@hraness/wordcell 0.25.1 → 0.26.1

package/README.md

@@ -9,14 +9,26 @@ sources as Markdown files beside your code, and agents find them by exact
 words, by meaning with an optional local model, or from the file they are
 about to change.
 
-A new coding-agent session can read your code, but not the decisions that
-stayed in the last session's chat. Wordcell keeps those decisions as Markdown
-files beside the repository, with the plans that depend on them and the web
-pages and PDFs that informed them. Tie a note to the paths it explains, and an
-agent about to change that code runs one command to get the notes and plans
-for that path. Exact search, backlinks, and Git history run on your machine
-with no account or model, and every index rebuilds from files you can read in
-any editor. Wordcell is free and open source.
+A new coding-agent session needs the reasons behind the code it is changing.
+Wordcell keeps the decision, its supporting sources, and the plan that puts it
+into practice in a connected set of Markdown files. Tie a note to a repository
+path, and the next agent can recover that context before it edits the file.
+When an assumption changes, update the decision and keep its earlier reasoning
+in Git.
+
+Captured sources preserve what you read, maintained notes explain what you
+currently understand, and plans record the work and its results. Named
+relationships such as `evidenced-by` and `supersedes` make those connections
+available to the embedded Oh graph engine, whose results point back to the
+supporting files. Optional local semantic search helps when the words in a
+question differ from the note; Git history connects the explanation to its
+commits and accompanying code changes.
+
+Use the CLI, local MCP server, or TypeScript SDK from your existing agent and
+editor. The public Agent Skill teaches agents to recover context, maintain
+plans, and leave reusable decisions for later sessions. Exact search, backlinks,
+and Git history need no account or model. Every index rebuilds from files you
+can read in Obsidian or any text editor. Wordcell is free and open source.
 
 Web capture, optional hosted reranking, and your agent's provider reach other
 services; [Privacy and boundaries](#privacy-and-boundaries) says what each one
@@ -54,14 +66,14 @@ Wordcell keeps the record in Markdown files you own, rebuilds every index from t
 The CLI and TypeScript SDK run with Bun. Install the versioned GitHub archive:
 
 ```sh
-bun add --global --ignore-scripts https://github.com/hraness/wordcell/releases/download/v0.25.1/hraness-wordcell-0.25.1.tgz
+bun add --global --ignore-scripts https://github.com/hraness/wordcell/releases/download/v0.26.1/hraness-wordcell-0.26.1.tgz
 wordcell --help
 ```
 
 Prefer npm? The same release is [mirrored there](https://www.npmjs.com/package/@hraness/wordcell):
 
 ```sh
-npm install --global --ignore-scripts @hraness/wordcell@0.25.1
+npm install --global --ignore-scripts @hraness/wordcell@0.26.1
 wordcell --help
 ```
 
@@ -70,10 +82,32 @@ add your package manager's global executable directory to `PATH` and reopen the
 terminal. Optional semantic search, browser capture, and PDF tools have
 [additional prerequisites](https://github.com/hraness/wordcell/blob/main/docs/reference.md#review-lifecycle-scripts-before-enabling-optional-adapters).
 
+Global Bun and npm installations on macOS and Linux check for updates daily
+before a command starts. Updates require the GitHub CLI (`gh`) to verify the
+release and preserve `--ignore-scripts`. An active command, MCP server, or
+preview server prevents replacement until it exits. Both installed commands
+share the same settings:
+
+```sh
+wordcell update status
+wordcell update check
+wordcell update
+wordcell update disable
+wordcell update enable
+```
+
+Use `HRANESS_NO_UPDATE=1 wordcell …` for an invocation without automatic update
+requests, including offline work. Help, version output, and SDK imports never
+check for updates. Source, project, copied, and Windows installations use manual
+upgrades. Exact Bun registry versions stay pinned until `update enable`; npm
+does not reliably retain the original global version constraint, so use
+`update disable` when you need a fixed global version. A versioned GitHub archive
+tracks verified releases by default. See the [update reference](docs/reference.md#cli-updates).
+
 ## Keep one decision available to the next session
 
 Run this from a directory where you want a new `kb/` folder. It creates one
-Markdown note and finds it without downloading a model or contacting a service:
+Markdown note and finds it without a search model or hosted search service:
 
 ```sh
 wordcell init kb
@@ -103,7 +137,7 @@ After trying the CLI, install the public Agent Skill into a compatible agent,
 such as Claude Code, Codex, Cursor, or GitHub Copilot:
 
