@dashup/connector 0.1.17 → 0.1.19

package/README.md

@@ -20,7 +20,7 @@ dashup projects
 dashup alert --project PROJECT_ID --title "Dashup is connected"
 ```
 
-The connector automatically reads existing Claude Code, Codex, and OpenCode conversations alongside Zed workspaces and VS Code chat history. It honors the harness's existing data directory, authentication, and native session IDs. Native stores are opened read-only; discovery never launches an agent, creates or resumes a conversation, or changes editor settings. Only a session the phone starts runs an agent (see below). Opening the same supported harness session through Zed and its native history uses one Dashup thread when their actual session identities match. Matching directory names alone never merges local and SSH projects.
+The connector automatically reads existing Claude Code, Codex, Kimi, and OpenCode conversations alongside Zed workspaces and VS Code chat history. It honors the harness's existing data directory, authentication, and native session IDs. Native stores are opened read-only; discovery never launches an agent, creates or resumes a conversation, or changes editor settings. Only a session the phone starts runs an agent (see below). Opening the same supported harness session through Zed and its native history uses one Dashup thread when their actual session identities match. Matching directory names alone never merges local and SSH projects.
 
 A thread's title is the agent's own (a rename, Codex's stored title, Claude's title), else the first message the person typed: Codex's injected AGENTS.md and environment messages and Claude Code's slash commands are skipped, and a Codex subagent is named for its task. In the conversation, Codex's injected messages and Claude Code's own meta rows stay out, and a Claude Code slash command reads as typed, followed by its output. A thread's time is its last conversation message in the agent's own history; editor bookkeeping such as Zed's sidebar restamps never moves it. Subagent sessions (OpenCode children, Codex spawned agents) carry their parent thread. Tool calls are joined with their results into one step with status, duration and, for file edits, a unified diff. Saved history has unknown live status; the phone can answer it by resuming it (see Starting sessions from the phone). File changes publish project metadata; only an approval, a question, an error or a finished turn sends an alert. A workspace becomes a project once it has a conversation. After every change the connector publishes its overview: every project, and the conversations Home shows (anything that needs the person or is working, then the newest 20). The phone renders Home from the overview alone and decodes a project's full snapshot only when a page opens it. Only a scan that read every source retires a project it published earlier and left off. Each phone read request reads a thread's native history once and publishes a snapshot of separately encrypted message fragments to the database. The phone reads bounded latest and earlier pages; realtime thread updates carry only summary and approval metadata. Native history remains the source, and an incomplete upload never replaces the previous published snapshot. Native live interfaces provide actual status and pending choices. Tool integrations can also queue explicit encrypted alerts with `alert`.
 
@@ -47,9 +47,9 @@ Only an explicit Queue reply starts a temporary official app-server helper to in
 
 Delivery requires that exact typed client-message ID in the original thread's native history database. A response receipt requires a later native assistant item in the same turn; it does not mean the agent finished. Receipts remain encrypted through the ordinary Dashup relay. History is read on request; the phone asks again while a thread is open and its session changes. Native approvals owned by the private-stdio process remain unsupported and require its original UI. Queue text never substitutes for a native approval.
 
-Each thread shows what its agent's own record says it last ran with. A Claude Code session shows the model of its newest reply and, where that model takes them, fast mode and ultracode; the choices and their names are the models the session's own Claude Code binary offers hosts in its initialize answer, or `claude`'s where the system does not name the binary. A Codex thread shows the model and reasoning effort of its newest turn and, where the model has the priority tier, fast mode, named from Codex's own `models_cache.json`. A setting an agent records only when it changes, such as ultracode or Codex's tier, is searched for however far back it lies. A saved thread carries these, without choices, only in its own published state, never in a project's snapshot.
+Each thread shows what its agent's own record says it last ran with. A Claude Code session shows the model of its newest reply and, where that model takes them, fast mode and ultracode; the choices and their names are the models the session's own Claude Code binary offers hosts in its initialize answer, or `claude`'s where the system does not name the binary. A Codex thread shows the model and reasoning effort of its newest turn and, where the model has the priority tier, fast mode, named from Codex's own `models_cache.json`. An OpenCode session shows the model and agent OpenCode keeps on the session (`/api/session`), among the models and primary agents it lists for the folder. Kimi records only a session's plan mode, so a session the phone runs shows the model and thinking it starts with, among the models Kimi's `config.toml` names. A setting an agent records only when it changes, such as ultracode or Codex's tier, is searched for however far back it lies. A saved thread carries these, without choices, only in its own published state, never in a project's snapshot.
 
-The phone changes a running session's settings: through the Claude plugin with Claude Code's own `/model`, `/fast` and `/effort ultracode` commands; in a Claude session the phone started, with control requests at the start of each turn; and in a Codex thread the connector holds, with the next `turn/start` it sends. An agent records a change when its next turn starts, so it shows from the next reply. A change expires with other commands after 60 seconds.
