CB-622: rename bridge_* tools to fleet_* in scripts, e2e tests and config; mount name bridged -> fleetd
CI / build (pull_request) Successful in 58s
CI / contract (pull_request) Successful in 1m9s

This commit is contained in:
Dai Ha
2026-08-22 21:49:15 +02:00
parent 5cabd09705
commit 03473a286b
9 changed files with 68 additions and 68 deletions
+18 -18
View File
@@ -1,16 +1,16 @@
#!/usr/bin/env python3
"""Live bridge_ask test — the REVERSE rendezvous (CB-205), watched end to end.
"""Live fleet_ask test — the REVERSE rendezvous (CB-205), watched end to end.
Every other harness drives the forward path: primary `bridge_send` → worker `bridge_reply`.
Every other harness drives the forward path: primary `fleet_send` → worker `fleet_reply`.
This drives the one that runs the other way. A worker is told to pause its delegated turn,
ask the primary a question via `bridge_ask`, and only finish once it has the answer — so the
ask the primary a question via `fleet_ask`, and only finish once it has the answer — so the
turn round-trips primary→worker→primary→worker inside a SINGLE delegation.
The mechanics that only this path exercises:
• a worker's mid-turn question surfacing on the primary's *own* blocked send (Outcome.QUESTION),
• the `turnId` correlation that lets the primary answer the exact paused turn,
• the answer resuming that same turn and the worker's final `bridge_reply` landing on the
• the answer resuming that same turn and the worker's final `fleet_reply` landing on the
re-opened forward waiter (never a stale or cross-wired one).
It is two blocking REST calls, no polling:
@@ -57,14 +57,14 @@ ANSWER_COLOR = "blue"
# A task that CANNOT be completed without asking: the worker is not told which color to choose,
# only that the primary will name one when asked. So a correct final reply is only reachable by
# actually calling bridge_ask and using the answer.
# actually calling fleet_ask and using the answer.
TASK_PROMPT = (
"You are a bridge worker in a quick coordination game. You do NOT know which color to pick — "
"only the primary does. Do exactly this, in order:\n"
"1. Call the `bridge_ask` tool with EXACTLY this question: \"PICK A COLOR: red or blue?\"\n"
"1. Call the `fleet_ask` tool with EXACTLY this question: \"PICK A COLOR: red or blue?\"\n"
"2. The primary will answer with one color word. Take that color and uppercase it.\n"
"3. Call `bridge_reply` with EXACTLY one line: CHOSEN=<COLOR> (e.g. CHOSEN=GREEN if told green).\n"
"Do not guess a color. Do not call bridge_reply before bridge_ask has returned an answer. "
"3. Call `fleet_reply` with EXACTLY one line: CHOSEN=<COLOR> (e.g. CHOSEN=GREEN if told green).\n"
"Do not guess a color. Do not call fleet_reply before fleet_ask has returned an answer. "
"Do nothing else — no file reads, no other tools."
)
@@ -134,7 +134,7 @@ def run(base, profile, repo, send_timeout, answer_timeout):
rec.update(tid=tid, pane=pane, spawned=True)
await_ready(base, tid)
# 1) Delegate the ask-forcing task. This blocks until the worker calls bridge_ask, at which
# 1) Delegate the ask-forcing task. This blocks until the worker calls fleet_ask, at which
# point our own send unblocks carrying the question and the turnId to answer on.
print(f"[{now()}] delegating task (blocks until the worker asks; up to {send_timeout}s)…")
t0 = time.time()
@@ -159,7 +159,7 @@ def run(base, profile, repo, send_timeout, answer_timeout):
rec.update(phase="no_turnid", detail="question surfaced without a turnId to answer on")
return rec
# 2) Answer on that exact turn. This blocks again until the resumed worker calls bridge_reply.
# 2) Answer on that exact turn. This blocks again until the resumed worker calls fleet_reply.
print(f"[{now()}] answering '{ANSWER_COLOR}' on turn {rec['turnId']} (blocks until reply; up to {answer_timeout}s)…")
t1 = time.time()
rec["phase"] = "awaiting_reply"
@@ -188,7 +188,7 @@ def run(base, profile, repo, send_timeout, answer_timeout):
def grade(rec):
"""PASS only if the worker asked, the turn resumed, and the reply reflects the answer."""
