Skip to content

root / tags / abonnement-claude

#abonnement Claude

3 fiches

AI Coding Agents & Skills Auto-verified translation

ACP : deux protocoles, un sigle, zéro rapport

Tech-watch note by **Didier Girard** dated **August 2, 2026**, prompted by a colleague's question ("what is ACP?") that turns out to address a problem that is not terminological but **documentary**. **Three protocols compete for the acronym**, with no technical overlap whatsoever: **Agent Client Protocol** (client ↔ agent — Zed, August 2025, JSON-RPC 2.0 over stdio, Apache-2.0, "what LSP did for languages"), **Agentic Commerce Protocol** (agent ↔ merchant — OpenAI + Stripe, Sept. 29, 2025, facing Google's **UCP** of Jan. 11, 2026 backed by **AP2**), and **Agent Communication Protocol** (agent ↔ agent — IBM Research / BeeAI, marginal but polluting searches). **The core of the note is not the disentangling but its observed failure**: the author searches "ACP" in his tech-watch knowledge base and gets **twelve results, all about the commerce protocol, zero about Zed's** — *"our watch agents had indexed the acronym without disambiguating it"*. Hence a knowledge-engineering rule: ***"never index a bare acronym"*** — the entity is "Agent Client Protocol", "ACP" is **only an alias**, carried by three distinct entities. A structuring clarification follows (**MCP connects an agent to its tools, ACP connects a client to an agent; the two stack**), then the textbook case: **Buzz**, published by **Block** on July 21, 2026 under Apache-2.0 — a self-hostable workspace built on **Nostr**, where every human or agent participant is a **keypair** and every message, workflow step, or git push is a **signed event** in an append-only log. A fully protocol-based architecture (`buzz-acp` an ACP harness over stdio, `buzz-agent` an ACP agent calling an LLM, `buzz-dev-mcp` an MCP server for shell + editing), hence the agent-agnosticism: **Goose, Claude Code, and Codex** plug in through the same harness, and **Hermes** (Nous Research) connected to it without Block writing a single line — *"N+M instead of N×M, running in production"*. The note closes on the question of the **Claude subscription** versus third-party agents, with a five-stage 2026 timeline and a **design rule** that applies beyond this case: the line is not legal but **architectural** — ***"who is consuming, and on whose behalf"*** (an `owner-only` agent consumes your subscription for you; an `anyone` agent in a shared channel routes your colleagues' requests through your account). ⭐ **Verification carried out on this corpus**: the thesis holds, and more starkly than the note asserts — not only is "Agent Client Protocol" **completely absent** from it, but the bare acronym `ACP` **is already typed as an entity** in two fiches, and the KB page `Agentic-Commerce-Protocol` **already attributes the protocol to Google** when it belongs to OpenAI + Stripe. The collision described is not a risk yet to come: it has **already produced an attribution error** in the graph.

#ACP#Agent Client Protocol#Agentic Commerce Protocol

**Didier Girard** — auteur de la note. Écrit ici depuis la position de **praticien de la veille outillée** : le déclencheur est une question de collègue · le matériau principal est le comportement observé de sa propre base de connaissances · et la conclusion est une **règle de curation** adoptée en interne. Le texte alterne donc deux voix — l'explicateur de protocoles et l'ingénieur de la connaissance qui constate un défaut chez lui et en tire une norme.

AI Coding Agents & Skills Auto-verified translation

Anthropic pauses Claude Agent SDK subscription change on day it was due to take effect

