pantheon-opencode 1.5.0-beta.14 → 1.5.0-beta.16

package/AGENTS.md

@@ -301,7 +301,9 @@ memory_store({
     agreements: ["point1", "point2"],
     divergences: [{"issue": "...", "resolution": "..."}],
     response_rate: "X of Y",
-    themis_audit: "approved|issues"
+    themis_audit: "approved|issues",
+    precedent_used: false,
+    timestamp: "<ISO-8601>"
   },
   metadata: {
     type: "council_decision",
@@ -310,6 +312,7 @@ memory_store({
   }
 })
 ```
+`value` is JSON-serialized before storing (the MCP `memory_store.value` argument is a string).
 
 ### Read Path (Precedent Fast-Path)
 Before dispatching a new council, Zeus runs:
@@ -320,8 +323,8 @@ memory_search(question, top_k=2, namespace="council_decisions")
 Result interpretation:
 | Score | Age | Action |
 |-------|-----|--------|
-| > 0.85 | < 30 days | Return precedent as fast-path answer. Skip council dispatch entirely. |
-| > 0.85 | >= 30 days | Return with warning "Reavaliar se contexto mudou" + proceed with council |
+| > 0.85 | < 30 days | Return precedent verbatim (note "⚠️ Decisão de [data] — reavaliar se contexto mudou") as fast-path answer. Skip council dispatch entirely. |
+| > 0.85 | >= 30 days | Return with warning "Reavaliar se contexto mudou — decisão tem mais de 30 dias" + proceed with council |
 | 0.5 - 0.85 | Any | Include as context for specialists but still dispatch council |
 | < 0.5 | Any | Ignore, proceed with fresh council |
 
@@ -371,7 +374,7 @@ You MUST self-monitor for these stall conditions:
 | Symptom | Detection Rule | Recovery Action |
 |---------|---------------|-----------------|
 | Silent loop | 3+ consecutive turns with no tool call AND no visible progress | Output `[STALL_DETECTED]` and re-read your task definition. If still stuck, escalate to user with: "I appear to be stuck on [task]. Options: (1) retry with different approach, (2) delegate to specialist, (3) simplify scope." |
-| Delegation black hole | Agent dispatched but no response after 2x the timeout from routing.yml | Log the hang, cancel via `cancel_task`, dispatch to fallback agent, report to user |
+| Delegation black hole | Agent dispatched but no response after 2x the timeout from routing.yml | Log the hang, cancel via `cancel_task`, then follow the fallback chain in `## ⏱️ Timeout & Retry Enforcement` |
 | Circular delegation | Same specialist re-dispatched for same task 2+ times without progress | Break cycle: dispatch to different specialist OR escalate to user |
 | Idle after completion | All background tasks completed but no synthesis/next step for 2+ turns | Force synthesis: summarize all completed results and propose next action |
 | Context thrash | Re-reading same files repeatedly without new action | Stop re-reading. State: "Already have context on [file]. Proceeding with [action]." |
@@ -397,9 +400,7 @@ When a delegation fails (timeout, empty response, error):
 
 2. **Retry ONCE** with rephrased prompt — add: "Previous attempt failed with: [error]. Adjusted approach: [what changed]."
 
-3. **If retry also fails** → DO NOT retry a third time blindly. Instead:
-   - Dispatch to fallback agent (from routing.yml)
-   - If no fallback, escalate to user with: "Task [X] failed after retry. Options: (a) simplify, (b) different agent, (c) manual intervention."
+3. **If retry also fails** → do NOT retry blindly; follow the fallback chain and escalation protocol in `## ⏱️ Timeout & Retry Enforcement`.
 
 ## Progress Checkpoint
 
@@ -564,10 +565,7 @@ sequenceDiagram
 ## Dispatch Sequence (9-Step Protocol)
 
 ### Step 0 — Precedent Fast-Path (Fase 1)
-Before any dispatch: `memory_search(query, top_k=2, namespace="council_decisions")`
-- Score > 0.85 AND age < 30 days → return precedent verbatim with note "⚠️ Decisão de [data] — reavaliar se contexto mudou". SKIP entire dispatch.
