ai-consultants 4.0.4 → 5.1.0

package/.env.example

@@ -130,8 +130,8 @@ GEMINI_API_MODEL=gemini-3.1-pro-preview
 # GEMINI_REASONING_EFFORT=
 
 # Codex - The Pragmatist
-CODEX_MODEL=gpt-5.6-sol
-CODEX_API_MAX_TOKENS=4096
+CODEX_MODEL=gpt-6-astra
+CODEX_API_MAX_TOKENS=16384
 CODEX_TIMEOUT=180
 CODEX_CMD=codex
 # Reasoning effort for the codex CLI (and API mode). Passed as
@@ -158,9 +158,9 @@ KIMI_TIMEOUT=180
 KIMI_CMD=kimi
 
 # Claude - The Synthesizer
-CLAUDE_MODEL=claude-opus-5 # ai-consultants:default
-# Fable 5 is catalogued and priced but remains an explicit CLAUDE_MODEL opt-in
-# after its local smoke timed out.
+CLAUDE_MODEL=claude-fable-5-1 # ai-consultants:default
+# For the lower-cost standard/medium Claude tier, set CLAUDE_MODEL to
+# claude-opus-5 (or apply_model_tier standard for a single run).
 CLAUDE_TIMEOUT=240
 CLAUDE_CMD=claude
 CLAUDE_API_MAX_TOKENS=16384
@@ -250,7 +250,7 @@ MINIMAX_FORMAT=openai
 # =============================================================================
 
 # Defaults used when --preset / --strategy are omitted
-DEFAULT_PRESET=balanced
+# DEFAULT_PRESET=balanced
 DEFAULT_STRATEGY=coverage
 
 # The invoking integration normally sets this per run for self-exclusion.

package/CLAUDE.md

@@ -6,7 +6,7 @@ AI Consultants is a multi-model coverage system that queries up to 10 AI consult
 
 **Self-Exclusion**: The invoking agent is automatically excluded from both the panel and synthesis. Claude Code won't query or synthesize with Claude, Codex CLI won't query or synthesize with Codex, etc.
 
-**Version**: 4.0.4
+**Version**: 5.1.0
 
 ## Distribution
 
@@ -349,9 +349,9 @@ Three normal tiers plus a `maximum` tier are configurable via `apply_model_tier(
 
 | Tier | Description | Example Models |
 |------|-------------|----------------|
-| **premium** | Latest flagship models | claude-opus-5, Gemini 3.7 Flash (High), gpt-5.6-sol |
-| **maximum** | All 10 consultants; maximum targets and highest provider effort | K3-256k, Qwen3.8-Max, MiniMax M3; Grok xhigh, GLM/DeepSeek max |
-| **standard** | Good quality at reasonable cost | claude-sonnet-5, Gemini 3.7 Flash (High), gpt-5.6-terra |
+| **premium** | Latest flagship models | claude-fable-5-1, Gemini 3.7 Flash (High), gpt-6-astra |
+| **maximum** | All 10 consultants; maximum targets and highest provider effort | claude-fable-5-1, K3-256k, Qwen3.8-Max, MiniMax M3; Grok xhigh, GLM/DeepSeek max |
+| **standard** | Good quality at reasonable cost | claude-opus-5, Gemini 3.7 Flash (High), gpt-5.6-terra |
 | **economy** | Optimized for speed and low cost | claude-haiku-4-5, Gemini 3.7 Flash (Low), gpt-5.6-luna |
 
