feat: show structured turn activity

This commit is contained in:
Miguel Palhas
2026-09-06 16:50:46 +01:00
parent 4ce432c227
commit a1f3690aaf
12 changed files with 416 additions and 50 deletions
+10 -4
View File
@@ -113,7 +113,7 @@ crate.
| `ToolDiff` | The same tool-call machinery, when the tool's content includes a `Diff` block. | Same `tool:<tool_call_id>` identity as `ToolCall`; the *kind* flips between the two as the tool's own content changes, not the row. |
| `Approval` | A daemon-originated permission request (`RequestPermissionRequest`), serialized without its nonce. | `approval:<uuid>` — minted fresh per request, unrelated to the ACP request's own id. |
| `Plan` | A `plan` update — the agent's current step list. | The fixed id `"plan"`. Each new plan **replaces** the row wholesale; entries are not diffed against the previous plan. |
| `Notice` | The raw JSON of any `session/update` variant the ACP dependency already decodes but the projection does not special-case. | `notice:<seq>`. |
| `Notice` | The raw JSON of any `session/update` variant the ACP dependency already decodes but the projection does not special-case. Maestro also uses a tagged `maestroTurnMeta` notice as the durable footer for a completed, cancelled, or failed turn. | `notice:<seq>` for ACP updates; `turn_meta:<uuid>` for a turn footer. |
`Notice` covers known-but-unspecialized `SessionUpdate` variants: ones the
`agent-client-protocol` dependency's schema already deserializes (it
@@ -147,7 +147,10 @@ choices, not daemon ones.
TUI renderers can never disagree about it.
- Turn lifecycle: when a turn begins, and whether an ACP response, a cancel,
or a failure ends it (`TurnState.responding` / `.thinking` /
`.active_tool_calls` are derived, not renderer-computed).
`.active_tool_calls` / `.started_at` are derived, not renderer-computed).
Ending a turn appends a durable `maestroTurnMeta` footer with its elapsed
time, outcome, model, and context-window usage/delta. ACP does not expose
provider billing-token counts, so these are explicitly context tokens.
- Approval nonce minting, secrecy, and the single-active-approval rule (see
below) — a client never sees an ACP permission request before the daemon
has already turned it into an `Approval` row and a nonce.
@@ -177,7 +180,9 @@ choices, not daemon ones.
the caret. Completing a command replaces only that token. The client omits
those state-only notices, along with `session_info_update`, from the visible
transcript.
- How `responding` vs. `thinking` are distinguished visually, if at all.
- How live `responding`, `thinking`, tool activity, elapsed time, and context
usage are drawn. The web client keeps these in a compact strip above the
composer and renders each durable turn footer inline with the transcript.
- How the operator is asked to resolve an `Approval` row — the daemon only
exposes the three-way decision (`AllowOnce` / `AllowForSession` / `Deny`),
never the UI that solicits it.
@@ -209,7 +214,8 @@ every row, once appended, is only ever patched or left alone.
The event log's own line position is the cursor: 1-based, shared by ACP
notifications and daemon-generated rows alike (`sidecar.rs`'s
`PersistedEvent` envelope is what lets `User` and `Approval` rows share a cursor
sequence with raw ACP JSON without pretending to be ACP traffic). Two ways to
sequence with raw ACP JSON without pretending to be ACP traffic; the envelope
also carries durable `Turn` footers). Two ways to
read it:
- **`WS /api/structured/:id`** — on connect, sends a `TranscriptSnapshot` and