Streaming Parsers, Not JSON, Are What Break During an LLM API Migration

·8 views

A migration diary argues that the streaming layer, rather than the non-streaming JSON responses, is where API cutovers typically fail silently. Providers that claim OpenAI compatibility can still differ on where usage data appears, whether a [DONE] marker is sent, and how tool-call arguments are split across chunks. The author recommends recording raw server-sent event bytes as fixtures, covering at least four shapes including plain text, tool calls, stop sequences, and errors returned after a 200 status. A state-machine normalizer is proposed that keys tool-call fragments by index and ignores comments and unknown fields. The cutover should then be gated on structural equality of normalized events rather than a one-off manual check.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Essay Argues Writing Is Closer to Thought Than Code

A blog post by Daniel Miessler contends that writing is more closely related to the process of thinking than to the act of coding. The piece appeared on Hacker News, where it received 3 points and no comments at the time of capture. The source material provided is limited to the headline, URL, and engagement metrics, so the full argument is not summarized here. Readers would need to consult the original article for the author's specific reasoning and examples.

0 comments Read more at Hacker News

ProgrammingDEV Community ·

Study finds AI-assisted developers slower on some tasks, prompting a book on agentic software development

The author argues that a single measurement showing a productivity gain or loss should not be taken as a verdict on AI coding tools, since the full body of results forms a trend that slopes in a particular direction. The piece distinguishes between evidence grades, noting that weakly supported claims can motivate practices but cannot establish them, and that small studies generalize only to similar groups. It draws on the Lindy effect to argue that Parnas's 1972 information-hiding principles remain relevant because they limit the errors an AI agent can make. The author also notes that AGENTS.md, a configuration convention roughly eighteen months old, is promising but not yet proven to be lasting infrastructure. The post introduces a book on the Agentic Development Lifecycle and invites readers to consider how they would ship AI-generated code safely.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Apple Concedes iPhone Duo Crease Cannot Be Eliminated, Says Matte Coating Only Softens It

Three days after the iPhone Duo went on sale, debate over a visible crease on its foldable inner display has intensified. Apple's hardware engineering chief acknowledged on September 19, 2026, that the physical crease cannot be removed and said the company reduces its visibility with a nanotexture surface and matte coating. Commentators note the device's 15,999-yuan price implies a level of display perfection the crease contradicts, even though Apple's spec sheet never promises a crease-free screen. A reviewer's test of 11,500 folds showed a deeper crease, which critics cite, though the piece argues this is only about 5.75% of Apple's rated 200,000-cycle hinge life and does not show hinge failure. The article also argues that crease visibility lacks any shared testing standard, so no vendor can easily quantify it.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Building a Python Workflow That AI Agents Can Discover Using APFlow

A tutorial walks through building a small Python workflow that combines two regional request counts into one report using local sample data and SQLite. It explains how APFlow, an open-source orchestration engine, separates workflow structure from execution order, with independent regional tasks able to run concurrently. Python functions are registered as capabilities with schemas that can be exposed to agents through MCP, A2A, REST, and CLI adapters. The example runs without a model provider or API key and requires Python 3.11 or newer. The article also covers how dependency data flows between tasks, how capability contracts can be inspected, and how to move from a local example toward a production-style setup. APFlow is noted as still classified as Alpha, so the author recommends starting with verifiable outcomes before adding external integrations.

0 comments Read more at DEV Community