 **Default models are now premium tier** for maximum quality.
@@ -383,14 +383,14 @@ Three new presets leverage the model tiers:
 ./scripts/consult_all.sh --preset fast "quick syntax question"
 ```
 
-### Premium Model Defaults (August 2026)
+### Premium Model Defaults (September 2026)
 All consultants now use premium models by default:
 
 | Consultant | Default Model |
 |------------|---------------|
-| Claude | claude-opus-5 |
+| Claude | claude-fable-5-1 |
 | Gemini | Gemini 3.7 Flash (High) (via agy CLI); API: gemini-3.1-pro-preview |
-| Codex | gpt-5.6-sol |
+| Codex | gpt-6-astra |
 | Mistral | CLI: mistral-medium-3.5; API: mistral-large-3 |
 | DeepSeek | deepseek-v4-pro |
 | GLM | glm-5.3-flash |
@@ -586,11 +586,11 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 | `ENABLE_SMART_ROUTING` | false | Intelligent routing by category |
 | `ENABLE_COST_TRACKING` | true | Track costs |
 | `MAX_SESSION_COST` | 1.00 | Max budget ($) |
-| `CLAUDE_MODEL` | claude-opus-5 | Claude model (v2.5) |
+| `CLAUDE_MODEL` | claude-fable-5-1 | Claude model (use claude-opus-5 for lower-cost standard) |
 | `CLAUDE_API_MAX_TOKENS` | 16384 | Claude API thinking + visible-output budget |
 | `GEMINI_MODEL` | Gemini 3.7 Flash (High) | Gemini agy CLI model |
 | `GEMINI_API_MODEL` | gemini-3.1-pro-preview | Gemini API-mode model ID (v2.15) |
-| `CODEX_MODEL` | gpt-5.6-sol | Codex model (v2.5) |
+| `CODEX_MODEL` | gpt-6-astra | Codex model (v2.5) |
 | `MISTRAL_MODEL` | mistral-large-3 | Mistral model (v2.5) |
 | `MISTRAL_CLI_MODEL` | mistral-medium-3.5 | Vibe CLI model alias |
 | `SYNTHESIS_STRATEGY` | coverage | Synthesis strategy (coverage=union of distinct points) |
@@ -760,6 +760,26 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 
 ## Changelog
 
+### v5.1.0 (2026-09-09)
+
+- **Fable and Astra model policy.** `scripts/config.sh` and `scripts/configure.sh` align default/premium/maximum with Fable 5.1 and Astra, retain Opus 5/Terra for standard and Haiku/Luna for economy, and migrate exact historical unpinned Codex defaults while recording their origin. `resolve_codex_effort` applies implicit high per request so a later tier cannot inherit an automatically exported value.
+- **Completion and identity are independent checks.** `scripts/lib/claude_stream.jq` derives content identity from assistant text events, keeps billing participants separate, rejects incomplete/error/max-token streams and preserves available accounting. `query_codex.sh` reads usage from JSON events while keeping the final-message file as the answer. Requested-only Codex identity remains truthful and is not an invented promotion blocker.
+- **Grok sandbox checks precede fallback decisions.** `scripts/lib/grok_sandbox.sh` supplies passive socket and diagnostic checks shared with doctor/OAuth. Hidden `--no-memory` is supported by the installed parser even though omitted from help: the earlier diagnosis of an unsupported flag was incorrect. It remains mandatory in dispatch. Metadata annotation cannot replace the adapter's status when its same-directory temporary file fails.
+- **Accounting and configuration.** Fable and Astra both have catalog-independent rate fallbacks. Astra estimates disclose long-context multipliers and excluded cache/service adjustments; no estimate is called a provider invoice. Explicit `AI_CONSULTANTS_CONFIG_DIR` selects private configuration; project dotenv discovery and credential import are not added.
+- **Validation scope.** CLI-only acceptance was selected explicitly. The three provider smoke results retain their actual commit and identity provenance; API paths retain automated tests without a live-promotion claim. The maintainer Breadth v1 harness is included in the repository but excluded from npm, and its frozen inputs are unchanged. No completed P1 benchmark or coverage-gain claim is made.
+
+
+### v5.0.0
+
+- **Coverage claims are now locally auditable instead of resting on synthesis prose.** `scripts/lib/coverage_integrity.sh` normalizes successful structured envelopes into deterministic `<consultant-slug>:<index>` findings, overwriting any provider-supplied IDs. `scripts/synthesize.sh` asks the synthesizer to cite those IDs, then independently compares expected and represented IDs. Missing/duplicate/non-normalizable sources produce `DEGRADED`; unknown IDs and structural failures produce `FAILED`; invented IDs are removed from published coverage. The legacy `coverage`, `weighted_recommendation`, risk, action, and individual-response fields remain present.
+- **Truncation can no longer hide evidence loss.** Coverage/union prompts receive complete atomic findings. Only non-normalizable fallback context is capped, at Unicode code-point boundaries, and local `coverage_input_truncated` / `truncated_consultants` values overwrite model output in normal, local-fallback, and failed-closed artifacts. The report renders status, audited fields, truncation, and the affected consultants. The first Ubuntu CI run exposed an jq-expression compatibility gap; the final form uses jq 1.6-compatible string slicing and passed the release runner.
+- **Presets are host-aware and fail closed.** `get_effective_preset_panel_size` and `select_preset_consultants` preserve the advertised panel after self-exclusion by filling from the canonical roster using static transport evidence only. `max_quality` is ten in the catalog and nine for a canonical host. Insufficient capacity now aborts with promised/selected/missing counts, and health-gate pruning is rechecked before Round 1. Custom agents can satisfy capacity; explicit per-consultant false values remain fallback opt-outs.