if rec["phase"] == "no_question":
return "NO_ASK", "the worker finished/stalled without ever calling bridge_ask"
return "NO_ASK", "the worker finished/stalled without ever calling fleet_ask"
if rec["phase"] in ("send_error", "answer_error", "spawn"):
return "ERROR", rec.get("detail") or "transport error before the round-trip completed"
if rec["phase"] == "no_turnid":
@@ -203,7 +203,7 @@ def grade(rec):
return "OK", "asked, resumed the same turn, and the reply reflected the primary's answer"
if reflected:
return "DEGRADED", f"reply reflected the answer but resolved via {rec['replySource']} " \
"(worker did not call bridge_reply cleanly)"
"(worker did not call fleet_reply cleanly)"
return "WRONG_ANSWER", f"the worker replied but did not reflect '{ANSWER_COLOR}' — " \
f"the answer may not have reached the resumed turn: {rec['reply']!r}"
return "WEDGE", f"unexpected terminal phase {rec['phase']}: {rec.get('detail')}"
@@ -213,16 +213,16 @@ def write_transcript(out_dir, rec, meta):
path = out_dir / "bridge_ask_transcript.md"
g, note = grade(rec)
with path.open("w") as f:
f.write(f"# Live bridge_ask — reverse rendezvous — {datetime.now():%Y-%m-%d %H:%M}\n\n")
f.write(f"# Live fleet_ask — reverse rendezvous — {datetime.now():%Y-%m-%d %H:%M}\n\n")
f.write(f"One worker paused its delegated turn to ask the primary, then resumed with the "
f"answer (profile `{meta['profile']}`). Result: **`{g}`**.\n\n")
f.write("## Round-trip\n\n")
f.write(f"1. **primary → worker** (delegation): the ask-forcing task.\n")
f.write(f"2. **worker → primary** (`bridge_ask`, {rec.get('ask_latency')}s): "
f.write(f"2. **worker → primary** (`fleet_ask`, {rec.get('ask_latency')}s): "
f"{rec.get('question')!r} — surfaced on the primary's blocked send as a "
f"`question` with `turnId={rec.get('turnId')}`.\n")
f.write(f"3. **primary → worker** (answer on that turn): `{ANSWER_COLOR}`.\n")
f.write(f"4. **worker → primary** (`bridge_reply`, {rec.get('answer_latency')}s, "
f.write(f"4. **worker → primary** (`fleet_reply`, {rec.get('answer_latency')}s, "
f"source={rec.get('replySource')}): {rec.get('reply')!r}\n\n")
f.write(f"> **{g}:** {note}\n")
if rec.get("detail"):
@@ -231,7 +231,7 @@ def write_transcript(out_dir, rec, meta):
def main():
ap = argparse.ArgumentParser(description="Live bridge_ask reverse-rendezvous test (CB-205)")
ap = argparse.ArgumentParser(description="Live fleet_ask reverse-rendezvous test (CB-205)")
ap.add_argument("--base", default="http://127.0.0.1:8765")
ap.add_argument("--profile", default=None)
ap.add_argument("--repo", default=str(REPO_ROOT))
@@ -241,7 +241,7 @@ def main():
ap.add_argument("--keep-worker", action="store_true")
args = ap.parse_args()
print(f"[{now()}] live bridge_ask: 1 primary, 1 worker "
print(f"[{now()}] live fleet_ask: 1 primary, 1 worker "
f"(profile={args.profile or 'default'}, repo={args.repo})\n")
rec = {"spawned": False, "pane": None}
@@ -262,7 +262,7 @@ def main():
print()
print("=" * 72)
print("LIVE bridge_ask SUMMARY — reverse rendezvous (CB-205)")
print("LIVE fleet_ask SUMMARY — reverse rendezvous (CB-205)")
print(f" asked: {rec.get('question')!r} (turnId={rec.get('turnId')}, {rec.get('ask_latency')}s)")
print(f" answered: {ANSWER_COLOR!r}")
print(f" replied: {rec.get('reply')!r} (source={rec.get('replySource')}, {rec.get('answer_latency')}s)")
+7 -7
View File
@@ -24,7 +24,7 @@ Usage:
--turn-timeout per-turn max wait, seconds (default 150)
--keep-worker do not stop the worker at the end
Exit code: 0 if every turn in the window resolved via a clean bridge_reply with no channel
Exit code: 0 if every turn in the window resolved via a clean fleet_reply with no channel
break; 1 otherwise. A live per-turn log streams to stdout so the run can be watched.
"""
import argparse
@@ -47,12 +47,12 @@ STEPS = [7, 3, 11, 5, 9, 4, 13, 6, 8, 2]
RULES = (
"Let's play a running-total game across several messages. The total starts at 0. "
"In each message I'll tell you to add a number; keep the running total yourself and "
"reply via bridge_reply with ONLY the current total as a plain integer — no words, no "
"reply via fleet_reply with ONLY the current total as a plain integer — no words, no "
"punctuation, just the number. Do not restate the arithmetic. First move: add {step}."
)
NEXT = ("Add {step}. Reply via bridge_reply with only the new running total.")
NEXT = ("Add {step}. Reply via fleet_reply with only the new running total.")
REANCHOR = ("Let's re-sync — the running total is {total}. Now add {step}. Reply via "
"bridge_reply with only the new running total.")
