| app:hideaibutton <VersionBadge version="v0.14" /> | bool | Set to true
to hide the AI button in the tab bar (defaults to false) |
| app:disablectrlshiftarrows <VersionBadge version="v0.14" /> | bool |
Set to true to disable Ctrl+Shift+Arrow keybindings for block navigation
(defaults to false) |
| app:disablectrlshiftdisplay <VersionBadge version="v0.14" /> | bool |
Set to true to disable the Ctrl+Shift visual indicator display (defaults
to false) |
This pull request introduces a new `test-conn` command-line tool for
testing SSH connection flows and user input handling, along with
improvements to user input provider extensibility and several
configuration and validation enhancements.
* New `test-conn` CLI Tool
* User Input Provider Abstraction
* Refactored user input handling to use a pluggable `UserInputProvider`
interface, with a default `FrontendProvider` and the ability to set a
custom provider
* AI Configuration and Verbosity updates
* Enforced that a `SwapToken` must be present in `CommandOptsType` when
starting a remote shell with wsh, improving validation and error
handling. (`pkg/shellexec/shellexec.go`)
* Improved config directory watcher logic to log the config directory
path and avoid logging errors for non-existent subdirectories
* ConnMonitor to track stalled connections
* New Stalled Overlay to show feedback when we think a connection is
stalled
* New Icon in ConnButton to show stalled connections
* Callbacks in domain socket and PTYs to track activity
This pull request introduces a new integration test tool for the
StreamManager streaming system, adding a standalone test binary with
supporting modules for simulating and verifying high-throughput data
transfer. The changes include a test driver, a configurable in-memory
delivery pipe for simulating network conditions, a data generator, a
verifier for end-to-end integrity, and a metrics tracker. Additionally,
several improvements are made to the circular buffer and StreamManager
for better handling of blocking writes and out-of-order acknowledgments.
**New StreamManager Integration Test Tool**
* Added a new test binary `cmd/test-streammanager` with a main driver
(`main-test-streammanager.go`) that orchestrates end-to-end streaming
tests, including configuration for data size, delivery delay/skew,
window size, slow reader simulation, and verbose logging.
* Implemented a configurable `DeliveryPipe` (`deliverypipe.go`) for
simulating network delivery with delay and skew, supporting separate
data and ack channels, out-of-order delivery, and high water mark
tracking.
* Added `WriterBridge` and `ReaderBridge` modules for interfacing
between brokers and the delivery pipe, enforcing correct directionality
of data and acks.
* Created a sequential test data generator (`generator.go`) and a
verifier (`verifier.go`) for checking data integrity and reporting
mismatches.
[[1]](diffhunk://#diff-3f2d6e0349089e3748c001791a383687b33a2c2391fd3baccfceb83e76e6ee0dR1-R40)
[[2]](diffhunk://#diff-cb3aab0bae9bec15ef0c06fe5d9e0e96094affcf4720680605a92054ab717575R1-R61)
* Introduced a metrics module (`metrics.go`) for tracking throughput,
packet counts, out-of-order events, and pipe usage, with a summary
report at test completion.
**StreamManager and CirBuf Improvements**
* Refactored circular buffer (`pkg/jobmanager/cirbuf.go`) to replace
blocking writes with a non-blocking `WriteAvailable` method, returning a
wait channel for buffer-full scenarios, and removed context-based
cancellation logic.
* Updated StreamManager (`pkg/jobmanager/streammanager.go`) to track the
maximum acknowledged sequence/rwnd tuple, ignoring stale or out-of-order
ACKs, and resetting this state on disconnect.
* Modified StreamManager's data handling to use the new non-blocking
buffer write logic, ensuring correct signaling and waiting for space
when needed.
**Minor Cleanup**
* Removed unused context import from `cirbuf.go`.
* Minor whitespace cleanup in `streambroker.go`.
* Track wave version when job was created (for future backward compat)
* New Flyover Menu off of "shell durability" icon. Help + Actions + UX
* Bug with conn typeahead not closing when clicking disconnect
* Auto-reconnect jobs that have been disconnected (check for "gone"
state)
* Disable tab indicator stuff (only indicates tab not block)
* Fix bug with dev logging path on connserver
* Fix bugs with restarting blockcontrollers on startup
* Fix bugs with getting HasExited status from job manager
* Fix startup files, quoting, tilde, etc in start job flow
* ...
