@event4u/agent-config 1.16.0 → 1.18.0

package/scripts/_phase2_shim_helper.py

@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+"""One-shot helper: add `superseded_by:` + `deprecated_in:` + warning
+banner to Phase 2 atomic-command shims.
+
+Idempotent — if a file already has `superseded_by:` set, it is skipped.
+"""
+from __future__ import annotations
+import sys
+from pathlib import Path
+
+# (file-stem, "<cluster> <sub>")  — "<cluster> --flag" for flag-based
+PHASE2_SHIMS: list[tuple[str, str]] = [
+    # chat-history cluster
+    ("chat-history-resume",     "chat-history resume"),
+    ("chat-history-clear",      "chat-history clear"),
+    ("chat-history-checkpoint", "chat-history checkpoint"),
+    # agents cluster
+    ("agents-audit",   "agents audit"),
+    ("agents-cleanup", "agents cleanup"),
+    ("agents-prepare", "agents prepare"),
+    # memory cluster
+    ("memory-add",     "memory add"),
+    ("memory-full",    "memory load"),
+    ("memory-promote", "memory promote"),
+    ("propose-memory", "memory propose"),
+    # roadmap cluster
+    ("roadmap-create",  "roadmap create"),
+    ("roadmap-execute", "roadmap execute"),
+    # module cluster
+    ("module-create",  "module create"),
+    ("module-explore", "module explore"),
+    # tests cluster
+    ("tests-create",  "tests create"),
+    ("tests-execute", "tests execute"),
+    # context cluster
+    ("context-create",   "context create"),
+    ("context-refactor", "context refactor"),
+    # override cluster
+    ("override-create", "override create"),
+    ("override-manage", "override manage"),
+    # copilot-agents cluster
+    ("copilot-agents-init",     "copilot-agents init"),
+    ("copilot-agents-optimize", "copilot-agents optimize"),
+    # judge cluster (do-and-judge / do-in-steps now sub-commands)
+    ("do-and-judge", "judge on-diff"),
+    ("do-in-steps",  "judge steps"),
+    # commit / create-pr — flag-based clusters
+    ("commit-in-chunks",     "commit --in-chunks"),
+    ("create-pr-description", "create-pr --description-only"),
+]
+
+DEPRECATED_IN = "1.17.0"
+COMMANDS_DIR = Path(".agent-src.uncompressed/commands")
+
+
+def patch_file(stem: str, target: str) -> str:
+    path = COMMANDS_DIR / f"{stem}.md"
+    if not path.exists():
+        return f"SKIP {stem}: not found"
+    text = path.read_text(encoding="utf-8")
+    if "superseded_by:" in text.split("---", 2)[1] if text.startswith("---") else False:
+        return f"SKIP {stem}: already shimmed"
+
+    if not text.startswith("---\n"):
+        return f"SKIP {stem}: no frontmatter"
+    end = text.find("\n---\n", 4)
+    if end == -1:
+        return f"SKIP {stem}: malformed frontmatter"
+    fm_block = text[4:end]
+    body = text[end + len("\n---\n"):]
+
+    if "superseded_by:" in fm_block:
+        return f"SKIP {stem}: already shimmed"
+
+    new_fm_lines = fm_block.rstrip("\n").splitlines()
+    new_fm_lines.append(f"superseded_by: {target}")
+    new_fm_lines.append(f'deprecated_in: "{DEPRECATED_IN}"')
+    new_fm = "\n".join(new_fm_lines)
+
+    is_flag = target.startswith(("commit ", "create-pr "))
+    if is_flag:
+        cluster_invocation = f"/{target}"
+    else:
+        cluster_invocation = f"/{target}"
+    banner = (
+        f"> ⚠️  /{stem} is deprecated; use {cluster_invocation} instead.\n"
+        f"> This shim is retained for one release cycle "
+        f"({DEPRECATED_IN} → next minor) and forwards to the same "
+        f"instructions below. See "
+        f"[`docs/contracts/command-clusters.md`]"
+        f"(../../docs/contracts/command-clusters.md).\n\n"
+    )
+
+    new_text = f"---\n{new_fm}\n---\n\n{banner}{body.lstrip(chr(10))}"
