Releases: cecli-dev/cecli
Releases · cecli-dev/cecli
v0.96.8
What's Changed
MR: #427
Full Changelog: v0.96.7...v0.96.8
Includes:
- Format system messages and in context files before adding user message to conversation stream
- Use relative paths consistently in conversation messages so models know we are referring to the same files
v0.96.7
What's Changed
MR: #424
Full Changelog: v0.96.6...v0.96.7
Addresses:
Includes:
- Add environment variable for cecli config file path by @gopar in #422
- Feature/rebrand website (remove Aider references, ensure site is cohesive with project identity) by @synth-mania in #423
- Allow ShowNumberedContext and ReplaceText tools to be used for multiple parallel searches and edits to cut down the number of exploration and edit turns required for models powerful enough to take advantage of it
- Change tool executor methods so models are allowed to hallucinate parameters without necessarily disrupting operations as long as they specify a proper superset of the real parameters
- Allow the
/addcommand to include files outside of the current repository
New Contributors
- @synth-mania made their first contribution in #423
v0.96.6
v0.96.5
What's Changed
MR: #418
Full Changelog: v0.96.4...v0.96.5
Includes:
- Autocomplete that functions in classic mode across all slash commands
- Autocomplete on empty prefix for initial recommendations
- Remind editor model that it actually needs to apply the edits from the architect model
- More (and forced) autosave checkpoints
v0.96.4
v0.96.3
What's Changed
MR: #412
Full Changelog: v0.96.2...v0.96.3
Includes:
/compact {message}to force compaction with hints to what the model should focus on- Fix chunk ordering on creation of temporary coder class creation for one-off messages (used extensively across the code base)
v0.96.2
What's Changed
MR: #411
Full Changelog: v0.96.1...v0.96.2
Includes:
- Upgrade litellm minimum version to better enforce their data contract
- Fix
/tokensto count tokens using the conversation system proeprly thought_signatureserror and translating them tothought_signaturefor general Gemini model operation- Restore original SSE transport implementation since being a subclass of the Http based transport doesn't work with the MCP SDK's signature expectations
v0.96.1
What's Changed
MR: #406
Full Changelog: v0.96.0...v0.96.1
Addresses:
#382
#397
#402
#403
#405
Includes:
- Add Python 3.13 and 3.14 by @gopar in #404
- Expand
~when given an mcp servers file by @gopar in #407 - Small Performance Enhancements
- Usage hints for commands in TUI, keys for mentions, text selection, etc.
- Add
/compactslash command /terminal-setupto respect terminal env variables- Fix pip auto install package name
v0.96.0
What's Changed
MR: #394
Full Changelog: v0.95.11...v0.96.0
Addresses:
#401
#399
#396
#392
#332
Includes:
- Unified
ReplaceTexttool for agent mode that allows for simultaneous edits, for models that can handle that - More forgiving
InsertBlocktool (will not complain about insertions on empty files) - Long background command handler (paves the way for running reactive agent loops)
- Conversation System Overhaul (should lead to at least a 10 - 25% price reduction for PAYG APIs through more careful context construction)
- [gh-392] Enable and disable mcp servers by @gopar in #398
- [#379 ](feat: Implement nested LLM retry configuration via --retries argument by @szmania in #379)
- Add "--show-thinking" parameter (True by default) to control showing/hiding CoT content in model responses