feat: multi-agent statusline support (Claude Code / pi / Kimi / Codex)#1
Merged
Conversation
- InputData: all fields now optional; accept host-provided context info via 'context_window' (pi dialect) or 'context' (kimi-code PR #2043 dialect), plus session_id and pi.session_file extension - ContextWindow segment: prefer host-provided context_window_size and current_usage over transcript parsing + models.toml guessing (fixes wrong 200k limit for pi sessions running Kimi K3 with 1M context) - models: recognize kimi-k3 (1M), kimi-k2.7-code / kimi-k2.6 (256K); bump legacy kimi-k2 entries to 262144 - new 'ccline --codex' / '--codex-session' mode: codex has no external statusline hook, so read the newest top-level rollout-*.jsonl from $CODEX_HOME/sessions directly (skips subagent threads, prefers cwd match), synthesizing model / cwd / token_count context data for tmux or sidecar use - Model segment: skip rendering when input has no model info - docs: add docs/multi-agent.md and per-agent support matrix in READMEs Claude-Session: https://claude.ai/code/session_01CzLbLRgFKRDZZjvDNQngRg
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adapts CCometixLine to the four commonly-used AI coding agents:
context_windowpayload — correct context limit (e.g. K3 = 1M instead of the 200k fallback) and exact token breakdown fromcurrent_usagekimi-k3(1M),kimi-k2.7-code/kimi-k2.6(256K); also pre-wired for the kimi-code statusline proposal dialect (contextblock, MoonshotAI/kimi-code#2043)ccline --codexmode reading rollout sessions directly, since codex has no external statusline hook (openai/codex#17827); skips subagent threads, prefers cwd-matching session; for tmux / sidecar panesChanges
InputData: fully lenient parsing (all fields optional), newcontext_window/contextblock,session_id,piextensionsrc/core/codex.rs: rollout locator + parser (session_meta/turn_context/token_count)kimi-k2@128k defaults were stale)docs/multi-agent.md+ support matrix in both READMEsTest plan
cargo test— 5 unit tests incl. real pi payload, kimicontextdialect, codex rollout fixture[new: 841; cr: 96.8k]breakdown--codexagainst live~/.codex/sessions→ GPT-5.6-sol, 51.0% contextcontext_window) → transcript fallback intactcargo clippy— no new warnings (2 pre-existing untouched)https://claude.ai/code/session_01CzLbLRgFKRDZZjvDNQngRg