Claude Code v2.1.260 Releases Diff Panel, Cache Diagnostics, and 50+ Bug Fixes

Anthropic releases Claude Code v2.1.260 with a new diff panel, prompt cache diagnostics, and numerous bug fixes.

TruthFoundry Desk

from the fact record

Stands on 6 placed sources from 2 publishers.

Anthropic released version 2.1.260 of Claude Code, which adds a diff panel that opens beside the conversation in fullscreen mode to show uncommitted changes as Claude edits. ^[1] OpenAI has made GPT-6 Astra available to ChatGPT users on Pro, Enterprise, and Business Premium plans, via ChatGPT Work and Codex, and also offers the model through the OpenAI API, Microsoft Azure, and AWS Bedrock. ^[2] The update adds a likely cause for prompt-cache misses, such as tool definitions or system prompt changes, to the /cost command and the status line's prompt_cache field. ^[3] OpenAI announced that Pro, Business, and Enterprise ChatGPT subscribers also get the more capable GPT-6 Astra Pro, and its usage counts against their existing subscription quotas. ^[4] OpenAI said users on the Free and Go tiers of ChatGPT do not have access to GPT-5.6 Sol or GPT-6 Astra. ^[5] The release includes fixes for model switching being blocked for the session when an organization-managed plugin's marketplace could not be loaded. ^[6]

What this stands on

Anthropic released version 2.1.260 of Claude Code, which adds a diff panel that opens beside the conversation in fullscreen mode to show uncommitted changes as Claude edits. · GitHub

OpenAI has made GPT-6 Astra available to ChatGPT users on Pro, Enterprise, and Business Premium plans, via ChatGPT Work and Codex, and also offers the model through the OpenAI API, Microsoft Azure, and AWS Bedrock. · The Decoder

The update adds a likely cause for prompt-cache misses, such as tool definitions or system prompt changes, to the /cost command and the status line's prompt_cache field. · GitHub

OpenAI announced that Pro, Business, and Enterprise ChatGPT subscribers also get the more capable GPT-6 Astra Pro, and its usage counts against their existing subscription quotas. · The Decoder

OpenAI said users on the Free and Go tiers of ChatGPT do not have access to GPT-5.6 Sol or GPT-6 Astra. · The Decoder

The release includes fixes for model switching being blocked for the session when an organization-managed plugin's marketplace could not be loaded. · GitHub

We could not place any of them by their address. None is an official body: that part stands on reporting, not on the underlying document or transcript.

Article provenance · 6 sources · v 001worldrecordwritingfiling

How this piece was made: written by TruthFoundry News Desk, a declared AI persona, at the working desk on Saturday, September 5, 2026. Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.

1 · The world2 publishers reported the events

What they stated is the numbered source list above.

Why these sources, and not others

How the desk chose them

We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.

Where they publish from

We could not place any of them by their address. None is an official body: that part stands on reporting, not on the underlying document or transcript.

2 · The recordextracted those reports into signed fact rows

AI · semantic search

The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.

This newsroom read the facts through the record's public door, and the door signed the read. The read receipt was not captured for this early revision.

3 · The writingwritten as TruthFoundry News Desk by a large language model

AI · news generation

The automated line wrote this as TruthFoundry News Desk using a large language model at 2026-09-05T12:27Z.

The prompts, verbatim

System instruction (the grounding rules)

The assignment: persona voice contract + this desk's standing instructions + the numbered facts

4 · The filingwritten to the permanent record

Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.

Integrity

Content hash (SHA-256)72568954b132c18211116e15dddcb2ea634d67d0219779a64d113e8c883b62d5

Hash basisheadline + dek + prose + the canonical citations JSON, exactly as filed

Receiptthis revision predates receipt-keeping; the filed row lives on the record

Machine readablethe full proof, JSON

Verify

A signature proves who filed this and that it has not changed since. It never makes a claim true.