# Telegram progress presentation

Status: implemented and verified, resumed by the user with instructions to
complete, commit and push. The evidenced OpenCode compatibility failure is handled in
[the current repair order](WO-opencode-production-compatibility-20261012.md).

## Requested behavior

- Show the agent's intermediate explanations in public group chat as a compact
  sequence of short paragraphs describing what it is doing or has learned.
- Keep detailed activity behind a button that opens the activity view.
- Present tool calls and results in clean, separate wrapped code blocks using
  supported Telegram message formatting and controls.
- Replace the public numbered started/succeeded activity dump and its generic
  "Working"/"Work ended" panel with useful intermediate chat narration.
- Deliver the final answer separately, with completion wording derived from
  actual delivery state rather than an internal handler's acceptance.

## Implementation and verification

The runner emits finalized main-agent prose as `assistant_text` with source
`model_visible_text`; the terminal chat/voice path renders that visible text.
Telegram action runs previously kept it only as a final reply candidate. The
bridge now publishes prose accompanying a same-response nonterminal work tool
through its existing bound progress writer. Standalone explicit
`telegram_progress` remains available. Hidden reasoning, final-only drafts,
transport contracts and internal guidance do not become progress.

Keep the four latest distinct paragraphs in collapsed public/private summaries.
Activity opens the chronological details; public Summary returns to prose.
Admin calls/results use separate escaped HTML code blocks; public detail shows
safe tool names and phases without leaking private arguments or outputs.
Keep telemetry and adversarial diagnostics in private archives while filtering
ordinary sub-agent display callbacks.

Verify private/public scope, edit and
send limits, interruption/Stop, callback ownership, long tool-output handling,
and that diagnostics/adversarial guidance remain out of ordinary public chat.
Progress never settles work or substitutes for final provider acknowledgement.
Verification: 126 focused presentation/routing tests passed; 51 public/native
fallback/diagnostic tests and 60 private-native tests also passed. These delivery
tests use explicit mocked Telegram acknowledgements and do not claim real bot
messages. The actual listener is exercised in `telegram-runner-commentary.test.ts`.
The full workspace rebuild and package audit passed. Real inference acceptance,
including production streaming, is recorded under the inference repair order.