-- Score > 0.85 AND age > 30 days → return precedent with ⚠️ "Reavaliar se contexto mudou — decisão tem mais de 30 dias"
-- Else → proceed to Step 0b
+Run the precedent read path defined in `## Memory Protocol > Council Decisions Namespace` (`memory_search(query, top_k=2, namespace="council_decisions")`). If no precedent applies, proceed to Step 0b.
 
 ### Step 0b — Apollo Pre-Scan (Fase 2, --research flag)
 If `/pantheon --research <question>`: dispatch @apollo with 30s timeout. Inject findings as `shared_context` into ALL specialist prompts. Skip if flag absent.
@@ -669,33 +667,11 @@ task(subagent_type: "themis", prompt: "Audit this council synthesis for fidelity
 - If issues → fix each issue before delivering to user
 
 ### Step 9 — Persist & Reconcile (Fase 1)
-```
-memory_store({
-  namespace: "council_decisions",
-  key: "council:<yyyy-mm-dd>:<slug>",
-  value: JSON.stringify({
-    question, specialists, recommendation, confidence,
-    agreements, divergences, precedent_used, timestamp
-  }),
-  metadata: {type: "council_decision", specialist_count: N}
-})
-board.markReconciled("<task-id>")
-```
+Persist the decision using the write path in `## Memory Protocol > Council Decisions Namespace`, then `board.markReconciled("<task-id>")`.
 
 ## Specialist Output Format (Fase 1 — machine-parseable structured fields)
 
-Specialists MUST return these structured fields in their response:
-
-```
-## specialist_response
-**position:** <clear one-sentence position>
-**reasoning:** <2-4 sentences>
-**trade_offs:** <what's gained vs lost>
-**risks:** <what could go wrong>
-**confidence:** High | Medium | Low
-**agreement_signals:** agree: @agent1, @agent2 on [issue] | disagree: @agent3 on [issue]
-**specific_claims:** <count of specific factual claims in response>
-```
+Specialists MUST return the structured `## specialist_response` format (position, reasoning, trade_offs, risks, confidence, agreement_signals, specific_claims) defined in `## Agent Return Format > Council Specialist Response Format`.
 
 ## Domain-to-Specialist Mapping
 
@@ -928,39 +904,14 @@ ANY NO  → full task (IMPL artifact + Themis review mandatory)
 3. **No Themis dependency** — output doesn't feed into a phase that requires review
 
 ## Subtask Return Format
-Expect a `subtask_summary` response with:
-```
-## subtask_summary
-**files_changed:** [paths]
-**summary:** What was done
-**tests:** ✅ or N/A
-**status:** complete | partial | escalated
-```
+Return the standard `## subtask_summary` defined in `## Agent Return Format` (files_changed, summary, tests, coverage, tokens, status, blockers).
 
 ## Timeout Parcial (Partial Results)
 
-Timeout parcial is ONLY for read-only, independent agents:
-- ✅ @apollo — can return partial file list ("found 7 of 12 files before timeout")
-- ✅ @gaia — can return partial literature findings
-
-- ✅ @talos — can confirm progress if hotfix times out
-- ❌ Never for implementers or reviewers — must complete or fail
-
-When dispatching with partial-OK, set expectation:
-```
-@apollo Search for auth files. Timeout parcial OK — return whatever you have.
-```
+Only agents marked ✅ in the Timeout Behavior table above may return partial results: @apollo (partial file list, e.g. "found 7 of 12 files before timeout"), @gaia (partial literature findings) and @talos (confirm progress if a hotfix times out). Never for implementers or reviewers — they must complete or fail. When dispatching with partial-OK, set the expectation: `@apollo Search for auth files. Timeout parcial OK — return whatever you have.`
 
 ---
 
 # 📊 TIMEOUT TRACKING
 
-Maintain awareness of in-flight delegations:
-
-| Agent | Timeout | Status | Partial OK? |
-|-------|---------|--------|-------------|
-| @apollo | 60s | ✅ complete | ✅ |