+- **Public modes and their documentation have one executable source of truth.** `scripts/public_registry.sh` owns `fast-check -> fast/coverage`, `coverage-review -> balanced/coverage`, `max-coverage -> max_quality/coverage`, every existing preset/alias, and every strategy/default. `scripts/generate_public_docs.sh --check` renders and verifies README, SKILL, and reference tables. CLI conflict/override/unknown diagnostics run before user config, output directories, health checks, or adapters. `doctor --suggest-preset` downgrades to runnable `minimal` when only two effective transports remain.
+- **The v5 release path was exercised end to end within the preregistered cap.** One no-retry `coverage-review` smoke dispatched Gemini, Mistral, and Kimi once each, then synthesized once with Claude: four dispatches total, 3/3 consultant responses, `coverage_integrity=MET` with 12/12 source IDs, and no truncation. The release gate passed 27/27 suites, ShellCheck, Bash 3.2 syntax, generated-doc drift, packaging, and sentinel isolation.
+- **Development safety record.** An early P0.5 mode-registry lookup returned only the mode name, left the preset empty, and caused a local test to invoke ambient adapter auth/capability gates. Gemini/Codex were fixtures; the other adapters returned missing-key/auth/capability diagnostics. The retained transcript does not establish a network/provider request and no successful provider response was observed. The lookup was fixed, all later local release gates used provider/curl sentinels, and the final stub-only mode smoke recorded zero non-fixture adapter calls.
+
+  Deliberately retained: every v4 preset/alias, advanced configuration key, smart routing, custom agents, self-exclusion, and legacy JSON fields. Not claimed: semantic verification that a synthesized sentence faithfully paraphrases the cited atom; v5.0 verifies attribution-set integrity, not natural-language entailment.
+
 ### v4.0.4
 
 - **Housekeeping now removes dead implementation without removing public compatibility.** The cleanup deletes uncalled API, cache, optimizer, common, cost, persona, reliability, routing-summary, and session-display helpers, plus the stale README changelog and redundant npm ignore file. The documented `get_routing_mode`, `get_recommended_count`, and `get_category_timeout` helpers stay available and are regression-tested. Six historic config keys that had no runtime reader remain accepted as explicitly deprecated no-ops through v4.x: `SESSION_CLEANUP_DAYS`, `ENABLE_PROGRESS_BARS`, `ENABLE_EARLY_TERMINATION`, `USE_COMPACT_PROMPTS`, `ENABLE_SELECTIVE_CONTEXT`, and `MAX_FILES_PER_CONSULTANT`.

package/README.md

@@ -1,8 +1,8 @@
-# AI Consultants v4.0.4
+# AI Consultants v5.1.0
 
 > **Coverage, not a single guess.** A panel of up to 10 frontier models from different vendors fans out on your question in parallel and hands you the *union* of what they collectively see — the risks, edge cases, and approaches a single model misses.
 
-[![Version](https://img.shields.io/badge/version-4.0.4-blue.svg)](https://github.com/matteoscurati/ai-consultants)
+[![Version](https://img.shields.io/badge/version-5.1.0-blue.svg)](https://github.com/matteoscurati/ai-consultants)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Claude Code Skill](https://img.shields.io/badge/Claude%20Code-Skill-orange.svg)](https://docs.anthropic.com/en/docs/claude-code/skills)
 [![GitHub stars](https://img.shields.io/github/stars/matteoscurati/ai-consultants?style=social)](https://github.com/matteoscurati/ai-consultants)
@@ -455,6 +455,7 @@ Choose the right balance of quality, speed, and cost with model quality tiers.
 
 A preset only chooses the **consultant set and model tier** — every run then fans out in
 parallel and returns the coverage union.
+Preset panels use statically configured transports only (a CLI on `PATH`, or selected API mode with its key). Host self-exclusion is fail-closed; lost canonical slots are filled from `ALL_CONSULTANTS` in canonical order. If the effective target cannot be met, including after an enabled health gate prunes the panel, the run stops with promised/selected/missing-capacity guidance. Configured custom API agents are appended and may satisfy capacity, so a full preset can exceed its advertised count. `max_quality` still advertises 10 consultants, with an effective target of 9 for a canonical invoking host.
 For `max_quality`, Grok, GLM, and DeepSeek are also pinned to their highest
 accepted reasoning effort: Grok Build uses `xhigh`, while GLM and DeepSeek use
 `max`. Unsupported transport capabilities fail explicitly instead of reducing
@@ -468,18 +469,24 @@ likewise receives a 16,384-token completion budget in the maximum tier and a
 provider-specific compact Markdown contract through mmx's native system channel.
 Provider output is tagged `structured`, `fallback`, or `error`;
 malformed/truncated JSON fails
-closed, while usable prose remains available to synthesis with its quality
-disclosed. Synthesis excludes error envelopes and retains bounded response
-detail instead of reducing every consultant to its summary.
+closed. In coverage/union mode, only locally atomized `summary`, `pros`,
+`cons`, `alternatives`, `caveats`, and `references` can be source-attributed;
+fallback prose remains context-only for manual review. `synthesis.json` records
+`coverage_integrity`: `MET` applies only to those audited fields, while
+`DEGRADED`/`FAILED` must not be read as comprehensive coverage. It also records
+locally authoritative `coverage_input_truncated` and `truncated_consultants`:
+only non-normalizable fallback context is capped (at Unicode code-point
+boundaries), never atomic findings; a truncated coverage input is disclosed
+and cannot support a comprehensive coverage claim.
 
 ### Models by Tier
 
 | Consultant | `max_quality` | Premium | Standard | Economy |
 |------------|---------------|---------|----------|---------|