# Add configurable verbosity for OpenAI Responses API
Fixes#2775
## Problem
Models like `gpt-5.2-codex` and other newer OpenAI models only support
`medium` reasoning and verbosity levels, but the codebase was using
`low` by default. This caused 400 Bad Request errors:
```
Failed to stream openai-responses chat: openai 400 Bad Request:
Unsupported value: 'low' is not supported with the 'gpt-5.2-codex' model.
Supported values are: 'medium'.
```
## Solution
This PR implements a scalable, user-configurable approach instead of
hardcoding model-specific constraints:
1. **Changed default verbosity** from `"low"` to `"medium"` - more
widely supported across OpenAI models
2. **Added `ai:verbosity` config option** - allows users to configure
verbosity per model in `waveai.json`
3. **Changed rate limit fallback** from `low` to `medium` thinking level
for better compatibility
4. **Removed hardcoded model checks** - solution is scalable for future
models
## Changes
### Backend Changes
- `pkg/aiusechat/openai/openai-convertmessage.go` - Use configurable
verbosity with safe defaults
- `pkg/aiusechat/uctypes/uctypes.go` - Add `Verbosity` field to
`AIOptsType`
- `pkg/aiusechat/usechat.go` - Pass verbosity from config to options
- `pkg/wconfig/settingsconfig.go` - Add `Verbosity` to
`AIModeConfigType`
### Schema Changes
- `schema/waveai.json` - Add `ai:verbosity` with enum values
(low/medium/high)
- `frontend/types/gotypes.d.ts` - Auto-generated TypeScript types
### Configuration Example
Users can now configure both thinking level and verbosity per model:
```json
{
"openai-gpt52-codex": {
"display:name": "GPT-5.2 Codex",
"ai:provider": "openai",
"ai:model": "gpt-5.2-codex",
"ai:thinkinglevel": "medium",
"ai:verbosity": "medium"
}
}
```
* Lots of work on ResyncController, issues with stale data, and
connection switching
* Add+Fix termination messages for shell controller
* Prune done/detached jobs on a timer
* Remove circular dependencies from wcore, use blockclose event in both
jobcontroller and blockcontroller instead of direct calls
* Fix concurrency bugs with job termination
* Send object update events when modifying the block datastructure in
jobcontroller
Working on bug fixes and UX. Streams restarting, fixed lots of bugs,
timing issues, concurrency bugs. Get status shipped to the FE to drive
"shield" state display. Deal with stale streams.
Also big UX changes to the block headers. Specialize the terminal
headers to prioritize the connection (sense of place), remove old
terminal icon and word "Terminal" from the header. Also drop "Web" and
"Preview" labels on web/preview blocks.
Added `wsh focusblock` command.
* Adds a Confirm on Quit dialog (and new config to disable it)
* New MacOS keybinding for Cmd:ArrowLeft/Cmd:ArrowRight to send Ctrl-A
and Ctrl-E respectively
* Fix Ctrl-V regression on windows to allow config setting to override
* Remove questionnaire in bug template
* Full featured tab indicators -- icon, color, priority, clear features.
Can be manipulated by new `wsh tabindicator` command
* Hook up BEL to new tab indicator system. BEL can now play a sound
and/or set an indicator (controlled by two new config options)
Big simplification. Remove the FileShare interface that abstracted
wsh://, s3://, and wavefile:// files.
It produced a lot of complexity for very little usage. We're just going
to focus on the wsh:// implementation since that's core to our remote
workflows.
* remove s3 implementation (and connections, and picker items for
preview)
* remove capabilities for FE
* remove wavefile backend impl as well
* simplify wsh file remote backend
* remove ability to copy/move/ls recursively
* limit file transfers to 32m
the longer term fix here is to use the new streaming RPC primitives.
they have full end-to-end flow-control built in and will not create
pipeline stalls, blocking other requests, and OOM issues.
these other impls had to be removed (or fixed) because transferring
large files could cause stalls or crashes with the new router
infrastructure.
Lots of updates across all parts of the system to get this working. Big
changes to routing, streaming, connection management, etc.