-| @hermes | 180s | ⏳ in progress | ❌ |
-| @themis | 120s | ⏳ in progress | ❌ |
-
-Log timeouts to `/memories/session/timeout-log.md` for later analysis.
+Track in-flight delegations against the Timeout Behavior table above. Log timeouts to `/memories/session/timeout-log.md` for later analysis.

package/CHANGELOG.md

@@ -18,6 +18,71 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
 ## ✅ Closed Issues
 
+## [v1.5.0-beta.16] - 2026-09-15
+
+<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
+     move this section to a versioned entry and reset the template below. -->
+
+## 🆕 What's New
+
+- **Modernização CI/supply-chain:** 22 actions SHA-pinadas; `gitleaks-action` v3
+  (fix crítico — a v2 morria com Node 20 em 2026-09-16) com CLI 8.30.1; cache
+  npm/pip; Dependabot; CodeQL `+python` e `codeql-config`; permissões reduzidas
+  no `docs.yml`; job `version-check` fundido no `validate`; `upload-artifact` v7
+  e `download-artifact` v8.
+- **Lean:** ~17 módulos mortos removidos de `src/pantheon/`, docs/scripts
+  obsoletos, `teste/`/`testes/`, `Dockerfile`/`docker-compose` (de outro projeto)
+  e caches; ~38% dos arquivos de teste removidos/consolidados; testes mínimos
+  readicionados para os módulos vivos (tool-ceiling, native-probe).
+- **Instructions:** deduplicação das instruções compartilhadas — contexto menor
+  sem perder nenhuma regra.
+
+## 🐞 Fixed
+
+- **2 flakes determinísticos eliminados:** TTL do MCP persistence
+  (`test_ttl_expiry_real_time`) e `logger.test.mjs` deixaram de depender de
+  timing/carga do host.
+- **Refs stale corrigidas:** referências de versão/ambiente atualizadas para
+  Node 22+.
+
+## [v1.5.0-beta.15] - 2026-09-15
+
+<!-- Add new changes here. Running `node scripts/versioning.mjs apply` will
+     move this section to a versioned entry and reset the template below. -->
+
+## 🆕 What's New
+
+- **Delegation `read` devolve o relatório completo:** o retorno de `read` passa a
+  ler o relatório integral do disco (com cap configurável e marker explícito de
+  truncamento) em vez do recibo resumido — o conteúdo é o mesmo tanto no caminho
+  nativo quanto no legado, com paridade garantida entre eles.
+- **`sanitizeReceiptText` UTF-8-safe:** a sanitização de recibos deixou de corromper
+  caracteres multibyte; acentuação e demais codepoints UTF-8 são preservados no
+  caminho nativo e no legado.
+- **TUI — cor de status na row inteira:** cada linha do painel Delegations passa a
+  ser pintada pelo estado — vermelho = falha, verde = concluído, amarelo = em
+  andamento — com o glyph mantido como canal redundante para acessibilidade.
+
+## 🐞 Fixed
+
+- **TUI — painel Delegations só da sessão ativa:** o painel deixa de renderizar
+  rows cross-session/órfãs que causavam "Session not found" ao clicar; a lista
+  agora cobre apenas a sessão ativa, mantendo a retenção de concluídas (2 min)
+  e falhas (10 min).
+- **Guards de estado e navegação órfã:** transições prematuras para `done` são
+  bloqueadas e a navegação defensiva ignora alvos órfãos, evitando seleção
+  inválida no painel.
+- **Isolamento do board nos testes:** testes que importam o plugin real agora
+  isolam o BackgroundJobBoard, eliminando o fantasma "preserve this running
+  delegation"; o board real foi limpo.
+- **Lean no core:** 17 módulos mortos de `src/pantheon/` removidos, ~38% dos
+  arquivos de teste removidos/consolidados e docs/scripts órfãos limpos, com
+  testes mínimos readicionados para os módulos vivos (tool-ceiling, native-probe).
+- **Flake de TTL determinístico:** `test_ttl_expiry_real_time` deixou de competir
+  com a truncagem de microssegundos do SQLite — o teste agora espera o início de
+  um segundo limpo antes do store e usa margem sobre o TTL, eliminando o flake
+  dependente de carga (test-only).
+
