Skip to content

A full-featured CRM built with React, shadcn/ui, and Supabase.

live progress

erwanMarmelab4ccdfd61afb4
diff --git a/.claude/agents/orchestrator.md b/.claude/agents/orchestrator.md
index 8a496174..f9b29afa 100644
--- a/.claude/agents/orchestrator.md
+++ b/.claude/agents/orchestrator.md
@@ -33,6 +33,7 @@ When your dispatch prompt carries `PERSONA: technical` (the `#technical-harness`
1. **Full technical register** — as stated in the User-facing-messaging bullet above.
2. **Raw reporting.** Your final report is not a summary; it is the mechanical truth. Include: each `TASK-XXX` and its status, the branch names (`session/<SESSION_SHORT_ID>` and the per-task branches), the commit SHAs, each reviewer verdict (`APPROVED` / `REJECTED: <feedback>`), and any ADR file paths the developer wrote. Do not soften or omit failures.
3. **Stop at the session branch — never auto-promote.** The session branch is your terminal point. Do **not** dispatch the Stage-B promotion into the base branch, and do **not** run the POST-DEV migration round (STATE PD-* / writing-migrations). Merge every ticket into `session/<SESSION_SHORT_ID>` (Stage A only) and stop. The developer reviews the session branch, promotes it, and generates/applies migrations themselves. Still run the `pending-deploys.mjs` detection for **information only**, and report "schema changes detected — you will need a migration on merge" when it is non-empty; never generate or apply the migration yourself.
+4. **Live progress log.** Your final report only reaches the developer when this long turn ends, so give them a live feed: append one timestamped line to `<session_dir>/harness-progress.log` at **every point where these instructions have you emit a progress line** — plan ready (ticket count), each ticket dispatched, each developer `DONE` (with `branch=`/`commit=`/`files=`), each reviewer verdict (`APPROVED` / `REJECTED: …`), each Stage-A merge, and the final stop. Append immediately after the event, before moving on, with `Bash("echo \"$(date -u +%H:%M:%S) <event>\" >> <session_dir>/harness-progress.log")` (substitute the real `<session_dir>` from your context). Overwrite nothing — append only. The developer runs `tail -f` on this file to watch the harness code in real time.
The main thread runs `/harness-diff` after you return, so end your report by naming the session branch it should diff.
diff --git a/CLAUDE.md b/CLAUDE.md
index 19717a84..1c3ed253 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -4,7 +4,7 @@
Code-change requests can be handled by the **agent harness**: a team of subagents (planner, developer, quality-reviewer, merger, documentator) that implements the change through a deterministic, foreground pipeline in git worktrees. **The harness is opt-in — it does NOT run by default.** By default the main thread implements the change itself, no agents.
-**Only when the user's request includes `#harness` or `#technical-harness` (or "use the agent team" / "with the harness") does the main (top-level) session dispatch the `orchestrator` agent and relay its result — never route or implement it yourself in that case.** Pass the `<session_dir>` value from your own context in the dispatch prompt (the orchestrator needs it to namespace worktrees and branches). **With `#technical-harness`**, also add a line `PERSONA: technical` to the dispatch prompt: it tells the orchestrator to use the full technical developer register (file paths, `TASK-XXX`, git terms, `database`/`migration`/`Supabase`), report the raw mechanical truth, and **stop at the session branch** (no promotion to the base branch, no deploy-time migration round). After that orchestrator returns, run `/harness-diff` to show the net diff of the session branch it stopped on. See the "Opting in" section below. **This directive is for the top-level session only: if you are a subagent (already inside the harness), ignore it — do your own job and never dispatch an orchestrator. A runtime hook (`block-nested-orchestrator`) enforces this.** The `orchestrator` owns all routing (classification SIMPLE vs COMPLEX, plus the SETUP / MEMORY / ROLLBACK-CONFLICT / RECOVERY operational intents, the dispatch templates, the wave + promotion mechanics, and the deploy-time migration round); it drives developer/reviewer/merger to a terminal point before returning. Each agent's last line is an output contract the others parse (`.claude/rules/agent-output-format.md`).
+**Only when the user's request includes `#harness` or `#technical-harness` (or "use the agent team" / "with the harness") does the main (top-level) session dispatch the `orchestrator` agent and relay its result — never route or implement it yourself in that case.** Pass the `<session_dir>` value from your own context in the dispatch prompt (the orchestrator needs it to namespace worktrees and branches). **With `#technical-harness`**, also add a line `PERSONA: technical` to the dispatch prompt: it tells the orchestrator to use the full technical developer register (file paths, `TASK-XXX`, git terms, `database`/`migration`/`Supabase`), report the raw mechanical truth, **stop at the session branch** (no promotion to the base branch, no deploy-time migration round), and append a live progress line per step to `<session_dir>/harness-progress.log`. **Before** you dispatch, print the watch command — `tail -f <session_dir>/harness-progress.log` (real `<session_dir>` substituted) — so the developer can follow along during the blocking run. After the orchestrator returns, run `/harness-diff` to show the net diff of the session branch it stopped on. See the "Opting in" section below. **This directive is for the top-level session only: if you are a subagent (already inside the harness), ignore it — do your own job and never dispatch an orchestrator. A runtime hook (`block-nested-orchestrator`) enforces this.** The `orchestrator` owns all routing (classification SIMPLE vs COMPLEX, plus the SETUP / MEMORY / ROLLBACK-CONFLICT / RECOVERY operational intents, the dispatch templates, the wave + promotion mechanics, and the deploy-time migration round); it drives developer/reviewer/merger to a terminal point before returning. Each agent's last line is an output contract the others parse (`.claude/rules/agent-output-format.md`).
**PD-ASK round-trip (migration confirmation).** The orchestrator ends its turn with a pending question — typically *"apply the database migration now?"* — and the task completes. Relay that question to the user (plain text or `AskUserQuestion`). **Do NOT resume the old orchestrator with `SendMessage` to relay their answer:** the runtime tags coordinator messages as carrying no user authority, so a relayed approval is ignored and the orchestrator loops re-asking forever. Instead, on the user's reply:
- **Approved** → dispatch a **fresh** `orchestrator` (a new `Agent` call) whose prompt begins with `<intent>apply-migration</intent>`, states the approval, and passes the same `<session_dir>`. It resumes the migration round from disk and applies it.
@@ -21,8 +21,9 @@ The harness is off by default; the main thread implements code changes itself. `
1. **Full technical register** — removes the plain-language filter that hides file paths, `TASK-XXX`, git terms, and words like `database`/`migration`/`Supabase`.
2. **Raw reporting** — the orchestrator reports the mechanical truth (per-ticket status, branch names, commit SHAs, reviewer verdicts, ADR paths), not a softened summary.
3. **Stops at the session branch** — the harness merges all work into `session/<id>` but does **not** promote to the base branch and does **not** run the deploy-time migration round. You review, promote, and generate/apply migrations yourself.
+4. **Live progress log** — the orchestrator appends each step (ticket dispatched, developer done, reviewer verdict, merge) to `<session_dir>/harness-progress.log` as it happens.
-After the orchestrator returns from a `#technical-harness` run, the main thread runs `/harness-diff` to show the net diff of the session branch it stopped on.
+Because the orchestrator runs in one long blocking turn (its final report only lands when it finishes), the main thread must, **before** dispatching a `#technical-harness` run, print the exact command to watch progress live — `tail -f <session_dir>/harness-progress.log` with the real `<session_dir>` substituted. After the orchestrator returns, the main thread runs `/harness-diff` to show the net diff of the session branch it stopped on.
## Agents