+    path.write_text(new_text, encoding="utf-8")
+    return f"OK   {stem} → {target}"
+
+
+def main() -> int:
+    results = []
+    for stem, target in PHASE2_SHIMS:
+        results.append(patch_file(stem, target))
+    for r in results:
+        print(r)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

package/scripts/agent-config

@@ -70,6 +70,12 @@ Commands:
                              Usage: chat-history:hook --platform <claude|augment|cursor|cline|windsurf|gemini>
   chat-history:checkpoint    Append a phase-boundary entry to .agent-chat-history
                              (CHECKPOINT fallback for platforms without native hooks)
+  roadmap-progress:hook      PostToolUse hook entry point (read JSON from stdin)
+                             Regenerates roadmaps-progress.md when a tool wrote under agents/roadmaps/
+  onboarding-gate:hook       Hook entry point (drains stdin)
+                             Writes .augment/state/onboarding-gate.json from .agent-settings.yml
+  context-hygiene:hook       PostToolUse hook entry point (read JSON from stdin)
+                             Maintains .augment/state/context-hygiene.json (turn count, loop, freshness)
   telemetry:record           Append one artefact-engagement event (default-off)
   telemetry:status           Print artefact-engagement telemetry status (read-only)
   telemetry:report           Aggregate the engagement log into a quartile report
@@ -316,6 +322,27 @@ cmd_chat_history_hook() {
   exec python3 "$script" hook-dispatch "$@"
 }
 
+cmd_roadmap_progress_hook() {
+  require_python3
+  local script
+  script="$(resolve_script "scripts/roadmap_progress_hook.py")" || return 1
+  exec python3 "$script" "$@"
+}
+
+cmd_onboarding_gate_hook() {
+  require_python3
+  local script
+  script="$(resolve_script "scripts/onboarding_gate_hook.py")" || return 1
+  exec python3 "$script" "$@"
+}
+
+cmd_context_hygiene_hook() {
+  require_python3
+  local script
+  script="$(resolve_script "scripts/context_hygiene_hook.py")" || return 1
+  exec python3 "$script" "$@"
+}
+
 cmd_chat_history_checkpoint() {
   require_python3
   local script
@@ -436,6 +463,9 @@ main() {
     refine-ticket:detect)    cmd_refine_ticket_detect "$@" ;;
     chat-history:hook)       cmd_chat_history_hook "$@" ;;
     chat-history:checkpoint) cmd_chat_history_checkpoint "$@" ;;
+    roadmap-progress:hook)   cmd_roadmap_progress_hook "$@" ;;
+    onboarding-gate:hook)    cmd_onboarding_gate_hook "$@" ;;
+    context-hygiene:hook)    cmd_context_hygiene_hook "$@" ;;
     telemetry:record)        cmd_telemetry_record "$@" ;;
     telemetry:status)        cmd_telemetry_status "$@" ;;
     telemetry:report)        cmd_telemetry_report "$@" ;;

package/scripts/ai_council/one_off_archive/2026-05/README.md

@@ -0,0 +1,45 @@
+# One-off archive — 2026-05
+
+> Archived per **Phase 0a.2** of `agents/roadmaps/road-to-rule-hardening.md`.
+> Each script here was a single-purpose AI-council probe or measurement
+> tied to a specific phase of `road-to-structural-optimization.md` (now
+> archived) or `road-to-rule-hardening.md`. The session output lives
+> under `agents/council-sessions/` (durable evidence) and the linter
+> `scripts/check_one_off_location.py` enforces that no new
+> `_one_off_*.py` lands outside this folder.
+
+## Lifecycle rule (uniform — Phase 0.2 of context-layer-maturity)
+
+> A one-off is **archived**, never deleted. The session manifest under
+> `agents/council-sessions/` is the audit trail; the script itself is
+> kept here so a future contributor can re-read intent, re-run a probe
+> on a future branch, or extract a reusable helper.