+The phone changes a running session's settings: through the Claude plugin with Claude Code's own `/model`, `/fast` and `/effort ultracode` commands; in a Claude session the phone started, with control requests at the start of each turn; in a Codex thread the connector holds, with the next `turn/start` it sends; in an OpenCode session, on the session itself, so the phone's messages go in what it runs with; and in a Kimi session the phone runs, as its next turn starts, with plan mode at once. An agent records a change when its next turn starts, so it shows from the next reply. A change expires with other commands after 60 seconds.
 
 Stop interrupts the running turn through each live interface: OpenCode's session abort, Codex `turn/interrupt`, the AHP client's turn cancellation, ACP `session/cancel`, and the Claude Code plugin's turn abort. It refuses when nothing is running and expires with other commands after 60 seconds, so a late stop cannot end a newer turn.
 
@@ -57,9 +57,9 @@ Live discovery is bounded to 100 sessions per endpoint. OpenCode supplies the la
 
 ## Starting sessions from the phone
 
-The phone starts a session in a local project, or in a new folder inside one of the folders that already hold this computer's projects, with Claude Code, Codex or OpenCode: whichever of `claude`, `codex` and `opencode` runs here. The agent works with its own settings and permission rules, and asks the phone before anything they don't allow. Claude Code runs headless (`claude -p`) for each turn and resumes the session for the next; Codex threads start in Codex's own app-server daemon (`codex app-server daemon start`) and outlive the connector; OpenCode sessions run on an `opencode serve` the connector starts for that folder. Claude Code's permission requests arrive with the command, or the diff an edit or write would make, and the rule that would stop it asking again; the phone answers its questions and plans as Claude Code's host.
+The phone starts a session in a local project, or in a new folder inside one of the folders that already hold this computer's projects, with Claude Code, Codex, Kimi or OpenCode: whichever of `claude`, `codex`, `kimi` and `opencode` runs here, and the Kimi Zed's agent registry installed when `kimi` is not on the PATH. The agent works with its own settings and permission rules, and asks the phone before anything they don't allow. Claude Code runs headless (`claude -p`) for each turn and resumes the session for the next; Codex threads start in Codex's own app-server daemon (`codex app-server daemon start`) and outlive the connector; OpenCode sessions run on an `opencode serve` the connector starts for that folder; Kimi runs its wire mode (`kimi --wire`) for each turn under a session id the connector chooses, and the phone answers its approvals and questions. Claude Code's permission requests arrive with the command, or the diff an edit or write would make, and the rule that would stop it asking again; the phone answers its questions and plans as Claude Code's host.
 
-A saved conversation is answered the same way when its agent runs here, its project is local, and nothing else has it open: Claude Code resumes it (`claude -p --resume`), Codex loads it in its daemon (`thread/resume`), and OpenCode serves its folder. One a native Codex process owns takes queued messages instead. A start expires with other commands after 60 seconds.
+A saved conversation is answered the same way when its agent runs here, its project is local, and nothing else has it open: Claude Code resumes it (`claude -p --resume`), Codex loads it in its daemon (`thread/resume`), Kimi resumes it (`kimi --wire --session`), and OpenCode serves its folder. One a native Codex process owns takes queued messages instead. A start expires with other commands after 60 seconds.
 
 ## Optional ACP wrapper
 
@@ -83,7 +83,7 @@ Answering yes to the walkthrough's background question, or running `dashup insta
 
 ## Local state and checks
 
-`~/.dashup/connector.json` holds this computer's secret, pairing keys, encrypted outbox, and replay counters. It is written atomically with private Unix permissions; it is not currently protected by an OS credential vault. Do not share or copy it to another connector. `DASHUP_CONFIG` selects a separate state file. `DASHUP_ZED_DATA` and `DASHUP_VSCODE_DATA` select custom editor data directories. Native history discovery honors `CLAUDE_CONFIG_DIR`, `CODEX_HOME`, and XDG paths. The selected conversation is parsed locally on demand; Dashup does not create another plaintext transcript database.
+`~/.dashup/connector.json` holds this computer's secret, pairing keys, encrypted outbox, and replay counters. It is written atomically with private Unix permissions; it is not currently protected by an OS credential vault. Do not share or copy it to another connector. `DASHUP_CONFIG` selects a separate state file. `DASHUP_ZED_DATA` and `DASHUP_VSCODE_DATA` select custom editor data directories. Native history discovery honors `CLAUDE_CONFIG_DIR`, `CODEX_HOME`, `DASHUP_KIMI_HOME` (else `~/.kimi`), and XDG paths. The selected conversation is parsed locally on demand; Dashup does not create another plaintext transcript database.
 
 From a checkout, run `pnpm install` and `pnpm exec turbo build --filter=@dashup/connector...` with pnpm 10.34.5, then use `pnpm --filter @dashup/connector dashup` in place of `dashup`. For isolated development fixtures, `DASHUP_LIVE_DISCOVERY=0` disables automatic process discovery. Explicit `DASHUP_OPENCODE_ENDPOINT`, `DASHUP_CODEX_SOCKET`, and `DASHUP_AHP_DATA` overrides allow local test endpoints without modifying editor configuration. They are not required for ordinary discovery.