 ## [v1.5.0-beta.14] - 2026-09-14
 
 <!-- Add new changes here. Running `node scripts/versioning.mjs apply` will

package/README.md

@@ -172,8 +172,7 @@ script's SHA-256 without regenerating it.
   covering OpenCode V1/V2 side by side — see
   [Sandbox validation](#sandbox-validation-v1v2).
 - Beta2 agent-economy policy: direct native delegation, bounded compaction
-  carry-forward, compact context encoding, and quality floors — see
-  [Beta2 agent economy policy](docs/ws3-token-opt-measurements.md#beta2-agent-economy-policy).
+  carry-forward, compact context encoding, and quality floors.
 - A `--prompts` installer flag is planned for a future release.
 
 ## OpenCode V1/V2 — Dual Version (1.5.0-beta.2)

package/README.pt-BR.md

@@ -31,7 +31,7 @@ de planejar o trabalho, avançar, conferir resultados e preservar o contexto
 
 ## Comece em 2 minutos
 
-Requisitos: [OpenCode 1.18.4+](https://opencode.ai/docs/) e Node.js 18+.
+Requisitos: [OpenCode 1.18.4+](https://opencode.ai/docs/) e Node.js 22+.
 
 No projeto em que você quer usar o Pantheon:
 

package/commands/pantheon.md

@@ -9,41 +9,7 @@ agent: zeus
 **When:** Architecture trade-offs, technology selection, security assessments, multi-stakeholder concerns
 **Returns:** Structured synthesis with recommendation, confidence level, resolved divergences
 
-## Dispatch Selection
-
-Choose 2-3 agents based on domain:
-
-| Domain | Specialists |
-|--------|-------------|
-| Architecture | hermes, demeter, themis, athena |
-| Security | themis, hermes, prometheus, nyx |
-| Database | demeter, hermes, prometheus |
-| AI/RAG | hephaestus, nyx |
-| Infrastructure | prometheus, hermes, themis |
-| Frontend/UX | aphrodite, themis, hermes |
-| Observability | nyx, hermes |
-| General | athena, themis, hermes |
-
-Send ALL `task()` calls in a single message. Each must return: Recommendation · Reasoning · Trade-offs · Risks · Confidence.
-
-## Synthesis Structure
-
-After ALL responses arrive, produce EXACTLY this structure:
-
-### 📋 Individual Assessments
-For each specialist: Recommendation, Reasoning, Trade-offs, Risks, Confidence
-
-### ✅ Agreements
-Where 2+ specialists converge
-
-### ⚡ Divergences
-Where they disagree — resolve each one with reasoning
-
-### 🔥 Total Divergence
-If ALL specialists disagree on a point, call this out explicitly
-
-### 🏆 Recommendation
-Decisive conclusion with confidence level
+Dispatch, specialist selection, and synthesis follow the canonical `## Zeus Council Synthesis` protocol (Steps 0–9: precedent fast-path, dispatch, confidence cross-validation, rebuttal, tie-break, Themis audit, persist). Send ALL `task()` calls in a single message; each specialist returns the `## specialist_response` structure from `## Agent Return Format`.
 
 ## Question:
 $ARGUMENTS

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pantheon-opencode",
-  "version": "1.5.0-beta.14",
+  "version": "1.5.0-beta.16",
   "description": "Multi-agent orchestration for OpenCode — 14 specialized agents, TDD, Themis review gates.",
   "type": "module",
   "publishConfig": {

package/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "pantheon",
   "publisher": "ils15",
-  "version": "1.5.0-beta.14",
+  "version": "1.5.0-beta.16",
   "displayName": "Pantheon",
   "description": "Conductor-Delegate orchestration platform with 14 specialized agents, 21 skills, and OpenCode support.",
   "agents": "./src/agents",

package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.backends._legacy:_Backend"
 
 [project]
 name = "pantheon"
-version = "1.5.0-beta.14"
+version = "1.5.0-beta.16"
 description = "Multi-agent orchestration framework"
 requires-python = ">=3.11"
 dependencies = []
@@ -37,10 +37,8 @@ ignore = ["E501"]
 "scripts/scrub-secrets.py" = ["N999"]
