createBranchedSession() wrote the file and set flushed=true even when the
branched path had no assistant message. The next _persist() call saw no
assistant, reset flushed=false, and the subsequent flush appended all
in-memory entries to the already-populated file, duplicating the header
and entries.
Fix: defer file creation when the branched path has no assistant message,
matching the newSession() contract. _persist() creates the file on the
first assistant response.
closes#1672
- Map redacted_thinking to ThinkingContent with redacted: true instead of
adding a new content type. The opaque payload goes in thinkingSignature,
thinking text is set to "[Reasoning redacted]" so it renders naturally
everywhere. Cross-model transform drops redacted blocks.
- Skip interleaved-thinking-2025-05-14 beta header for Opus 4.6 / Sonnet 4.6
where adaptive thinking makes it deprecated/redundant.
- Do not send temperature when thinkingEnabled is true (incompatible with
both adaptive and budget-based thinking).
Based on #1665 by @tctev
The test used 'github.com/test/extension' as the git source, but
parseGitUrl() requires a 'git:' prefix for bare hostnames. Changed
to 'git:github.com/test/extension' so the source is correctly
parsed as a git type and update() actually runs.
When resolving --model zai/glm-5, the resolver now correctly interprets
'zai' as the provider and 'glm-5' as the model id, rather than matching
a vercel-ai-gateway model whose id is literally 'zai/glm-5'.
If the provider/model split fails to find a match, falls back to raw id
matching to still support OpenRouter-style ids like 'openai/gpt-4o:extended'.
Changed koffi import from top-level to dynamic require in
enableWindowsVTInput() and added --external koffi to bun build.
This prevents embedding all 18 platform .node files (~74MB) into
every compiled binary. For Windows builds, only the win32_x64
koffi.node is shipped alongside the binary.
Binary size reduction: darwin-arm64 142MB -> 67MB, archive 43MB -> 28MB.
Added to both OpenAI API and OpenAI Codex (ChatGPT OAuth) providers.
128k context window, text-only, research preview with zero cost.
Not yet functional via pi, may become available in the next few hours or days.
After compaction, context token count is unknown until the next LLM
response. Instead of showing stale pre-compaction values or heuristic
estimates, the footer now shows ?/200k.
ContextUsage.tokens and ContextUsage.percent are now number | null
(breaking change). Removed usageTokens, trailingTokens, lastUsageIndex
from ContextUsage (internal details).
Also fixed _checkCompaction() using .find() (first compaction) instead
of getLatestCompactionEntry() (latest), which caused incorrect overflow
detection with multiple compactions.
Closes#1382
Add metadata?: Record<string, unknown> to StreamOptions so providers
can extract fields they understand. Anthropic provider extracts user_id
for abuse tracking and rate limiting. Other providers ignore it.
Based on #1384 by @7Sageer, reworked to use a generic type instead of
Anthropic-specific typing on the base interface.
- Replace verbose ANTIGRAVITY_SYSTEM_INSTRUCTION with compact version from CLIProxyAPI
- Replace bridgePrompt override with [ignore] wrapper pattern
- Switch Antigravity Gemini test model from gemini-3-flash to gemini-3-pro-high
- Rename calculator tool to math_operation (gemini-3-pro ignores schema for 'calculator')
closes#1415
Include tool parameter names, types, descriptions in a collapsible
section under each tool in the export HTML. Also adds parameters to
pi.getAllTools() return value.
closes#1407, closes#1416
rg was only downloaded lazily when the grep tool was invoked, but the
LLM often uses rg directly via the bash tool. Ensure both fd and rg
are downloaded at startup so they are available in PATH for all tools.
fixes#1348
- Use parametersJsonSchema instead of parameters for Gemini tool declarations
to support full JSON Schema (anyOf, oneOf, const, etc.)
- Keep legacy parameters field for Claude models on Cloud Code Assist, where
the API translates parameters into Anthropic's input_schema
- Revert claude-opus-4-6-thinking back to claude-opus-4-5-thinking (model
doesn't exist on the Antigravity endpoint)
fixes#1398
Windows does not ship with unzip, causing fd/rg download to fail on
first run in PowerShell. Use tar (bsdtar, available on Windows 10+)
for both .tar.gz and .zip extraction. Also adds proper error checking
on the extraction result.
fixes#1348
Mario Zechner