@ricsam/r5dctl 0.0.60 → 0.0.62

package/README.md

@@ -69,21 +69,26 @@ r5dctl -s <session-id> conversation --raw              # raw JSON message/tool p
 r5dctl -s <session-id> conversation --tools            # include provider-shaped tool definitions
 r5dctl -s <session-id> conversation --system           # include system prompt messages
 r5dctl -s <session-id> conversation --raw --tools --system  # exact raw agent request transcript
+r5dctl -s <session-id> conversation -f                  # print current transcript, then follow new output (--watch also works)
 r5dctl conversation overview <session-id>               # dialogue/thinking with tool work omitted
 r5dctl conversation inspect-node <session-id> <node-id>  # raw persisted node plus traversal metadata
 r5dctl conversation inspect-work <session-id> <work-id> # compact call list for one omitted turn
 r5dctl conversation inspect-work <session-id> <work-id> --summary
 r5dctl conversation inspect-work <session-id> <work-id> --full
-r5dctl -s <session-id> prompt --mode plan --model max "..."
-r5dctl -s <session-id> answer-questions -a1 "Recipe Collection" -a2 "Both Manual & AI"
-r5dctl -s <session-id> answer-env-request -e KEY=value --context "Generate the remaining salts"
+r5dctl session prompt --worker <label> --mode plan --model max <session-id> "..."
+r5dctl -s <session-id> answer-questions --worker <label> --mode plan --model max -a1 "Recipe Collection" -a2 "Both Manual & AI"
+r5dctl -s <session-id> answer-env-request --worker <label> --mode agent --model max -e KEY=value --context "Generate the remaining salts"
 
-r5dctl -p <project> agent start --worker <label> --source worktree:main debug "Fix the failing tests"
-r5dctl agent status <session-id>
-r5dctl agent prompt --worker <label> <session-id> "Also check the migration"
-r5dctl agent merge --worker <label> <session-id>
-r5dctl agent stop <session-id>
-r5dctl agent finish-merge --worker <label> <resolver-session-id> --summary "Resolved the conflicts"
+r5dctl -p <project> session start --worker <label> --worktree main --model max "Explore the failure"
+r5dctl -p <project> session start --worker <label> --new-worktree fix/tests --source worktree:main --model max -f "Fix the failing tests"
+r5dctl session status <session-id>
+r5dctl session prompt --worker <label> --mode agent --model max <session-id> "Also check the migration"
+r5dctl session stop <session-id>
+
+r5dctl -p <project> merge fix/tests
+r5dctl -p <project> merge --worker <label> --create-conflict-worktree fix/tests
+r5dctl -p <project> merge --worker <label> --launch-conflict-resolution-agent fix/tests
+r5dctl -p <project> merge finish --worker <label> conflicts/fix-tests --summary "Resolved the conflicts"
 
 r5dctl -p <project> -b <branch> shell
 r5dctl -p <project> -b <branch> shell -c "bun test"
@@ -99,7 +104,11 @@ r5dctl k8s usage --window 7d
 r5dctl k8s usage --workload default/api --window 7d --json
 ```
 
-Branch agents are independent sessions on automatically created branches. `agent start` requires an explicit worker and `--source worktree:<branch>`; it never infers either from the local directory. The source is the named branch worktree, including its committed and uncommitted files. Starting returns after that worktree has been copied into the new branch worktree and queued; execution continues asynchronously. Follow-up, merge, and resolver commands must name the session's bound worker; they do not move work between workers implicitly. A prompt response reports whether it was `queued` into an active generation or `started` as a new generation. Use `agent status` to inspect progress, then `agent merge` after the agent reaches a terminal state. A conflicting merge starts a resolver session; stop that resolver for manual takeover and use `agent finish-merge` after resolving and reviewing its worktree.
+`session start` creates an ordinary agent-mode chat on an explicitly selected existing worktree, or creates a named worktree from an explicit `worktree:<branch>` source. It requires project, worker, model, and prompt and never infers them from the current shell. Starts and prompts return after durable enqueue while execution continues asynchronously. Task specialization belongs in the prompt; there are no predefined debug, explore, research, or test agents.
+
+Add `-f`/`--follow`/`--watch` to `session start` to attach after enqueue, or to `conversation` to print the current transcript and follow new output. Assistant text is written to stdout and lifecycle/tool progress to stderr; `--tools` includes tool calls and results. With global `--json`, follow mode emits one JSON event per line. Ctrl-C only detaches and never stops the session. The CLI reconnects transiently interrupted event streams and resynchronizes committed conversation revisions without repeating assistant text.
+
+`merge` merges a managed source worktree into its recorded parent. By default conflicts are reported without creating more work. `--create-conflict-worktree` prepares a manual conflict worktree, while `--launch-conflict-resolution-agent` starts the dedicated merge-conflict resolver; those strategies are mutually exclusive. A worker-bound shell credential supplies its own worker automatically; otherwise pass `--worker`. Finish a reviewed manual resolution with `merge finish`.
 
 `shell` connects to the same live worker PTY as the web Shell tab. Without `-c` it attaches the local terminal interactively. With `-c`/`--command`, it runs the supplied shell expression, streams combined PTY output, and exits with the remote command's status. Because command output uses a PTY, stdout and stderr are combined and programs may emit colors or other terminal control sequences.
 
@@ -120,7 +129,7 @@ Conversation output is human-readable by default and excludes both the system pr
 
 When available, conversation rendering uses the newest complete persisted model-request snapshot on the active conversation branch, so its mode, tier, model, thinking mode, tools, and messages reflect the request that actually ran. Legacy or empty sessions without snapshots fall back to reconstruction from the latest conversation context.
 
-`conversation overview` is a deterministic active-branch projection for continuing work in another session. It keeps user messages, injected context, assistant thinking/commentary/final responses, and user decisions, while replacing each turn's tool batches with a stable work ID and numbered call ranges. Adjacent tool batches with no visible content between them are coalesced into one range. Use `conversation inspect-work` with that session and work ID to inspect the omitted calls. Inspection is compact by default; `--summary` adds bounded targets/outcomes and `--full` renders persisted inputs and results with the normal tool renderers. The explicit `--compact`, `--summary`, and `--full` flags are mutually exclusive. Compact and summary output are designed to be narrowed with `grep`, `head`, `tail`, `sed`, or `cat -n`.
+`conversation overview` is a deterministic active-branch projection for recovering earlier work after a fresh-context boundary. It keeps user messages, injected context, assistant thinking/commentary/final responses, and user decisions, while replacing each turn's tool batches with a stable work ID and numbered call ranges. Adjacent tool batches with no visible content between them are coalesced into one range. Use `conversation inspect-work` with that session and work ID to inspect the omitted calls. Inspection is compact by default; `--summary` adds bounded targets/outcomes and `--full` renders persisted inputs and results with the normal tool renderers. The explicit `--compact`, `--summary`, and `--full` flags are mutually exclusive. Compact and summary output are designed to be narrowed with `grep`, `head`, `tail`, `sed`, or `cat -n`.
 
 `conversation inspect-node` reads one exact persisted conversation node as formatted JSON. Its header includes the previous node, every direct next node, the next node on the active branch, whether the selected node is active, and the containing `work_...` ID when one is available. This allows callers that start with only a copied chat node ID to traverse nearby nodes or zoom out with `conversation inspect-work`.