Per-provider vision blocks; parser repairs local models' almost-JSON

config.toml now carries a [vision.<provider>] block per backend —
model/base_url/key_env — with vision_provider picking the active one,
so the committed file documents every recipe and switching is a
one-line flip. Only the active block applies; typo'd block names and
keys warn like every other config mistake.

First real Ollama run (qwen2.5vl:7b) surfaced what local models emit:
almost-JSON with trailing commas. parse_vision_response now makes one
cheap repair pass before declaring a response unusable.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016jXZFSTZQKzAC8fqpWSz9g
This commit is contained in:
Eric Wagoner
2026-08-03 18:39:27 -04:00
co-authored by Claude Fable 5
parent 0358079da4
commit 118503e4e0
6 changed files with 99 additions and 12 deletions
+1 -1
View File
@@ -70,7 +70,7 @@ Every stage is idempotent and resumable: kill it mid-run, restart, lose nothing.
## Requirements
- macOS or Linux, Python 3.12+, [uv](https://docs.astral.sh/uv/)
- A vision model for extraction — an [Anthropic API key](https://console.anthropic.com/) by default, or any OpenAI-compatible endpoint via `config.toml` (`vision_provider = "openai-compatible"` + `vision_base_url`): OpenAI, OpenRouter, or a free local runtime like [Ollama](https://ollama.com/) with a vision-capable model. Local models read spines noticeably worse than frontier ones — expect a longer proofread pass on the Titles page, not a broken pipeline.
- A vision model for extraction — an [Anthropic API key](https://console.anthropic.com/) by default, or any OpenAI-compatible endpoint: OpenAI, OpenRouter, or a free local runtime like [Ollama](https://ollama.com/) with a vision-capable model. `config.toml` carries a `[vision.<provider>]` block for each; `vision_provider` picks one. Local models read spines noticeably worse than frontier ones — expect a longer proofread pass on the Titles page, not a broken pipeline.
- A BoardGameGeek account **and a registered BGG application** — as of BGG's [2025 API policy](https://boardgamegeek.com/using_the_xml_api), the XML API requires a Bearer token from a registered app. Register a free non-commercial application at [boardgamegeek.com/applications](https://boardgamegeek.com/applications) (approval can take a week or more, so **apply on day one**), then create a token. Each user needs their own; tokens must not be shared.
## Quick start