RepoSense RS Monogram
RepoSensereposen.se
/llm.txtGitHub Repo
stanfordnlp icon

stanfordnlp/dspy

v3.4.1

Curated ai tools / ai-framework / ai-evals / backend repository (stanfordnlp/dspy) tracked via conditional GitHub .atom polling.

BREAKING
What is stanfordnlp/dspy?

dspy-ai is an open-source library and developer tool in the stanfordnlp/dspy ecosystem. It saves developers from writing repetitive low-level boilerplate from scratch by providing a battle-tested, open-source implementation ready for production.

AI-FRAMEWORKnpm:dspy-aiPythonreleases.atom
#ai-framework#ai-evals#dspy
AI Executive Summary & Artifact Size Impact
Quick Summary: What Changed · What To Do · Upgrade Effort

skills: reference material for the reflection LM. Pass a. Review breaking API changes before up… Migration: Moderate.

Semver: PATCH·Manifest: package.json
Artifact Size Impactunavailable
Size Unavailable
Telemetry unmeasured for pre-release or source-only registry build
Breaking Changes, Release Highlights & Migration Snippet

Key Release Highlights (v3.4.1)

  • skills: reference material for the reflection LM. Pass a path, a directory containing SKILL.md, an inline string, or a list of these. YAML frontmatter is parsed at construct...
  • additional_instructions: extra guidance applied to every proposal.
  • base_instructions: replaces the reflection prompt but keeps its input and output fields.
  • max_chars: a hard character limit. A draft that is too long gets one compression attempt; DSPy never truncates an instruction.

Breaking Changes (Action Required)

  • To keep a removed model working offline, point LITELLM_MODEL_COST_MAP_URL at a metadata file that still contains its entry, and unset LITELLM_LOCAL_MODEL_COST_MAP. The file replaces the whole map, so it must cover every model you use.
  • DSPy now supports Python 3.15 (requires-python = ">=3.10, <3.16").
Copy-Paste Upgrade / Migration Snippet
npm install dspy-ai@3.4.1

Ecosystem Compatibility Matrix & Verified Graph Warnings

TypeScript 5.xcompatible— Ships standard TypeScript declaration files without type regressions.

Zero-Noise Historical Release Timeline (1)

Format: [Core Change] + [Required Action] + [Migration Effort]
v3.4.1BREAKING⚖️ Size Unavailable

skills: reference material for the reflection LM. Pass a. Review breaking API changes before up… Migration: Moderate.

Upgrade & Migration Q&A (stanfordnlp/dspy v3.4.1)

Direct Answers for Engineers & AI Agents

Is stanfordnlp/dspy v3.4.1 safe to upgrade in production?

stanfordnlp/dspy v3.4.1 is classified as BREAKING (PATCH release). skills: reference material for the reflection LM. Pass a. Review breaking API changes before up… Migration: Moderate.

What breaking changes or compatibility risks exist in stanfordnlp/dspy v3.4.1?

To keep a removed model working offline, point LITELLM_MODEL_COST_MAP_URL at a metadata file that still contains its entry, and unset LITELLM_LOCAL_MODEL_COST_MAP. The file replaces the whole map, so it must cover every model you use. DSPy now supports Python 3.15 (requires-python = ">=3.10, <3.16").

What is the bundle size impact of dspy-ai v3.4.1?

Measured bundle size telemetry is currently unavailable for dspy-ai v3.4.1; verify build output locally before deploying.

How do I upgrade dspy-ai to v3.4.1?

Upgrade dspy-ai to v3.4.1 by running "npm install dspy-ai@3.4.1" and applying the migration steps: npm install dspy-ai@3.4.1