-| Claude | claude-opus-5 | claude-opus-5 | claude-sonnet-5 | claude-haiku-4-5 |
+| Claude | claude-fable-5-1 | claude-fable-5-1 | claude-opus-5 | claude-haiku-4-5 |
 | Gemini CLI | Gemini 3.7 Flash (High) | Gemini 3.7 Flash (High) | Gemini 3.7 Flash (High) | Gemini 3.7 Flash (Low) |
 | Gemini API | gemini-3.1-pro-preview | gemini-3.1-pro-preview | gemini-3.1-pro-preview | gemini-3.1-pro-preview |
-| Codex | gpt-5.6-sol | gpt-5.6-sol | gpt-5.6-terra | gpt-5.6-luna |
+| Codex | gpt-6-astra | gpt-6-astra | gpt-5.6-terra | gpt-5.6-luna |
 | Mistral CLI | mistral-medium-3.5 | mistral-medium-3.5 | mistral-medium-3.5 | devstral-small-2 |
 | Mistral API | mistral-large-3 | mistral-large-3 | mistral-large-3 | mistral-large-3 |
 | DeepSeek | deepseek-v4-pro | deepseek-v4-pro | deepseek-v4-flash | deepseek-v4-flash |
@@ -494,8 +501,9 @@ smoke through the `agy` adapter and is now the CLI default; Low is the CLI
 economy target. The Google API model remains `gemini-3.1-pro-preview`, while
 `gemini-3.7-flash` stays an API-only opt-in until that separate transport is
 verified. The new Mistral API IDs (`mistral-medium-3-5`,
-`mistral-large-2512`, `mistral-small-2603`) and Claude Fable 5 likewise remain
-catalogued opt-ins. Selecting a preset later intentionally reapplies that
+`mistral-large-2512`, `mistral-small-2603`) remain catalogued opt-ins. Claude
+Fable 5.1 is the default/premium/maximum target; use
+`CLAUDE_MODEL=claude-opus-5` for the lower-cost standard override. Selecting a preset later intentionally reapplies that
 preset's tier and can replace an explicit model override for the run.
 Qwen3.8-Max is likewise selected by `max_quality` only when API mode already
 points at an authenticated OpenAI-compatible Token Plan `/chat/completions`
@@ -525,39 +533,47 @@ apply_model_tier "economy"   # Set all to economy models
 
 ## Configuration
 
-### Presets
+<!-- ai-consultants:public-registry:start -->
+<!-- ai-consultants:default-synthesis-strategy=coverage -->
+### Public Modes
+
+| Mode | Preset | Default strategy | Use case |
+|---|---|---|---|
+| `fast-check` | `fast` | `coverage` | Fast economy panel for a quick coverage check |
+| `coverage-review` | `balanced` | `coverage` | Balanced panel for a general coverage review |
+| `max-coverage` | `max_quality` | `coverage` | Maximum-quality panel for the broadest coverage |
+
+### Configuration Presets
+
+| Preset | Alias | Target | Tier | Use case |
+|---|---|---:|---|---|
+| `minimal` | — | 2 | base | Quick questions |
+| `balanced` | — | 3 | base | Standard coverage |
+| `thorough` | — | 3 | base | Comprehensive analysis |
+| `high-stakes` | — | 4 | premium | Critical decisions |
+| `security` | — | 3 | base | Security reviews |
+| `cost-capped` | — | 3 | economy | Budget-conscious options |
+| `max_quality` | `max-quality` | 10 | maximum | Maximum coverage for critical decisions |
+| `medium` | — | 3 | standard | General questions |
+| `fast` | — | 2 | economy | Quick checks |
 
-Choose how many consultants to use:
+### Synthesis Strategies
 
-| Preset | Consultants | Tier | Use Case |
-|--------|-------------|------|----------|
-| `max_quality` | All 10 | Maximum + max effort | Critical decisions |
-| `medium` | 3 | Standard | General questions |
-| `fast` | 2 | Economy | Quick checks |
-| `minimal` | 2 (Gemini + Codex) | Default | Quick questions, low cost |
-| `balanced` | 3 (+ Mistral) | Default | Standard consultations |
-| `thorough` | 3 | Default | Comprehensive analysis |
-| `high-stakes` | Expanded panel (4 of 10) | Default | Critical decisions |
-| `security` | Security-focused (3) | Default | Security reviews |
-| `cost-capped` | Budget-conscious | Default | Minimal API costs |
+| Strategy | Description |
+|---|---|
+| `coverage` | Union of every distinct point across the panel **Default** |
+| `compare_only` | Present each consultant side-by-side, without a synthesized union |
+| `majority` | Produce one blended recommendation, weighting all equally |
+| `risk_averse` | Weight conservative responses higher |
+| `security_first` | Prioritize security-focused insights |
+| `cost_capped` | Prefer cheaper consultant opinions within budget |
+<!-- ai-consultants:public-registry:end -->
 
 **Bash:**
 ```bash
 ./scripts/consult_all.sh --preset balanced "Question"
 ```
 
-### Synthesis Strategies
-
-Control how responses are combined:
-
-| Strategy | Description |
-|----------|-------------|
-| `majority` | Most common answer wins (default) |
-| `risk_averse` | Weight conservative responses higher |
-| `security_first` | Prioritize security considerations |
-| `cost_capped` | Prefer simpler, cheaper solutions |
-| `compare_only` | No recommendation, just comparison |
-
 **Bash:**
 ```bash
 ./scripts/consult_all.sh --strategy risk_averse "Question"
@@ -594,11 +610,11 @@ Auto-selected `*_USE_API` values are marked `# ai-consultants:auto`, allowing a
 later run to adapt when a CLI or credential changes. Environment variables,
 `--set`, and unmarked values remain explicit user choices, except for the exact
 historical generated Claude default described below.
-Managed model defaults use `# ai-consultants:default`; `configure` upgrades the
-historical unmarked `CLAUDE_MODEL=claude-opus-4-8` default to Opus 5 and upgrades
-the exact managed Gemini CLI, GLM, and Grok defaults. To keep
-4.8 intentionally, run
-`ai-consultants configure --set CLAUDE_MODEL=claude-opus-4-8`; explicit model
+Managed model defaults use `# ai-consultants:default`; `configure` upgrades
+un-pinned historical `CLAUDE_MODEL=claude-opus-4-8` and `claude-opus-5` defaults
+to Fable 5.1, along with the exact managed Gemini CLI, GLM, and Grok defaults.
+To keep the lower-cost Opus 5 choice, run
+`ai-consultants configure --set CLAUDE_MODEL=claude-opus-5`; explicit model
 overrides are stored with `# ai-consultants:pin`.
 