"fleet_reply with only the new running total.")
def parse_int(reply):
@@ -142,15 +142,15 @@ def main():
print("=" * 72)
print(f"SUSTAINED CONVERSATION SUMMARY — 1 primary <-> 1 worker over {dur}s (~{dur/60:.1f} min)")
print(f" turns: {turns}")
print(f" clean bridge_reply exchanges: {oks + drifts}/{turns} (channel breaks: {breaks})")
print(f" clean fleet_reply exchanges: {oks + drifts}/{turns} (channel breaks: {breaks})")
print(f" arithmetic correct (continuity held): {oks}/{turns} (drifts: {drifts})")
print(f" latency: avg {avg}s over {turns} turns")
ok = breaks == 0 and turns >= 2
if ok and drifts == 0:
print(" RESULT: PASS — every turn resolved via bridge_reply and the worker held the "
print(" RESULT: PASS — every turn resolved via fleet_reply and the worker held the "
"running total across the whole window.")
elif ok:
print(f" RESULT: PASS (channel) — every turn resolved via bridge_reply for the full "
print(f" RESULT: PASS (channel) — every turn resolved via fleet_reply for the full "
f"window; {drifts} arithmetic drift(s) (worker recovered after re-anchor).")
else:
print(" RESULT: FAIL — the channel broke on at least one turn (see CHANNEL BREAK above).")
+4 -4
View File
@@ -4,7 +4,7 @@ the running `bridged` daemon, fully captured, with automatic gap analysis.
This is the repeatable form of the ad-hoc channel test that surfaced the CB-115 gaps
(herdr `unknown` misclassification, dirty completion scrape, workers not calling
bridge_reply). It drives a real off-subscription worker over the live gateway exactly
fleet_reply). It drives a real off-subscription worker over the live gateway exactly
as a primary Opus session would (async fire-and-poll), records every turn, and grades
the channel.
@@ -130,9 +130,9 @@ def grade(rec):
phase, source, reply = rec["phase"], rec["source"], rec["reply"]
has_reply = bool(reply and reply.strip())
if phase == "done" and source == "reply" and has_reply:
return "OK", "clean explicit bridge_reply"
return "OK", "clean explicit fleet_reply"
if phase == "done" and has_reply:
return "DEGRADED", f"resolved via {source} (worker did not call bridge_reply)"
return "DEGRADED", f"resolved via {source} (worker did not call fleet_reply)"
if phase == "done" and not has_reply:
return "EMPTY", "turn completed but reply was empty"
if phase == "failed":
@@ -206,7 +206,7 @@ def main():
ok = all(g in ("OK", "DEGRADED") for g in grades)
reply_clean = all(g == "OK" for g in grades)
if reply_clean:
print(" RESULT: PASS — every turn delivered and got a clean bridge_reply.")
print(" RESULT: PASS — every turn delivered and got a clean fleet_reply.")
elif ok:
print(" RESULT: PASS (with notes) — every turn delivered & replied, but some via fallback.")
else:
+4 -4
View File
@@ -12,7 +12,7 @@ and collects every reply concurrently. That stresses what a single worker never
• reply routing under concurrency (worker A's answer must never resolve worker B's send),
and, as the payload, whether a fleet of off-subscription workers can actually surface
real issues in the repo and report them back structurally via bridge_reply.
real issues in the repo and report them back structurally via fleet_reply.
It talks ONLY to the bridge's REST face on loopback — it never sets ANTHROPIC_BASE_URL
and never touches herdr directly, so it is subscription-safe by construction.
@@ -64,7 +64,7 @@ PROMPT_TMPL = (
"You are one of several issue-hunting workers in the claude-bridge repo (it is your "
"current working directory). Your assignment: inspect the file `{target}` and find the "
"SINGLE most important real bug, correctness gap, or risk in it. Read the file before "
"answering. Reply via bridge_reply with EXACTLY these four lines:\n"
"answering. Reply via fleet_reply with EXACTLY these four lines:\n"
"1. {target}:<line>\n"
"2. issue: <one sentence>\n"
"3. fix: <one line>\n"
@@ -147,9 +147,9 @@ def grade(rec):
phase, source, reply = rec["phase"], rec["source"], rec["reply"]
has_reply = bool(reply and reply.strip())
if phase == "done" and source == "reply" and has_reply:
return "OK", "clean explicit bridge_reply"
return "OK", "clean explicit fleet_reply"
if phase == "done" and has_reply:
return "DEGRADED", f"resolved via {source} (worker did not call bridge_reply)"
return "DEGRADED", f"resolved via {source} (worker did not call fleet_reply)"
if phase == "done" and not has_reply:
return "EMPTY", "turn completed but reply was empty"
if phase == "failed":