 ```sh
-bunx skills add hraness/wordcell#v0.25.1 --skill wordcell
+bunx skills add hraness/wordcell#v0.26.1 --skill wordcell
 ```
 
 Then ask:
@@ -175,7 +209,7 @@ provider failure retains the baseline order with a diagnostic. See the
 
 | Task | Command | Evidence and effects |
 | --- | --- | --- |
-| Find a saved decision | `wordcell search "parser retries" --root kb --mode exact` | Reads current Markdown; no model or network request. |
+| Find a saved decision | `wordcell search "parser retries" --root kb --mode exact` | Reads current Markdown; no model or hosted search request. |
 | Recover context for code | `wordcell context packages/parser/src/index.ts --root kb --repo .` | Returns scoped notes, plans, and inherited `AGENTS.md` rules. |
 | Inspect explicit connections | `wordcell backlinks notes/parser-contract --root kb` | Returns notes that link to the decision. |
 | Search by meaning | `wordcell search "retry policy" --root kb --mode hybrid` | Adds optional local QMD keyword and vector retrieval; model setup is required. |
@@ -249,39 +283,19 @@ keeps one vault current on several machines.
 
 ## Evidence and comparisons
 
-On eight questions sealed before the passage selector was finished,
-`wordcell search --selected-passage` returned an excerpt holding the labeled
-answer for **6 of 8**, versus **1 of 8** for the older search snippets, at the
-same 512-byte limit and from the same retrieved notes. It runs locally with no
-model. The corpus is small and consists of Wordcell's own notes; containing the
-answer is not the same as an agent answering correctly.
-[Method, raw results, and reproduction](https://github.com/hraness/wordcell/blob/main/docs/evidence.md#measure-whether-excerpts-contain-the-answer).
-
-In a four-query example over a seven-note public vault, packed search snippets
-used **80% fewer UTF-8 bytes** than passing the same matching notes in full:
-12,126 versus 60,584 bytes. This measures context payload size, not tokenizer
-counts, answer quality, latency, or a win over another search tool.
-
-In a separate public SciFact study, optional hosted Jev reranking placed a
-judged relevant result first for **161 of 300 queries**, versus **101** with
-Wordcell exact search alone. It sends bounded context to a paid provider;
-this is evidence on scientific abstracts, not a comparison with QMD or a
-guarantee for repository notes. [Results and limits](https://github.com/hraness/wordcell/blob/main/docs/reranking.md#evidence-and-limits).
-
-Wordcell's benefit is selecting relevant context and keeping its sources
-inspectable. Local ownership is also available in other tools, and Wordcell
-does not claim to beat QMD's retrieval quality or every Markdown workflow.
-
-[Measured evidence](https://wordcell.io/docs/evidence)
-shows a reproducible public-vault example, with the inputs, output sizes, and
-limits beside each result. [The comparison guide](https://wordcell.io/docs/comparisons)
+On the public SciFact dataset of scientific abstracts, optional hosted Jev
+reranking placed a relevant result first for **161 of 300 queries**, versus
+**101** with Wordcell exact search alone. Hosted reranking is optional and uses
+a paid provider. [Results and method](https://github.com/hraness/wordcell/blob/main/docs/reranking.md#evidence-and-limits).
+
+[The comparison guide](https://wordcell.io/docs/comparisons)
 covers Markdown alone, QMD, Basic Memory, Obsidian, static publishing tools,
 Supermemory, Mem0, and Zep using their own documentation. Choose the smallest
 workflow that meets your needs.
 
-The [benchmarks page](https://wordcell.io/benchmarks) shows the excerpt, payload,
-and SciFact results beside the published results of Oh, the embedded memory
-framework, each with its source data and limits. On all 500 LongMemEval-S
+The [benchmarks page](https://wordcell.io/benchmarks) shows the SciFact results
+and the published results of Oh, the embedded memory framework, each with its
+source data and method. On all 500 LongMemEval-S
 questions, Oh semantic retrieval scored 88.87% and BM25 86.13% with the same
 reader and budget; on the measure Oh named before the run, its interval does
 not rule out a tie. Oh's scores measure its own memory-retrieval path, not a
@@ -334,7 +348,7 @@ exist. [Graph queries and proof limits](https://github.com/hraness/wordcell/blob
 Add the same immutable release to a Bun project:
 
 ```sh
-bun add --exact --ignore-scripts https://github.com/hraness/wordcell/releases/download/v0.25.1/hraness-wordcell-0.25.1.tgz
+bun add --exact --ignore-scripts https://github.com/hraness/wordcell/releases/download/v0.26.1/hraness-wordcell-0.26.1.tgz
 ```
 
 The SDK provides read-only vault sessions, metadata queries, search, graph

package/dist/capture.js

@@ -5,25 +5,25 @@ import {
   captureSummary,
   main,
   runCapture
-} from "./index-t3abkwk4.js";
-import"./index-hxyjer3x.js";
+} from "./index-zbv70qmk.js";
+import"./index-hacpnaew.js";
 import"./index-k86wepd8.js";
 import {
   adapterCapabilities,
   inspectClipEnvironment,
   renderDoctorReport
-} from "./index-nwrehke7.js";
+} from "./index-nd8v7r0z.js";
 import"./index-5n05se68.js";
-import"./index-xwxy71ew.js";
+import"./index-ncwzmsge.js";
 import"./index-cd75vky9.js";
 import"./index-2gv8y733.js";
+import"./index-mxxxytys.js";
 import"./index-w2zc0vwa.js";
 import"./index-e5fbsywq.js";
+import"./index-gh719d91.js";
 import {
   parseArguments
 } from "./index-byz4kzww.js";
-import"./index-gh719d91.js";
-import"./index-mxxxytys.js";
 import"./index-1xxnjn0d.js";
 import"./index-4knsp9qj.js";
 import"./index-z1w83f81.js";

package/dist/cli-bin.js

@@ -0,0 +1,14 @@
+#!/usr/bin/env bun
+// @bun
+import {
+  runWordcellBin
+} from "./index-6jz050v0.js";
+import"./index-3t0v457d.js";
+import"./index-8pabwzqg.js";
+import"./index-4knsp9qj.js";
+import"./index-z1w83f81.js";
+
+// src/cli-bin.ts
+import { fileURLToPath } from "url";
+if (import.meta.main)
+  process.exitCode = await runWordcellBin("wordcell", fileURLToPath(import.meta.url), process.argv.slice(2));