+
+## Inventory
+
+| Script | Roadmap / Phase | Council session id |
+|---|---|---|
+| `_one_off_2a4_acceptance.py` | structural-optimization 2A.4 | various 2A sessions |
+| `_one_off_context_layer_v1_estimate.py` | context-layer-maturity v1 cost estimate | `2026-05-03T17-56-21Z` |
+| `_one_off_context_layer_v1_review.py` | context-layer-maturity v1 review | `2026-05-03T17-56-21Z` |
+| `_one_off_followups_review.py` | road-to-1-16-followups review | session under `agents/council-sessions/` |
+| `_one_off_nondestructive_inline_audit.py` | non-destructive-by-default audit | session under `agents/council-sessions/` |
+| `_one_off_phase4_dispatch_latency.py` | structural-optimization 4.3.1 cluster latency benchmark | local benchmark, no council |
+| `_one_off_phase6_trigger_jaccard.py` | structural-optimization Phase 6 trigger overlap | local measurement |
+| `_one_off_phase_2a_budget_rebalance.py` | structural-optimization 2A budget rebalance | `2026-05-03T*` |
+| `_one_off_phase_2a_post_revert.py` | structural-optimization 2A post-revert | `2026-05-03T*` |
+| `_one_off_rebalancing_audit.py` | rebalancing roadmap audit | session under `agents/council-sessions/` |
+| `_one_off_roundtrip.py` | council client roundtrip smoke test | local smoke test |
+| `_one_off_rule_hardening_v1.py` | rule-hardening v1 review | `2026-05-03T19-16-25Z` |
+| `_one_off_structural_open_questions.py` | structural-optimization open questions | session under `agents/council-sessions/` |
+| `_one_off_structural_optimization.py` | structural-optimization initial review | session under `agents/council-sessions/` |
+| `_one_off_structural_v3_gaps.py` | structural-optimization v3 gap audit | session under `agents/council-sessions/` |
+| `_one_off_structural_v3_review.py` | structural-optimization v3 review | session under `agents/council-sessions/` |
+
+## Re-running an archived script
+
+Imports may have shifted (e.g. `scripts.ai_council.*`). If a probe
+needs to be re-run against a current branch, copy it back to its
+original location, fix imports, run, then move the working copy
+back here. Do **not** edit in place — keep the archive immutable
+beyond cosmetic README updates.

package/scripts/ai_council/one_off_archive/2026-05/_one_off_2a4_acceptance.py

@@ -0,0 +1,208 @@
+"""Council acceptance review of Phase 0.4 2A.4 worked example.
+
+Purpose: Phase 0.4.3 of road-to-structural-optimization.md requires a
+council acceptance pass on the 2A.4 obligation-keyword-diff contract
+before Phase 2A may begin. The artefact lives at
+`agents/roadmaps/structural-optimization-2A4-example.md` plus two
+sandbox files. Status will move from `draft` to `locked` only on
+ACCEPT or ACCEPT_WITH_REVISIONS where revisions are minor.
+
+Invocation:
+    .venv/bin/python -m scripts.ai_council._one_off_2a4_acceptance
+"""
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+from scripts.ai_council.bundler import bundle_files
+from scripts.ai_council.clients import (
+    AnthropicClient,
+    OpenAIClient,
+    load_anthropic_key,
+    load_openai_key,
+)
+from scripts.ai_council.orchestrator import (
+    CostBudget,
+    CouncilQuestion,
+    consult,
+    estimate,
+)
+from scripts.ai_council.pricing import estimate_cost, load_prices
+from scripts.ai_council.project_context import detect_project_context
+from scripts.ai_council.session import SessionManifest, save as save_session
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+ARTEFACTS = [
+    REPO_ROOT / "agents/roadmaps/structural-optimization-2A4-example.md",
+    REPO_ROOT / "agents/roadmaps/examples/2A4-direct-answers/direct-answers.slim.md",
+    REPO_ROOT / "agents/roadmaps/examples/2A4-direct-answers/direct-answers-mechanics.md",
+]
+
+ORIGINAL_ASK = (
+    "Phase 0.4 of road-to-structural-optimization v3.1 dry-runs the "
+    "2A.4 obligation-keyword-diff contract on `direct-answers.md` to "
+    "lock the contract before Phase 2A begins. The artefact and two "
+    "sandbox files (slim rule + extracted mechanics) are presented. "
+    "Council task: ACCEPT / ACCEPT_WITH_REVISIONS / REJECT the "
+    "contract for use across the remaining 8 always-rules in Phase 2A."
+)
+
+REVIEW_PROMPT = """\
+# Council Acceptance Review — 2A.4 Worked Example
+
+## Context
+
+The host agent ran Phase 0.4 of `road-to-structural-optimization` v3.1: \
+took one always-rule (`direct-answers.md`, smallest of the top-3), split \
+it into a slim RULE+LOGIC half and a MECHANICS context, then applied \
+the 2A.4 obligation-keyword diff contract. The artefact is the report \
+of that dry-run; the two sandbox files are the actual produced split.