 # These modules defer optional/heavy imports until the corresponding command is used.
 "scripts/vector_memory/*.py" = ["PLC0415"]
-"tests/test_code_mode_args.py" = ["PLC0415"]
 "tests/test_code_mode_sandbox.py" = ["PLC0415", "N806"]
 "tests/test_code_mode_server.py" = ["PLC0415"]
-"tests/test_eval_store.py" = ["PLC0415", "PLR2004"]
 "tests/test_memory_mcp_server.py" = ["PLC0415", "PLR2004"]
 # Existing public APIs and test fixtures are intentionally broad/simple; refactoring
 # them would be behavior-affecting rather than a mechanical lint correction.
@@ -54,8 +52,7 @@ ignore = ["E501"]
 "scripts/vector_memory/query.py" = ["PLR0913"]
 "src/mcp/eval_store.py" = ["PLR2004"]
 "tests/test_code_mode_frontmatter.py" = ["PLR2004"]
-"tests/test_eval_judge.py" = ["PLR2004"]
-"tests/test_eval_static.py" = ["PLR2004"]
+"tests/test_eval.py" = ["PLR2004"]
 "tests/test_mcp_persistence_server.py" = ["PLR2004"]
 
 [tool.mypy]

package/src/agents/zeus.md

@@ -301,32 +301,10 @@ vão a idle com todos incompletos. Guards (todos no `src/pantheon/todo-enforcer.
 
 ## Wave 4 (PR #46): Empty-Result Retry + /cost + Themis Tier
 
-### Empty-Result Retry (dispatch-guard — MANUAL orchestration)
-OpenCode 1.18.x NAO permite interceptar a conclusao de `task()` via hooks,
-entao o `src/pantheon/dispatch-guard.ts` e uma lib pura usada POR VOCE na
-orquestracao (NAO esta wired no plugin):
-
-```
-import { createDispatchGuard } from '.../src/pantheon/dispatch-guard.ts'  # via code-mode ou subagente
-
-guard = createDispatchGuard({ retryOnEmpty: true, logger: { warn: console.warn } })
-
-# classificar resultado de task_status/wait:
-#   'content'      → tem texto, pronto
-#   'empty-mode1'  → SEM texto E SEM tokens (nada voltou)      → RETRY 1x
-#   'empty-mode2'  → SEM texto, MAS tokens (raciocinou, perdeu a parte de texto;
-#                    assinatura da falha themis Wave-2)         → RETRY 1x
-
-out = await guard.maybeRetry(result, async () => { ...task() de novo... })
-# out.retried=true se redisparou; CAP DURO de 1 retry — nunca 2x.
-# Se o retry voltar vazio, `out.retried=false` — NAO tente de novo: escale.
-```
-Regra: retry 1x APENAS em `empty-mode1`/`empty-mode2`. Resultado com conteudo
-nunca redispara. Apos 1 retry vazio → escalate (mesma regra do TODO Enforcer).
-
-> **Waves DEVEM usar `zeusDelegateWithRetry`** (`src/pantheon/zeus-delegate-with-retry.ts`) — encapsula `delegate → waitForTerminal → classify → retry 1x → escalate` com cap duro 1; se ainda vazio throw `ZeusEscalationError` (escale: tente outro agente, simplifique, manual).
-> Uso alto-nível: `import { zeusDelegateWithRetry } from './pantheon/zeus-delegate-with-retry.ts'` → `await zeusDelegateWithRetry({ board, client, sessionID, agent, prompt })`.
-> Uso baixo-nível: `createZeusRetryHelper().executeWithRetry(first, () => secondRead())` — classifica empty e decide retry/escalate (mesmo cap 1).
+### Empty-Result Retry (runtime — automatic)
+Empty-response detection (`empty-mode1` / `empty-mode2`) and stuck-agent
+classification are wired at runtime in `delegation-classifier.ts` (consumed by
+`delegation.ts`). No manual retry helper is required.
 
 ### /cost — pantheon_cost tool (WIRED no plugin)
 `pantheon_cost({ days?: number })` le o `opencode.db` READ-ONLY usando o backend

package/src/instructions/memory-protocol.instructions.md

@@ -84,7 +84,9 @@ memory_store({
     agreements: ["point1", "point2"],
     divergences: [{"issue": "...", "resolution": "..."}],
     response_rate: "X of Y",
-    themis_audit: "approved|issues"
+    themis_audit: "approved|issues",
+    precedent_used: false,
+    timestamp: "<ISO-8601>"
   },
   metadata: {
     type: "council_decision",
@@ -93,6 +95,7 @@ memory_store({
   }
 })
 ```
+`value` is JSON-serialized before storing (the MCP `memory_store.value` argument is a string).
 