Article by **Paul Sawers** published in **The New Stack** on **June 16, 2026**, on **Anthropic's suspension** — *« on the very day it was scheduled to go live »* — of the billing split that was to separate **Agent SDK** usage from Claude subscription limits. **Anthropic's message, quoted**: *« We're pausing the changes to Claude Agent SDK usage described below. For now, nothing has changed. »* **The article's contribution is not the announcement itself but the surrounding context**, in three circles. **Circle 1 — Anthropic's week**: on June 9, the release of **Fable 5 and Mythos 5**, the first generally available Mythos-class models with hardened cybersecurity safeguards; a few days later, a **US government export-control directive** forces Anthropic to **withdraw both models for all its customers worldwide**. The pricing suspension is read as *« a little good news »* in this context. **Circle 2 — the collateral damage of the timing**: companies that had already passed the change on to their own customers find themselves caught out; **Conductor**, a multi-agent coding tool built on the Agent SDK, has to publish a retraction (*« Anthropic has delayed the subscription updates to Claude plans »*). **Circle 3 — the underlying tension, which extends beyond Anthropic**: a quote from **Boris Cherny** (head of Claude Code) in April, during an earlier restriction, saying subscriptions *« weren't built for the usage patterns of these third-party tools »* — an acknowledgment that **flat-rate plans and open-ended agentic usage don't mix**; **GitHub** reached the same conclusion, removing Copilot's flat-rate *premium requests* model in June in favor of **token-based billing**, despite the backlash. Added to this, **the same week**, a **proposed class action** was filed in a federal court in California, alleging that **Max** tiers fall well short of the advertised usage multipliers during heavy coding sessions. Anthropic does not say when a revised approach will arrive, only that it *« works to update the plan to better support how users build with Claude subscriptions »*. **The author's final reading**: between government pressure over Fable and Mythos, a planned **IPO**, and **rumored price cuts at OpenAI**, Anthropic is seeking to **keep its developer base on side** — and the suspension is, for now, a way of doing that.

#Anthropic#Claude Agent SDK#Claude subscription

**Paul Sawers** — journaliste tech · signe ici pour **The New Stack**. Registre de **presse spécialisée** : l'article ne relaie pas seulement l'annonce · il la replace dans une série (les changements de facturation successifs d'Anthropic) · la compare à un précédent sectoriel (GitHub Copilot) et l'articule à trois pressions concomitantes (export control, IPO, concurrence). Sourçage explicite et attribué — le billet de Zed · l'analyse de Matthew Diakonov · le post de Conductor · une déclaration antérieure de Boris Cherny.

AI Coding Agents & Skills Auto-verified translation

What Anthropic's New Claude Billing Means for Zed Users

Blog post on **Zed**'s blog signed by **Franciska Dethlefsen** (head of growth and marketing), published on **May 14, 2026** — the day after Anthropic's announcement — to answer questions from Zed users. **Subject**: starting **June 15**, Anthropic **splits Claude subscription billing into two pools** — one for its **first-party tools** (chat, official Claude Code CLI), the other for **third-party agent and SDK usage** (anything going through **ACP**, `claude -p`, or a third-party tool). Usage via ACP **then stops drawing from Pro or Max limits** and switches to a monthly **"Agent SDK" credit**: **$20 for Pro, $100 for Max 5x, $200 for Max 20x**. Once the credit is exhausted, usage continues **at standard API pricing** if overage is enabled — otherwise requests stop until the next cycle. **The figure driving the article**: subscriptions had until then subsidized agentic usage by a factor of **≈ 15 to 30×** relative to API pricing, and the new credits are billed **at full API pricing** — hence *"for anyone using agents heavily, this is a major cost increase"*. **Three options proposed**, in an order that reveals Zed's position: (1) keep the subscription by launching the **official `claude` CLI in a terminal inside Zed** rather than via ACP — *"when the official claude CLI runs in the terminal, it uses your subscription's limits, not the new credit"*; (2) use Zed's built-in agent with the provider of one's choice (Zed-hosted models, API keys, Copilot, local Ollama, DeepSeek); (3) plug in **any ACP agent** — OpenCode, Codex, Factory, Cursor — several of which still offer rate-limited subscriptions that subsidize heavy usage. **The underlying thesis**, and the real reason for the post: *"ACP is an open protocol… so that your editor is never locked into one provider's pricing decisions"*, with the explicit anticipation that *"this kind of change won't be the last"*. ⚠️ **The post carries an addendum dated June 16, 2026** announcing that **the change is suspended**: ACP, `claude -p`, the Agent SDK, and third-party applications continue to work with subscriptions **as before**, no separate credit to claim, limits unchanged, Anthropic revising its plan with announced advance notice. **The artifact is therefore self-contradicted**: its most important content — the reversal — postdates its own publication date by a month.

#Zed#Anthropic#Claude subscription

**Franciska Dethlefsen** — head of growth and marketing chez **Zed Industries**. Le rôle est déterminant pour lire le texte : ce n'est pas un billet d'ingénierie mais une **communication de crise produit** · écrite le lendemain d'une annonce d'un fournisseur dont Zed dépend · à destination d'utilisateurs inquiets. La signature growth/marketing explique la structure (problème → options → réassurance) et le fait que l'argument protocolaire arrive en conclusion plutôt qu'en tête.