+
+You are not asked to re-litigate the v3.1 roadmap or the choice of \
+`direct-answers.md` — both were settled in earlier rounds. Verdict \
+solely concerns whether the **contract** (keyword × counts × \
+accept-rationale table, plus its tie-break rules) is now ready to be \
+applied to the remaining 8 always-rules in Phase 2A.
+
+## Output Contract (STRICT)
+
+Produce exactly these blocks in order. Be decisive — total response \
+budget <= 1200 words.
+
+```
+### Contract correctness
+
+**Verdict:** <ACCEPT | ACCEPT_WITH_REVISIONS | REJECT>
+**Keyword extraction completeness:** <COMPLETE | PARTIAL — list missing>
+**Tie-break rules sufficient:** <YES | NO — name the gap>
+**Required revisions (numbered, 1-3 max, only on ACCEPT_WITH_REVISIONS):**
+  1. <one sentence — smallest change>
+  2. <...>
+  3. <...>
+```
+
+```
+### Sandbox split quality
+
+**Slim file preserves all RULE+LOGIC obligations:** <YES | NO — list lost>
+**Mechanics file holds only mechanics+examples:** <YES | NO — list misplaced>
+**Round-trip: rule_slim + load_context(mechanics) == original behaviour:**
+  <YES | NO — name the divergence>
+```
+
+```
+### Generalisability to remaining 8 rules
+
+**Contract scales without per-rule tuning:** <YES | NO — name failure mode>
+**Single biggest risk on the next rule (likely `non-destructive-by-default`):**
+  <one sentence>
+```
+
+```
+### Final verdict
+
+**Lockable as-is for Phase 2A?** <YES | NO>
+**If NO, single blocking change required:** <one sentence>
+```
+
+Verdict definitions:
+- **ACCEPT** — contract ships unchanged; status moves to locked.
+- **ACCEPT_WITH_REVISIONS** — locks after the 1-3 listed revisions land.
+- **REJECT** — contract is structurally wrong; describe the fault.
+
+The three artefacts follow this prompt verbatim.
+"""
+
+
+def main() -> int:
+    anthropic = AnthropicClient(api_key=load_anthropic_key(), model="claude-sonnet-4-5")
+    openai = OpenAIClient(api_key=load_openai_key(), model="gpt-4o")
+    members = [anthropic, openai]
+
+    context = bundle_files(ARTEFACTS)
+    project = detect_project_context(REPO_ROOT)
+    table = load_prices()
+
+    user_prompt = REVIEW_PROMPT + "\n\n---\n\n" + context.text
+
+    question = CouncilQuestion(
+        mode="files",
+        user_prompt=user_prompt,
+        max_tokens=3072,
+    )
+
+    estimates = estimate(
+        question, members, table, project=project, original_ask=ORIGINAL_ASK,
+    )
+    print("=== ESTIMATE (single round, max tokens) ===")
+    total_est = 0.0
+    for c, e in zip(members, estimates):
+        print(f"  {c.name}/{c.model}: ~{e.input_tokens} in + {e.output_tokens} out = ${e.total_usd:.4f}")
+        total_est += e.total_usd
+    print(f"  TOTAL per round (max): ${total_est:.4f}")
+    print()
+
+    budget = CostBudget(
+        max_input_tokens=200_000,
+        max_output_tokens=80_000,
+        max_calls=20,
+        max_total_usd=2.50,
+    )
+
+    rounds_collected: list[list] = []
+
+    def _on_round_complete(round_idx: int, round_responses) -> None:
+        rounds_collected.append(list(round_responses))
+        print(f"=== ROUND {round_idx + 1} COMPLETE ===")
+        for r in round_responses:
+            if r.error:
+                print(f"  [error] {r.provider}/{r.model}: {r.error}")
+                continue
+            actual = estimate_cost(r.provider, r.model, r.input_tokens, r.output_tokens, table)
+            print(f"  [done] {r.provider}/{r.model}: {r.input_tokens} in / "
+                  f"{r.output_tokens} out · {r.latency_ms} ms · ${actual.total_usd:.4f}")
+        print()
+
+    print("=== CONSULT (1 round, 2A.4 acceptance review) ===")