* Persistent sessions behind a metadata flag for now
* New backlog queue in the router to prevent hanging
* Fix connection Close() issues that caused hangs when network was down
* Fix issue with random routeids (need to be generated fresh each time
the JWT is used and not fixed) so you can run multiple-wsh commands at
once
* Fix issue with domain sockets changing names across wave restarts
(added a symlink mechanism to resolve new names)
* ClientId caching in main server
* Quick reorder queue for input to prevent out of order delivery across
multiple hops
* Fix out-of-order event delivery in router (remove unnecessary go
routine creation)
* Environment testing and fix environment variables for remote jobs (get
from connserver, add to remote job starts)
* Add new ConnServerInit() remote method to call before marking
connection up
* TODO -- remote file transfer needs to be fixed to not create OOM
issues when transferring large files or directories
lots of stuff here.
introduces a streaming framework for the RPC system with flow control.
new authentication primitives for the RPC system. this is used to create
a persistent "job manager" process (via wsh) that can survive
disconnects. and then a jobcontroller in the main server that can
create, reconnect, and manage these new persistent jobs.
code is currently not actively hooked up to anything minus some new
debugging wsh commands, and a switch in the term block that lets me test
viewing the output.
after PRing this change the next steps are more testing and then
integrating this functionality into the product.
the PR spiraled and ended up being much larger than anticipated.
it is a refactor of wshrouter to have it track "links" as opposed to
just routes. this lets us simplify a lot of things when it comes to
multi-level routing.
* now the router can handle unauthenticated links directly, instead of a
weird limbo in wshproxy
* no more wshmultiproxy
* no more "authtoken" weirdness
* more straightforward handling in connserver (when using router option)
also adds more debugging, more logging, some windows fixes, other wsl
fixes
* announce and unannounce should propagate
* route the sendmessage command
* add timeouts for sending to OutputCh (appropriately)
* add ctx for SendCancel function
tie the tool approvals to the lifecycle of the SSE connection, NOT FE
keepalive packets. this prevents timeouts when the FE hasn't rendered
the tools (or FE tool rendering lifecycle issues). also allows immediate
timeouts on refresh.
other small fixes: convert to use wshclient in wshcmd-*.go files,
cleanup in SSE code
* remove title bar on windows windows
* re-integrate native controls into our tab bar
* remove menu completely (weird "Alt" activation)
* actually fix Ctrl-V in terminal
* clamp zoom levels better (0.4 - 2.6)
* simplify macos / windows drag regions (keep responsive to zoom)
* fix settings schemas for windows
We were too conservative by defaulting ignorebrackedpastemode in
xterm.js to true. it should have been set to false. this solves issues
with pasting multi-line strings into zsh, claude code, etc.
add a new context menu option to more easily disable if you're in a
weird ssh session or a REPL that doesn't support bracketedpaste.
- [x] Add new API type constant for Google Gemini in uctypes.go
- [x] Create gemini directory under pkg/aiusechat/
- [x] Implement gemini-backend.go with streaming chat support
- [x] Implement gemini-convertmessage.go for message conversion
- [x] Implement gemini-types.go for Google-specific types
- [x] Add gemini backend to usechat-backend.go
- [x] Support tool calling with structured arguments
- [x] Support image upload (base64 inline data)
- [x] Support PDF upload (base64 inline data)
- [x] Support file upload (text files, directory listings)
- [x] Build verification passed
- [x] Add documentation for Gemini backend usage
- [x] Security scan passed (CodeQL found 0 issues)
- [x] Code review passed with no comments
- [x] Revert tsunami demo go.mod/go.sum files (per feedback - twice)
- [x] Add `--gemini` flag to main-testai.go for testing
- [x] Fix schema validation for tool calling (clean unsupported fields)
- [x] Preserve non-map property values in schema cleaning
## Summary
Successfully implemented a complete Google Gemini backend for WaveTerm's
AI chat system. The implementation:
- **Follows existing patterns**: Matches the structure of OpenAI and
Anthropic backends
- **Fully featured**: Supports all required capabilities including tool
calling, images, PDFs, and files
- **Properly tested**: Builds successfully with no errors or warnings
- **Secure**: Passed CodeQL security scanning with 0 issues
- **Well documented**: Includes comprehensive package documentation with
usage examples
- **Minimal changes**: Only affects backend code under pkg/aiusechat
(tsunami demo files reverted twice)
- **Testable**: Added `--gemini` flag to main-testai.go for easy testing
with SSE output
- **Schema compatible**: Cleans JSON schemas to remove fields
unsupported by Gemini API while preserving valid structure
## Testing
To test the Gemini backend using main-testai.go:
```bash
export GOOGLE_APIKEY="your-api-key"
cd cmd/testai
go run main-testai.go --gemini 'What is 2+2?'
go run main-testai.go --gemini --model gemini-1.5-pro 'Explain quantum computing'
go run main-testai.go --gemini --tools 'Help me configure GitHub Actions monitoring'
```
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: sawka <2722291+sawka@users.noreply.github.com>