 Enter credentials through `--interactive`/`--advanced` or export them before the
@@ -691,7 +707,11 @@ Classify -> Route -> Fan out (parallel) -> Coverage synthesis
 1. **Classify** the question into a category.
 2. **Route** (optional, `ENABLE_SMART_ROUTING`) to the consultants with the best category affinity (`references/affinity.json`).
 3. **Fan out** to every selected consultant in parallel — one shot each, no serial rounds.
-4. **Synthesize** the **coverage union**: the deduplicated set of every distinct point, recommendation, risk, and edge case raised by any consultant. Override with `--strategy compare_only` (side-by-side) or `majority` (a single blended recommendation).
+4. **Synthesize** the **coverage union** over auditable normalized fields. Read
+   `coverage_integrity` before treating it as complete: `MET` means every local
+   atomic source ID is represented once; `DEGRADED` and `FAILED` are explicitly
+   non-comprehensive. Override with `--strategy compare_only` (side-by-side) or
+   `majority` (a single blended recommendation).
 
 ### Output
 
@@ -704,7 +724,7 @@ ${XDG_CACHE_HOME:-$HOME/.cache}/ai-consultants/consultations/TIMESTAMP/
 ├── codex.json           #   with confidence scores
 ├── mistral.json
 ├── grok.json
-├── synthesis.json       # Coverage union
+├── synthesis.json       # Coverage union plus coverage_integrity/audited_fields
 ├── optimization_metrics.json
 └── report.md            # Human-readable report
 ```

package/SKILL.md

@@ -5,10 +5,10 @@ license: MIT
 compatibility: Requires bash, jq, and at least 2 AI CLI tools (agy, codex, vibe, etc.). macOS and Linux.
 metadata:
   author: matteoscurati
-  version: 4.0.4
+  version: 5.1.0
 ---
 
-# AI Consultants v4.0.4 - AI Expert Panel
+# AI Consultants v5.1.0 - AI Expert Panel
 
 **Coverage, not a single guess.** Convene a panel of AI "consultants" from different vendors for coding questions: they fan out in parallel and you get the *union* of what they collectively see — the risks, edge cases, and approaches a single model misses. Each consultant has a **configurable persona** that decorrelates its analysis.
 
@@ -106,7 +106,8 @@ smoke-tested K3-256k and MiniMax M3 targets, plus Qwen3.8-Max when an authentica
 already configured. Gemini 3.7 Flash High is the exact-transport-smoked `agy`
 default for maximum, premium, and standard CLI tiers; Low serves economy. The
 Gemini API target remains 3.1 Pro until `gemini-3.7-flash` completes a separate
-API smoke. Claude Fable 5 and the new Mistral API IDs remain explicit opt-ins.
+API smoke. Claude Fable 5.1 is the default/premium/maximum target; the new
+Mistral API IDs remain explicit opt-ins.
 Grok, GLM, and DeepSeek receive their
 highest accepted reasoning effort in this preset (`xhigh`, `max`, and `max`
 respectively); no failed target is silently replaced.
@@ -115,8 +116,14 @@ Maximum-quality transports use smoke-tested runtime budgets: four advisory
 turns for Mistral/Grok, extended Qwen/DeepSeek timeouts, and larger response
 budgets for reasoning APIs and a compact native-system Markdown contract for
 MiniMax M3. Responses carry an explicit `structured`,
-`fallback`, or `error` quality. Truncated JSON fails closed; usable prose is
-retained and disclosed, and synthesis consumes successful envelopes only.
+`fallback`, or `error` quality. Truncated JSON fails closed. Coverage/union
+synthesis source-attributed claims use only locally normalized atomic fields;
+fallback prose remains visible as context-only manual-review material. Inspect
+`coverage_integrity`: `MET` applies only to its listed `audited_fields`, while
+`DEGRADED` and `FAILED` are never comprehensive coverage claims.
+`synthesis.json` locally records `coverage_input_truncated` and
+`truncated_consultants`; only non-normalizable fallback context can be capped
+(on Unicode code-point boundaries), never normalized atomic findings.
 
 **Self-Exclusion**: The invoking agent is automatically excluded from the panel. When invoked from Claude Code, Claude is excluded; when invoked from Codex CLI, Codex is excluded, etc.
 
@@ -147,7 +154,46 @@ For detailed CLI installation instructions, see [Setup Guide](docs/SETUP.md).
 /ai-consultants:consult "What could go wrong with this design?" src/service.ts
 ```
 