+    consult(
+        members, question, budget,
+        rounds=1,
+        on_round_complete=_on_round_complete,
+        table=table, project=project, original_ask=ORIGINAL_ASK,
+    )
+
+    if not rounds_collected:
+        print("[error] no rounds completed", file=sys.stderr)
+        return 1
+
+    actual_total = 0.0
+    for round_responses in rounds_collected:
+        for r in round_responses:
+            if r.error:
+                continue
+            actual = estimate_cost(r.provider, r.model, r.input_tokens, r.output_tokens, table)
+            actual_total += actual.total_usd
+    print(f"=== TOTAL ACTUAL: ${actual_total:.4f} ===")
+
+    final_round = rounds_collected[-1]
+    if not [r for r in final_round if not r.error]:
+        return 1
+
+    manifest = SessionManifest(
+        mode="files",
+        artefact="agents/roadmaps/structural-optimization-2A4-example.md",
+        original_ask=ORIGINAL_ASK,
+        members=[f"{r.provider}/{r.model}" for r in final_round],
+        rounds=len(rounds_collected),
+        cost_usd_estimated=total_est,
+        cost_usd_actual=actual_total,
+        extra={"purpose": "Council acceptance review of Phase 0.4 2A.4 worked example"},
+    )
+    session_dir = save_session(manifest=manifest, responses=rounds_collected)
+    print(f"[saved] {session_dir.relative_to(REPO_ROOT)}/")
+    return 1 if any(r.error for round_r in rounds_collected for r in round_r) else 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/scripts/ai_council/one_off_archive/2026-05/_one_off_budget_v2_audit.py

@@ -0,0 +1,206 @@
+"""Council audit of Budget-v2 result (Phase 4.5 of road-to-context-layer-maturity).
+
+Phase 4 of road-to-context-layer-maturity selected two 4d-trim paths
+(`direct-answers`, `no-cheap-questions`) from a fixed option set
+documented in agents/contexts/budget-v2-matrix.md and shipped them.
+Exit-gate actuals (run 2026-05-04): total 44,928 / 49,000 chars
+(91.7 %, 4,072 chars headroom) — ≥ 4,000 headroom goal hit. Top-3
+sum unchanged. Safety-floor rules untouched.
+
+Phase 4.5 requires a council audit before archival: confirm the
+trim choices were sound, no semantic drift introduced, no better
+path missed inside the Phase 4 inputs gate.
+
+Invocation:
+    .venv/bin/python -m scripts.ai_council.one_off_archive.2026-05._one_off_budget_v2_audit
+"""
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+from scripts.ai_council.bundler import bundle_files
+from scripts.ai_council.clients import (
+    AnthropicClient,
+    OpenAIClient,
+    load_anthropic_key,
+    load_openai_key,
+)
+from scripts.ai_council.orchestrator import (
+    CostBudget,
+    CouncilQuestion,
+    consult,
+    estimate,
+)
+from scripts.ai_council.pricing import estimate_cost, load_prices
+from scripts.ai_council.project_context import detect_project_context
+from scripts.ai_council.session import SessionManifest, save as save_session
+
+REPO_ROOT = Path(__file__).resolve().parents[4]
+ARTEFACTS = [
+    REPO_ROOT / "docs/contracts/load-context-budget-model.md",
+    REPO_ROOT / "agents/contexts/budget-v2-matrix.md",
+    REPO_ROOT / ".agent-src.uncompressed/rules/direct-answers.md",
+    REPO_ROOT / ".agent-src.uncompressed/rules/no-cheap-questions.md",
+]
+
+ORIGINAL_ASK = (
+    "Phase 4 of road-to-context-layer-maturity trimmed two always-rules "
+    "(direct-answers, no-cheap-questions) under the locked Model (b) "
+    "literal budget contract, hitting the ≥ 4,000-chars headroom goal "
+    "(actual: 4,072). Council task: audit the trim choices for "
+    "soundness and semantic drift before roadmap archival."
