Split OpenAICompat into OpenAICompletionsCompat and OpenAIResponsesCompat
for type-safe API-specific compat settings. Added strictResponsesPairing
option to suppress orphaned reasoning/tool calls on incomplete turns,
fixing 400 errors on Azure's Responses API which requires strict pairing.
Closes#768
* Support shell command execution for API key resolution in models.json
Add ! prefix support to apiKey field in models.json to execute shell commands
and use stdout as the API key. This allows users to store API keys in secure
credential managers like macOS Keychain, 1Password, Bitwarden, or HashiCorp Vault.
Example: "apiKey": "!security find-generic-password -ws 'anthropic'"
The apiKey field now supports three formats:
- !command - executes shell command, uses trimmed stdout
- ENV_VAR_NAME - uses environment variable value
- literal - uses value directly
fixes#697
* feat(coding-agent): cache API key command results for process lifetime
Shell commands (! prefix) are now executed once and cached. Environment
variables and literal values are not cached, so changes are picked up.
Addresses review feedback on #762.
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
Container components with embedded Input/Editor children must implement
Focusable and propagate focus state to enable correct IME candidate
window positioning.
Related to #827
Components with search inputs now implement Focusable interface and
propagate focus state to their child Input components. This allows
the hardware cursor to be positioned correctly for IME candidate
window placement.
Affected components:
- ModelSelectorComponent
- ScopedModelsSelectorComponent
- SessionSelectorComponent (and SessionList)
- ExtensionInputComponent
- LoginDialogComponent
- TreeSelectorComponent (and LabelInput)
fixes#827
Adds deleteWordForward action bound to Alt+D, which deletes from cursor
to the end of the current word and saves to kill ring for later yanking.
Consecutive forward kills append to the same kill ring entry.
Add kill ring functionality with:
- Ctrl+W/U/K save deleted text to kill ring
- Ctrl+Y yanks (pastes) most recent deletion
- Alt+Y cycles through kill ring (after Ctrl+Y)
- Consecutive deletions accumulate into single entry
In legacy terminal mode (non-Kitty protocol), Alt+key is sent as ESC
followed by the key character. This was only supported for specific keys
(space, backspace, arrows) but not for regular letters.
Add support for Alt+letter sequences to enable keybindings like Alt+Y.
- Replace hardcoded pi->CC tool mappings with single CC tool name list
- Case-insensitive lookup: if tool name matches CC tool, use CC casing
- Remove broken find->Glob mapping (round-trip failed)
- Add test coverage for tool name normalization
When an assistant message has stopReason 'error', its tool calls are now
excluded from pending tool tracking. This prevents synthetic tool results
from being generated for calls that will be dropped by provider-specific
converters (e.g., Codex drops tool calls from errored messages).
Previously, this mismatch caused OpenAI to reject requests with 'No tool
call found for function call output with call_id ...' errors.
fixes#812
Bedrock Claude models require max_tokens to exceed thinking.budget_tokens.
This constraint was handled for anthropic-messages API but missing for
bedrock-converse-stream, causing compaction failures.
Extracted adjustMaxTokensForThinking() helper that:
- Adds thinking budget on top of desired output tokens
- Reduces thinking budget if insufficient room (min 1024 output tokens)
- Applied to both anthropic-messages and bedrock-converse-stream APIs
Instead of skipping unsigned tool calls entirely (which lobotomizes context),
convert them to text with an explicit note telling the model this is historical
context from a different model and not a format to mimic.
This preserves tool call/result context when switching from providers without
thought signatures (e.g. Claude via Antigravity) to Gemini 3.
When auto-compaction fails (e.g., quota exceeded), emit the error via
the auto_compaction_end event instead of throwing. The UI now displays
the error message, allowing users to take action (switch models, wait
for quota reset, etc.) instead of crashing.
fixes#792
