Commit Graph

15 Commits

Author SHA1 Message Date
ton 367ebc1c7f new_pull 2026-07-26 14:02:37 +07:00
Mario Zechner abbd911693 Merge main into model-registry 2026-06-22 14:00:18 +02:00
Mario Zechner 717a8f958a fix(ai): revert selective pi-ai base entrypoints 2026-06-22 12:54:32 +02:00
Fred K. Schott 0d89a33373 feat(packages): Add selective pi-ai base entrypoints (#5348) 2026-06-19 00:41:49 +02:00
Armin Ronacher 21a904f4b7 fix(ai): disable OpenCode long cache retention for rejecting routes
closes #5702
2026-06-13 23:59:45 +02:00
Mario Zechner 8a0903ebf2 feat(ai): compat entrypoint, core-only root barrel (phase 5)
The root barrel is now core-only and side-effect free: types,
createModels/createProvider, auth substrate, lazyStream/lazyApi, faux,
utils. Generated catalogs, api-registry, env-api-keys, images, global
stream functions, and per-API lazy wrappers leave the root.

New @earendil-works/pi-ai/compat preserves the old surface verbatim as
a strict superset of the root: api-dispatch stream/complete with env
key injection, the builtin registration side effect (skip-if-present so
it cannot clobber earlier overrides), deprecated getModel/getModels/
getProviders aliases of the new getBuiltin* reads in providers/all,
lazy api wrappers + setBedrockProviderModule, and image generation.
Compat dies with the coding-agent ModelManager migration.

Packaging: exports map gains ./compat, ./providers/*, ./api/*;
sideEffects array lists only the effectful modules.

Old-global imports across agent/coding-agent/examples and pi-ai tests
switch to /compat (path-only; compat is a superset). The coding-agent
extension loader resolves the pi-ai ROOT specifier to compat, so
existing user extensions using the old global API keep working at
runtime until compat is removed. vitest configs alias /compat to src;
browser smoke imports old globals from /compat.
2026-06-10 21:17:12 +02:00
Mario Zechner ba93da9a93 feat(ai): move API implementations to src/api with lazy wrappers (phase 2)
Stream implementations move from src/providers/ to src/api/, renamed by
API id (anthropic.ts -> anthropic-messages.ts, google.ts ->
google-generative-ai.ts, mistral.ts -> mistral-conversations.ts,
amazon-bedrock.ts -> bedrock-converse-stream.ts). Every module now
exports exactly stream/streamSimple; shared helpers move alongside.

New ProviderStreams dispatch contract in types.ts, lazyApi() wrapper in
api/lazy.ts, and one .lazy.ts wrapper per API. Bedrock's wrapper keeps
the node-only variable-specifier import and setBedrockProviderModule()
(now taking ProviderStreams).

providers/register-builtins.ts deleted; interim until the compat
entrypoint lands, builtin api-registry registration lives in stream.ts
and lazy wrappers are exported from the root barrel. Old per-API lazy
exports (streamAnthropic, ...) are gone; package.json subpaths retarget
to dist/api/.
2026-06-10 20:08:59 +02:00
Mario Zechner f1f7cd50c3 test: speed up provider payload coverage 2026-05-20 12:37:58 +02:00
Mario Zechner 4cd4cfd98e fix(ai): support long cache retention compat
closes #3543
2026-04-23 23:43:34 +02:00
Mario Zechner e58d631c89 Reapply "fix(ai): own Anthropic SSE parsing to avoid SDK JSON.parse hard-failures"
This reverts commit fc9220d2de.
2026-04-21 23:42:19 +02:00
Mario Zechner fc9220d2de Revert "fix(ai): own Anthropic SSE parsing to avoid SDK JSON.parse hard-failures"
This reverts commit 4b926a30a2.
2026-04-21 23:19:52 +02:00
Mario Zechner 4b926a30a2 fix(ai): own Anthropic SSE parsing to avoid SDK JSON.parse hard-failures
Bypass the Anthropic SDK streaming parser entirely. Use
client.messages.create().asResponse() and decode the SSE stream
ourselves with defensive JSON parsing that repairs invalid escape
sequences and control characters inside string literals.

- Switch from SDK .stream() to .asResponse() + pi-owned SSE decoder
- Add repairJson() / parseJsonWithRepair() to json-parse.ts
- Add anthropic-sse-parsing.test.ts regression for malformed tool deltas
- Update github-copilot-anthropic.test.ts mock to match new call path
- Update deprecated claude-3-5-haiku-20241022 refs to claude-haiku-4-5
- Remove stale non-reasoning model test

fixes #3175
2026-04-21 23:00:56 +02:00
Mario Zechner 111a31e4db fix(ai): apply cache_control to string user messages 2026-02-02 19:19:12 +01:00
Mario Zechner abfd04b5c5 feat(ai): add cacheRetention stream option 2026-02-01 09:32:10 +01:00
Mario Zechner 1b6a147579 feat(ai): add PI_CACHE_RETENTION env var for extended prompt caching
Adds support for extended cache retention via PI_CACHE_RETENTION=long:
- Anthropic: 5m -> 1h TTL
- OpenAI: in-memory -> 24h retention

Only applies to direct API calls (api.anthropic.com, api.openai.com).
Proxies and other providers are unaffected.

fixes #967
2026-01-29 02:22:06 +01:00