+)
+
+REVIEW_PROMPT = """\
+# Council Audit — Budget-v2 Trim Result (Phase 4.5)
+
+## Context
+
+Phase 4 selected two 4d-trim paths from a fixed option set documented
+in `budget-v2-matrix.md`. The matrix evaluated 4a (demote→auto), 4b
+(merge), 4c (shared-context, locked at 3a Model (b) literal — no-op),
+and 4d (compress prose) for every touchable always-rule. Safety-floor
+rules (scope-control, non-destructive-by-default, commit-policy,
+agent-authority) were untouchable. Outcome-untested rules were
+restricted to 4d only per the Phase 4.0 inputs gate.
+
+## Selected paths and result
+
+- **4d on `direct-answers`** — emoji-scope subsection trimmed,
+  failure-mode collapsed to pointer. Δ ext: 4,098 → 3,987 (−111).
+- **4d on `no-cheap-questions`** — "What counts as cheap" subsection
+  collapsed to pointer at `asking-and-brevity-examples.md`. Δ ext:
+  4,257 → 3,933 (−324).
+
+Combined: −435 chars · headroom 3,637 → 4,072 (+435) · top-3 sum
+unchanged · safety-floor rules untouched.
+
+## Audit questions (please address each)
+
+1. **Trim soundness** — do the surviving Iron Laws in both rules still
+   carry the rule's purpose, or did the prose trim sacrifice precision?
+   Cite the specific subsection if you find drift.
+
+2. **Path selection** — was 4d the right choice for these two rules
+   given the matrix? Or should one of the deferred paths (4a, 4b)
+   have been picked despite the matrix verdict?
+
+3. **Missed leverage** — inside the Phase 4 inputs gate (4d only on
+   outcome-untested rules; safety-floor untouchable), is there a
+   higher-leverage 4d target the matrix missed?
+
+4. **Headroom durability** — 4,072 chars is +72 over the 4,000 goal.
+   Is this margin stable against expected near-term rule edits, or
+   should Phase 5 be tightened to defend it?
+
+## Output Contract (STRICT)
+
+```
+### Verdict
+**Trim choices sound:** <YES — archive · NO — escalate>
+**One-sentence rationale:** <≤ 30 words>
+```
+
+```
+### Per-question findings (1–4 above)
+  1. <≤ 2 sentences>
+  2. <≤ 2 sentences>
+  3. <≤ 2 sentences>
+  4. <≤ 2 sentences>
+```
+
+```
+### Risk note
+**Single biggest residual risk:** <one sentence>
+**Mitigation (if any):** <one sentence or NONE>
+```
+
+Be decisive — total response ≤ 800 words. Artefacts follow verbatim.
+"""
+
+
+def main() -> int:
+    anthropic = AnthropicClient(api_key=load_anthropic_key(), model="claude-sonnet-4-5")
+    openai = OpenAIClient(api_key=load_openai_key(), model="gpt-4o")
+    members = [anthropic, openai]
+
+    context = bundle_files(ARTEFACTS)
+    project = detect_project_context(REPO_ROOT)
+    table = load_prices()
+
+    user_prompt = REVIEW_PROMPT + "\n\n---\n\n" + context.text
+
+    question = CouncilQuestion(mode="files", user_prompt=user_prompt, max_tokens=2048)
+
+    estimates = estimate(question, members, table, project=project, original_ask=ORIGINAL_ASK)
+    print("=== ESTIMATE (single round) ===")
+    total_est = 0.0
+    for c, e in zip(members, estimates):
+        print(f"  {c.name}/{c.model}: ~{e.input_tokens} in + {e.output_tokens} out = ${e.total_usd:.4f}")
+        total_est += e.total_usd
+    print(f"  TOTAL per round (max): ${total_est:.4f}\n")
+
+    budget = CostBudget(
+        max_input_tokens=200_000,
+        max_output_tokens=80_000,
+        max_calls=20,
+        max_total_usd=2.50,
+    )
+
+    rounds_collected: list[list] = []
+
+    def _on_round_complete(round_idx: int, round_responses) -> None:
+        rounds_collected.append(list(round_responses))
+        print(f"=== ROUND {round_idx + 1} COMPLETE ===")
+        for r in round_responses:
+            if r.error:
+                print(f"  [error] {r.provider}/{r.model}: {r.error}")
+                continue
+            actual = estimate_cost(r.provider, r.model, r.input_tokens, r.output_tokens, table)
+            print(f"  [done] {r.provider}/{r.model}: {r.input_tokens} in / "
