Commit Graph

7 Commits

Author SHA1 Message Date
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