mirror of https://github.com/vectorize-io/hindsight.git synced 2026-09-14 19:31:49 +08:00

Files

T

History

Nicolò Boschi ead16521ea fix(reflect): say when the structured-output extraction failed (#4230 )

Reflect with a `response_schema` runs a second LLM call that reshapes the prose
answer into the caller's schema. When that call errored or returned something
unparseable, the bare `except` swallowed it and the caller got 200 with
`structured_output: null` — indistinguishable from an answer that genuinely held
nothing matching the schema. The machine-readable half, which is the reason a
caller supplied a schema at all, failed invisibly: no retry signal, no alert.

Returning 200 with the text answer is still right; the missing piece was saying
the structured half did not happen. `StructuredOutputResult` now carries an
`error`, and reflect surfaces it as a nullable `structured_output_error` on the
response. Present => the extraction broke (retryable); absent with a null
`structured_output` => nothing to extract.

The mental-model refresh path uses the same helper and now records the reason in
its `structured_output_failed` failure detail instead of only "extraction
failed".

2026-09-09 12:38:52 +02:00

blog

docs: point the Slack community links at a redirect instead of a raw invite token (#4223 )

2026-09-08 11:29:27 -04:00

docs

fix(reflect): say when the structured-output extraction failed (#4230 )

2026-09-09 12:38:52 +02:00

docs-integrations

feat(coding-agents): spread page refreshes with hashed cron fields (H) (#4208 )

2026-09-08 11:06:42 +02:00

examples

fix(api): type the list and graph rows instead of returning bare dicts (#4218 ) (#4233 )

2026-09-08 18:48:52 +02:00

guides

docs(hermes): disable Hermes's built-in memory via config flags (#3940 )

2026-08-31 17:26:59 +02:00

plugins/integration-changelogs

docs: make every integration changelog reachable, and compact the Integrations Hub (#4005 )

2026-09-02 10:21:08 +02:00

scripts

docs: make every integration changelog reachable, and compact the Integrations Hub (#4005 )

2026-09-02 10:21:08 +02:00

src

release(coding-agents): v0.5.2

2026-09-08 17:46:12 +02:00

static

fix(reflect): say when the structured-output extraction failed (#4230 )

2026-09-09 12:38:52 +02:00

versioned_docs

docs(docker): reserve shared memory for embedded PostgreSQL (#3896 )

2026-09-01 12:03:16 +02:00

versioned_sidebars

docs: point the Slack community links at a redirect instead of a raw invite token (#4223 )

2026-09-08 11:29:27 -04:00

.gitignore

…

docusaurus.config.ts

docs: point the Slack community links at a redirect instead of a raw invite token (#4223 )

2026-09-08 11:29:27 -04:00

package.json

perf(docs): switch the Docusaurus build to Rspack + SWC (#3357 )

2026-08-10 17:52:51 +02:00

README.md

…

sidebars-integrations.ts

docs: launch Coding Agents + mark the per-agent plugins superseded (#3162 )

2026-08-07 17:00:50 +02:00

sidebars.ts

docs: point the Slack community links at a redirect instead of a raw invite token (#4223 )

2026-09-08 11:29:27 -04:00

tsconfig.json

…

versions.json

Release v0.9.0

2026-08-07 18:16:35 +02:00

README.md

Website

This website is built using Docusaurus, a modern static website generator.

Installation

npm install

Local Development

npm start

This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.

Build

npm run build

This command generates static content into the build directory and can be served using any static contents hosting service.

Deployment

Using SSH:

USE_SSH=true npm run deploy

Not using SSH:

GIT_USER=<Your GitHub username> npm run deploy

If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the gh-pages branch.