+                  f"{r.output_tokens} out · {r.latency_ms} ms · ${actual.total_usd:.4f}")
+        print()
+
+    print("=== CONSULT (1 round, Phase 4.5 Budget-v2 audit) ===")
+    consult(
+        members, question, budget,
+        rounds=1,
+        on_round_complete=_on_round_complete,
+        table=table, project=project, original_ask=ORIGINAL_ASK,
+    )
+
+    if not rounds_collected:
+        print("[error] no rounds completed", file=sys.stderr)
+        return 1
+
+    actual_total = 0.0
+    for round_responses in rounds_collected:
+        for r in round_responses:
+            if r.error:
+                continue
+            actual = estimate_cost(r.provider, r.model, r.input_tokens, r.output_tokens, table)
+            actual_total += actual.total_usd
+    print(f"=== TOTAL ACTUAL: ${actual_total:.4f} ===")
+
+    final_round = rounds_collected[-1]
+    if not [r for r in final_round if not r.error]:
+        return 1
+
+    manifest = SessionManifest(
+        mode="files",
+        artefact="agents/roadmaps/road-to-context-layer-maturity.md",
+        original_ask=ORIGINAL_ASK,
+        members=[f"{r.provider}/{r.model}" for r in final_round],
+        rounds=len(rounds_collected),
+        cost_usd_estimated=total_est,
+        cost_usd_actual=actual_total,
+        extra={"purpose": "Phase 4.5 Budget-v2 trim-result audit"},
+    )
+    session_dir = save_session(manifest=manifest, responses=rounds_collected)
+    print(f"[saved] {session_dir.relative_to(REPO_ROOT)}/")
+    return 1 if any(r.error for round_r in rounds_collected for r in round_r) else 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/scripts/ai_council/one_off_archive/2026-05/_one_off_context_layer_v1_estimate.py

@@ -0,0 +1,67 @@
+"""One-shot estimator for the v1 council review (no consult call).
+
+Sibling of `_one_off_context_layer_v1_review.py`. Prints bundle size and
+per-model token / cost projection so the user can confirm spend before
+the actual consult fires.
+"""
+from __future__ import annotations
+
+from pathlib import Path
+
+from scripts.ai_council._one_off_context_layer_v1_review import (
+    ORIGINAL_ASK,
+    REVIEW_PROMPT_HEADER,
+    ROADMAP_PATH,
+    _diff_stat,
+    _pr_body,
+)
+from scripts.ai_council.bundler import bundle_prompt
+from scripts.ai_council.clients import (
+    AnthropicClient,
+    OpenAIClient,
+    load_anthropic_key,
+    load_openai_key,
+)
+from scripts.ai_council.orchestrator import CouncilQuestion, estimate
+from scripts.ai_council.pricing import load_prices
+from scripts.ai_council.project_context import detect_project_context
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+
+
+def main() -> int:
+    roadmap_text = ROADMAP_PATH.read_text(encoding="utf-8")
+    parts = [
+        REVIEW_PROMPT_HEADER,
+        "## PR #36 — diff --stat\n\n```\n" + _diff_stat() + "\n```",
+        "## PR #36 — body\n\n" + _pr_body(),
+        "## Roadmap v1\n\n" + roadmap_text,
+    ]
+    bundle_text = "\n\n---\n\n".join(parts)
+    print(f"Bundle bytes: {len(bundle_text.encode('utf-8'))}")
+
+    ctx = bundle_prompt(bundle_text)
+    project = detect_project_context(REPO_ROOT)
+    table = load_prices()
+
+    anthropic = AnthropicClient(api_key=load_anthropic_key(), model="claude-sonnet-4-5")
+    openai = OpenAIClient(api_key=load_openai_key(), model="gpt-4o")
+    members = [anthropic, openai]
+
+    question = CouncilQuestion(mode="prompt", user_prompt=ctx.text, max_tokens=4096)
+    estimates = estimate(
+        question, members, table, project=project, original_ask=ORIGINAL_ASK,
+    )
+    total = 0.0
+    for c, e in zip(members, estimates):
+        print(
+            f"  {c.name}/{c.model}: ~{e.input_tokens} in + "
+            f"{e.output_tokens} out = ${e.total_usd:.4f}"
+        )
+        total += e.total_usd
+    print(f"  TOTAL (max, single round): ${total:.4f}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())