex/lit-loop/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@litcodex/lit-loop",
-	"version": "0.3.13",
+	"version": "0.3.15",
 	"description": "LitCodex Lit-Loop runtime: durable repo-native multi-goal orchestration with embedded success criteria and observable evidence audit.",
 	"type": "module",
 	"bin": {
@@ -19,7 +19,7 @@
 	"scripts": {
 		"build": "tsc -p tsconfig.build.json",
 		"typecheck": "tsc --noEmit",
-		"test": "vitest --run"
+		"test": "vitest --config vitest.config.ts --run"
 	},
 	"engines": {
 		"node": ">=20.0.0"

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "litcodex-ai",
-	"version": "0.3.13",
+	"version": "0.3.15",
 	"description": "Codex loop harness installer. Run `npx litcodex-ai install` to set up the LitCodex Codex platform: the bare `lit` hook and the durable lit-loop runtime.",
 	"keywords": ["codex", "litcodex", "lit-loop", "ai-agents", "orchestration"],
 	"author": "LitCodex Authors",
@@ -15,7 +15,7 @@
 	},
 	"files": ["bin", "dist", "model-catalog.json", "README.md", "LICENSE"],
 	"dependencies": {
-		"@litcodex/lit-loop": "0.3.13"
+		"@litcodex/lit-loop": "0.3.15"
 	},
 	"bundledDependencies": ["@litcodex/lit-loop"],
 	"scripts": {