-Presets: `minimal`, `balanced`, `thorough`, `high-stakes`, `security`, `cost-capped`, `max_quality`, `medium`, `fast`. Strategies: `coverage` (default; union of distinct points), `compare_only`, `majority`, `risk_averse`, `security_first`, `cost_capped`. See [Reference Details](references/details.md) for full tables, bash usage, and best practices.
+<!-- ai-consultants:public-registry:start -->
+<!-- ai-consultants:default-synthesis-strategy=coverage -->
+## Public Modes
+
+| Mode | Preset | Default strategy | Use case |
+|---|---|---|---|
+| `fast-check` | `fast` | `coverage` | Fast economy panel for a quick coverage check |
+| `coverage-review` | `balanced` | `coverage` | Balanced panel for a general coverage review |
+| `max-coverage` | `max_quality` | `coverage` | Maximum-quality panel for the broadest coverage |
+
+## Configuration Presets
+
+| Preset | Alias | Target | Tier | Use case |
+|---|---|---:|---|---|
+| `minimal` | — | 2 | base | Quick questions |
+| `balanced` | — | 3 | base | Standard coverage |
+| `thorough` | — | 3 | base | Comprehensive analysis |
+| `high-stakes` | — | 4 | premium | Critical decisions |
+| `security` | — | 3 | base | Security reviews |
+| `cost-capped` | — | 3 | economy | Budget-conscious options |
+| `max_quality` | `max-quality` | 10 | maximum | Maximum coverage for critical decisions |
+| `medium` | — | 3 | standard | General questions |
+| `fast` | — | 2 | economy | Quick checks |
+
+## Synthesis Strategies
+
+| Strategy | Description |
+|---|---|
+| `coverage` | Union of every distinct point across the panel **Default** |
+| `compare_only` | Present each consultant side-by-side, without a synthesized union |
+| `majority` | Produce one blended recommendation, weighting all equally |
+| `risk_averse` | Weight conservative responses higher |
+| `security_first` | Prioritize security-focused insights |
+| `cost_capped` | Prefer cheaper consultant opinions within budget |
+<!-- ai-consultants:public-registry:end -->
+
+Agents may use `--mode` instead of `--preset`; the mode chooses its mapped
+preset and coverage strategy unless an explicit `--strategy` is supplied. See
+[Reference Details](references/details.md) for capacity, fallback, and Bash
+usage details.
 
 ## Workflow
 

package/bin/ai-consultants

@@ -15,6 +15,17 @@ BIN_DIR="$(cd -P "$(dirname "$SOURCE")" && pwd)"
 PROJECT_ROOT="$(cd -P "$BIN_DIR/.." && pwd)"
 SCRIPTS_DIR="$PROJECT_ROOT/scripts"
 
+load_public_registry() {
+  # Keep `version` and the lightweight malformed-install diagnostic usable even
+  # when a partial installation lacks the optional public registry file.
+  if [ ! -f "$SCRIPTS_DIR/public_registry.sh" ]; then
+    echo "Error: public registry missing at $SCRIPTS_DIR/public_registry.sh" >&2
+    return 1
+  fi
+  # shellcheck source=../scripts/public_registry.sh
+  source "$SCRIPTS_DIR/public_registry.sh"
+}
+
 # --- Ensure execute permissions (npm can strip them) ---
 ensure_permissions() {
   local needs_fix=false
@@ -47,11 +58,13 @@ case "${1:-}" in
     exit 0
     ;;
   help|--help|-h)
+    load_public_registry || exit 1
     cat <<EOF
 ai-consultants v$VERSION - Cross-vendor AI coverage panel
 
 Usage:
   ai-consultants "question" [files...]        Consult AI experts
+  ai-consultants --mode <name> "question"     Use a public mode
   ai-consultants --preset <name> "question"   Use a configuration preset
   ai-consultants --strategy <name> "question" Use a synthesis strategy
   ai-consultants doctor [--fix] [--json]      Run diagnostics
@@ -62,10 +75,9 @@ Usage:
   ai-consultants version                      Show version
   ai-consultants help                         Show this help
 
-Presets:   minimal, balanced, thorough, high-stakes, security, cost-capped,
-           max_quality, medium, fast
-
-Strategies: coverage, compare_only, majority, risk_averse, security_first, cost_capped
+Modes:      $(registry_mode_rows | cut -d'|' -f1 | tr '\n' ' ' | sed 's/ $//')
+Presets:    $(registry_preset_rows | cut -d'|' -f1 | tr '\n' ' ' | sed 's/ $//')
+Strategies: $(registry_strategy_rows | cut -d'|' -f1 | tr '\n' ' ' | sed 's/ $//')
 
 Examples:
   npx ai-consultants "How to optimize this SQL query?"

package/docs/COST_RATES.md

@@ -1,4 +1,4 @@
-# Cost Rates - AI Consultants v4.0.4
+# Cost Rates - AI Consultants v5.1.0
 
 This page documents the per-token rates used by the cost tracking system.
 
@@ -28,12 +28,14 @@ models programmatically.
 | Gemini 3.1 Pro (High) | CLI opt-in | $0.002 | Gemini (agy CLI) |
 | gemini-3.1-pro-preview | API default | $0.00125 | Gemini API |
 | Gemini 3.6 Flash (High/Low) | Legacy CLI pins | $0.0015 | Gemini |
-| gpt-5.6-sol | Premium | $0.005 | Codex |
+| gpt-6-astra | Maximum/Premium | $0.010 | Codex |
+| gpt-5.6-sol | Explicit override | $0.004 | Codex |
 | gpt-5.6-terra | Standard | $0.002 | Codex |
 | gpt-5.6-luna | Economy | $0.0002 | Codex |
-| claude-opus-5 | Premium | $0.005 | Claude |
-| claude-fable-5 | Opt-in | $0.010 | Claude |
-| claude-sonnet-5 | Standard | $0.003 | Claude |
+| claude-fable-5-1 | Maximum/Premium | $0.010 | Claude |
+| claude-opus-5 | Standard | $0.005 | Claude |
+| claude-fable-5 | Legacy pins | $0.010 | Claude |
+| claude-sonnet-5 | Legacy pins | $0.003 | Claude |
 | claude-haiku-4-5 | Economy | $0.001 | Claude |
 | mistral-large-3 | Premium | $0.002 | Mistral |
 | mistral-medium-3.5 / mistral-medium-3-5 | Premium CLI / API opt-in | $0.0015 | Mistral |
@@ -70,12 +72,14 @@ models programmatically.
 | Gemini 3.1 Pro (High) | CLI opt-in | $0.012 | Gemini (agy CLI) |
 | gemini-3.1-pro-preview | API default | $0.005 | Gemini API |
 | Gemini 3.6 Flash (High/Low) | Legacy CLI pins | $0.0075 | Gemini |
-| gpt-5.6-sol | Premium | $0.030 | Codex |
+| gpt-6-astra | Maximum/Premium | $0.050 | Codex |
+| gpt-5.6-sol | Explicit override | $0.020 | Codex |
 | gpt-5.6-terra | Standard | $0.012 | Codex |
 | gpt-5.6-luna | Economy | $0.0012 | Codex |
-| claude-opus-5 | Premium | $0.025 | Claude |
-| claude-fable-5 | Opt-in | $0.050 | Claude |
-| claude-sonnet-5 | Standard | $0.015 | Claude |
+| claude-fable-5-1 | Maximum/Premium | $0.050 | Claude |
+| claude-opus-5 | Standard | $0.025 | Claude |
+| claude-fable-5 | Legacy pins | $0.050 | Claude |
+| claude-sonnet-5 | Legacy pins | $0.015 | Claude |
 | claude-haiku-4-5 | Economy | $0.005 | Claude |
 | mistral-large-3 | Premium | $0.006 | Mistral |
 | mistral-medium-3.5 / mistral-medium-3-5 | Premium CLI / API opt-in | $0.0075 | Mistral |

package/docs/JSON_SCHEMA.md

@@ -22,7 +22,10 @@ The schema is defined in `scripts/lib/schema.json` following JSON Schema Draft-0
     "cons": [...],
     "alternatives": [...],
     "caveats": [...],
-    "references": [...]
+    "references": [...],
+    "findings": [
+      {"id": "gemini:1", "kind": "summary", "field": "summary", "text": "..."}
+    ]
   },
   "confidence": {
     "score": 8,
@@ -61,6 +64,65 @@ The schema is defined in `scripts/lib/schema.json` following JSON Schema Draft-0
 
 ## Optional Fields
 
+### response.findings
+
+`findings` is added locally by the synthesis stage to successful consultant
+responses. It preserves all legacy fields and never trusts provider-supplied
+IDs. Each item has a deterministic local `id` of
+`<consultant-slug>:<one-based-index>`, plus `kind`, source `field`, and the
+atomically attributable `text`. The shared slug rule ASCII-lowercases the
+consultant name, retains `[a-z0-9_]`, replaces other runs with `_`, trims edge
+underscores, and uses `unknown` if empty. Thus the public custom name
+`My_agent` has IDs such as `my_agent:1`.
+
+The conservative normalization contract derives findings only from `summary`,
+`pros`, `cons`, `alternatives`, `caveats`, and `references`; alternatives may
+be meaningful strings or objects with meaningful name/reason text. Empty,
+null, or whitespace alternatives create no finding. Free-form fallback prose
+(`response_quality: fallback`) and successful envelopes with zero atomic
+findings are retained for human review but are non-normalizable; neither can
+be presented as audited coverage. Error envelopes remain excluded from
+synthesis.
+
+## Synthesis Coverage Attribution
+
+Each synthesized `coverage` item requires `source_ids`, containing only local
+IDs from normalized findings. `scripts/lib/schema.json` defines this as
+`definitions.synthesis_coverage_item`; the model prompt requests it, but the
+local post-check is authoritative.
+
+Every synthesis includes `coverage_integrity`:
+
+| Status | Meaning |
+|-------|---------|
+| `MET` | Every expected normalized source ID appears exactly once, with at least one expected ID and no non-normalizable success. It applies only to the audited fields. |
+| `DEGRADED` | A coverage-union source is missing or duplicated, no atomic source exists, or a successful response is non-normalizable. It is never comprehensive. |
+| `FAILED` | Coverage/source attribution is structurally unusable or includes an invented source ID; do not rely on coverage. |
+| `NOT_APPLICABLE` | A non-coverage strategy was selected and no attribution failure was found; it makes no coverage-union claim. |
+
+The object contains `expected_count`, `represented_count`, `missing_ids`,
+`unknown_ids`, `duplicate_ids`, `non_normalizable_consultants`,
+`structural_errors`, `audited_fields`, and `normalization_version`.
+`represented_count` is the count of unique expected IDs actually represented;
+unknown and duplicate IDs cannot inflate it. In coverage/union mode only
+`audited_fields` reach the attributable prompt. Structured `detailed` text and
+fallback prose are not atomized; fallback text is context-only and must never
+produce coverage items or source IDs.
+
+Every synthesis artifact also carries locally authoritative
+`coverage_input_truncated` (boolean) and `truncated_consultants` (a stable,
+first-occurrence-unique array of consultant names discovered in lexically
+ordered response-file order). These fields overwrite any values supplied by a
+model and are present even on local fallback or failed-closed artifacts.
+`SYNTH_DETAIL_MAX_CHARS` applies only to usable, non-normalizable fallback
+context, never to normalized finding text. Its unit is Unicode code points:
+input with exactly the limit is retained and does not set the flag; only input
+with more code points is shortened to that limit, preserving complete
+multibyte UTF-8 characters. When such context is truncated, coverage/union is
+at least `DEGRADED` and its disclosure names the affected consultants; it is
+never a comprehensive claim. A non-coverage strategy can remain
+`NOT_APPLICABLE`, but still exposes this metadata and disclosure.
+
 ### response.code_snippets
 
 Array of code snippets:
@@ -307,3 +369,23 @@ jq 'has("consultant") and has("response") and has("confidence")' output.json
   }
 }
 ```
+
+### Codex cost and cached-input metadata
+
+When present, `metadata.cost_source` is `unavailable` without token data, otherwise
+`estimated-standard-rates` or `estimated-long-context-standard-rates`.
+`metadata.cost_note` discloses excluded cache/service adjustments; an estimate
+is not a provider invoice. `metadata.tokens_cached_input`, when supplied by
+CLI telemetry, is the cached subset of `tokens_input` and is not added again.
+Unknown splits use the documented estimation heuristic; they cannot establish
+an exact long-context bill. Astra maximum/premium uses `high` by default,
+including in max_quality; valid explicit Codex effort always takes precedence.
+
+### Claude streaming billing metadata
+
+`metadata.billing_models` is an optional array of provider billing model IDs.
+It does not attest the content model. Claude content identity comes only from
+response-bearing assistant events; successful terminal completion is a separate
+requirement. `provider_cost_usd`, when present, is the provider's terminal cost.
+Token accounting prefers a supplied per-model billing aggregate over terminal
+usage, without adding those two summaries together; absent usage is estimated.

package/docs/SETUP.md

@@ -592,10 +592,16 @@ shell history or observed by other local processes. Use `--interactive`,
 ### Using .env file
 
 ```bash
-cp .env.example .env
+mkdir -p "${XDG_CONFIG_HOME:-$HOME/.config}/ai-consultants"
+# For a new configuration only; keep existing credentials/settings if present.
+cp -n .env.example "${XDG_CONFIG_HOME:-$HOME/.config}/ai-consultants/.env"
+chmod 600 "${XDG_CONFIG_HOME:-$HOME/.config}/ai-consultants/.env"
 ```
 
-Edit `.env`:
+Edit that user configuration `.env`. A different existing private directory must
+be selected explicitly with `AI_CONSULTANTS_CONFIG_DIR`; project `.env` files
+are not discovered automatically:
+
 
 ```bash
 # Enable/disable consultants (10 available)
@@ -797,3 +803,50 @@ less "$output_dir/report.md"
 ```
 
 See [README.md](../README.md) for usage examples and full documentation.
+
+For a configuration outside the standard user config directory, set
+`AI_CONSULTANTS_CONFIG_DIR=/absolute/private/config-directory` explicitly.
+The loader does not discover project `.env` files. Keep credentials in your
+existing private configuration; do not copy them into this repository.
+
+Claude CLI uses `stream-json --verbose`. Only response-bearing assistant
+messages attest the content model; terminal `modelUsage` records billing
+participants separately. A missing or conflicting content model remains
+`requested-only` and cannot pass a model-promotion gate. Successful terminal
+completion is required even when partial response text or billing is available.
+
+Codex defaults to `gpt-6-astra`; premium and maximum select Astra, standard
+selects `gpt-5.6-terra`, economy selects `gpt-5.6-luna`. Sol remains an explicit
+`CODEX_MODEL=gpt-5.6-sol` override. Configure migrates exact unpinned persisted
+`gpt-5.5` and `gpt-5.6-sol` values to Astra and records `migrated-from` provenance.
+Use `# ai-consultants:pin`, an environment override or `--set` to keep a model.
+
+Astra uses `high` effort when no effort is configured. Explicit `low`, `medium`,
+`high`, `xhigh`, and `max` prevail; `none`/`minimal` fail before dispatch.
+The default completion budget is 16384 tokens, including reasoning; override
+`CODEX_API_MAX_TOKENS` explicitly as needed. The text-only Chat Completions
+request uses `max_completion_tokens` and `reasoning_effort`, without tools.
+See the [official migration guide](https://developers.openai.com/api/docs/guides/latest-model).
+CLI JSON events supply token telemetry; the final message file supplies content.
+A CLI `-m` selection remains `requested-only`, not provider attestation.
+
+[Astra Standard pricing](https://developers.openai.com/api/docs/models/gpt-6-astra)
+is $10/M input and $50/M output. More than 272K input tokens doubles input
+and multiplies output by 1.5 for the whole request. Reported cost is an estimate
+unless a provider cost is supplied: cache writes, cached-input discounts and
+service processing rates can change the invoice.
+
+Grok CLI and doctor passively inspect the container-runtime socket deny paths,
+including Docker Desktop locations. Symlink endpoints (including dangling links)
+block CLI dispatch because the sandbox cannot safely resolve those deny rules.
+Absent paths and ordinary socket files pass this check. Nothing is removed and
+Docker configuration is never changed. Runtime `sandbox_profile_refused` and
+`sandbox_not_applied` diagnostics fail even with exit zero; they cannot trigger
+retry or API fallback. OAuth synchronization and per-run isolation remain active.
+
+
+Grok compatibility includes a provider-free parser probe of the complete advisory
+argument list. Hidden flags such as `--no-memory` are still required in the
+actual request even when omitted from public help. Unsupported mandatory flags
+block dispatch; the optional `--no-auto-update` guard is used when its parser
+probe succeeds, including on CLIs that hide it from help.