 ### Read Path (Precedent Fast-Path)
 Before dispatching a new council, Zeus runs:
@@ -103,8 +106,8 @@ memory_search(question, top_k=2, namespace="council_decisions")
 Result interpretation:
 | Score | Age | Action |
 |-------|-----|--------|
-| > 0.85 | < 30 days | Return precedent as fast-path answer. Skip council dispatch entirely. |
-| > 0.85 | >= 30 days | Return with warning "Reavaliar se contexto mudou" + proceed with council |
+| > 0.85 | < 30 days | Return precedent verbatim (note "⚠️ Decisão de [data] — reavaliar se contexto mudou") as fast-path answer. Skip council dispatch entirely. |
+| > 0.85 | >= 30 days | Return with warning "Reavaliar se contexto mudou — decisão tem mais de 30 dias" + proceed with council |
 | 0.5 - 0.85 | Any | Include as context for specialists but still dispatch council |
 | < 0.5 | Any | Ignore, proceed with fresh council |
 

package/src/instructions/zeus-anti-stall.instructions.md

@@ -15,7 +15,7 @@ You MUST self-monitor for these stall conditions:
 | Symptom | Detection Rule | Recovery Action |
 |---------|---------------|-----------------|
 | Silent loop | 3+ consecutive turns with no tool call AND no visible progress | Output `[STALL_DETECTED]` and re-read your task definition. If still stuck, escalate to user with: "I appear to be stuck on [task]. Options: (1) retry with different approach, (2) delegate to specialist, (3) simplify scope." |
-| Delegation black hole | Agent dispatched but no response after 2x the timeout from routing.yml | Log the hang, cancel via `cancel_task`, dispatch to fallback agent, report to user |
+| Delegation black hole | Agent dispatched but no response after 2x the timeout from routing.yml | Log the hang, cancel via `cancel_task`, then follow the fallback chain in `## ⏱️ Timeout & Retry Enforcement` |
 | Circular delegation | Same specialist re-dispatched for same task 2+ times without progress | Break cycle: dispatch to different specialist OR escalate to user |
 | Idle after completion | All background tasks completed but no synthesis/next step for 2+ turns | Force synthesis: summarize all completed results and propose next action |
 | Context thrash | Re-reading same files repeatedly without new action | Stop re-reading. State: "Already have context on [file]. Proceeding with [action]." |
@@ -41,9 +41,7 @@ When a delegation fails (timeout, empty response, error):
 
 2. **Retry ONCE** with rephrased prompt — add: "Previous attempt failed with: [error]. Adjusted approach: [what changed]."
 
-3. **If retry also fails** → DO NOT retry a third time blindly. Instead:
-   - Dispatch to fallback agent (from routing.yml)
-   - If no fallback, escalate to user with: "Task [X] failed after retry. Options: (a) simplify, (b) different agent, (c) manual intervention."
+3. **If retry also fails** → do NOT retry blindly; follow the fallback chain and escalation protocol in `## ⏱️ Timeout & Retry Enforcement`.
 
 ## Progress Checkpoint
 

package/src/instructions/zeus-council-synthesis.instructions.md

@@ -85,10 +85,7 @@ sequenceDiagram
 ## Dispatch Sequence (9-Step Protocol)
 
 ### Step 0 — Precedent Fast-Path (Fase 1)
-Before any dispatch: `memory_search(query, top_k=2, namespace="council_decisions")`
-- Score > 0.85 AND age < 30 days → return precedent verbatim with note "⚠️ Decisão de [data] — reavaliar se contexto mudou". SKIP entire dispatch.
-- Score > 0.85 AND age > 30 days → return precedent with ⚠️ "Reavaliar se contexto mudou — decisão tem mais de 30 dias"
-- Else → proceed to Step 0b
+Run the precedent read path defined in `## Memory Protocol > Council Decisions Namespace` (`memory_search(query, top_k=2, namespace="council_decisions")`). If no precedent applies, proceed to Step 0b.
 
 ### Step 0b — Apollo Pre-Scan (Fase 2, --research flag)
 If `/pantheon --research <question>`: dispatch @apollo with 30s timeout. Inject findings as `shared_context` into ALL specialist prompts. Skip if flag absent.
@@ -190,33 +187,11 @@ task(subagent_type: "themis", prompt: "Audit this council synthesis for fidelity
 - If issues → fix each issue before delivering to user
 
 ### Step 9 — Persist & Reconcile (Fase 1)
-```
-memory_store({
-  namespace: "council_decisions",
-  key: "council:<yyyy-mm-dd>:<slug>",
-  value: JSON.stringify({
-    question, specialists, recommendation, confidence,
-    agreements, divergences, precedent_used, timestamp
-  }),
-  metadata: {type: "council_decision", specialist_count: N}
-})
-board.markReconciled("<task-id>")
-```
+Persist the decision using the write path in `## Memory Protocol > Council Decisions Namespace`, then `board.markReconciled("<task-id>")`.
 
 ## Specialist Output Format (Fase 1 — machine-parseable structured fields)
 
-Specialists MUST return these structured fields in their response:
-
-```
-## specialist_response
-**position:** <clear one-sentence position>
-**reasoning:** <2-4 sentences>
-**trade_offs:** <what's gained vs lost>
-**risks:** <what could go wrong>
-**confidence:** High | Medium | Low
-**agreement_signals:** agree: @agent1, @agent2 on [issue] | disagree: @agent3 on [issue]
-**specific_claims:** <count of specific factual claims in response>
-```
+Specialists MUST return the structured `## specialist_response` format (position, reasoning, trade_offs, risks, confidence, agreement_signals, specific_claims) defined in `## Agent Return Format > Council Specialist Response Format`.
 
 ## Domain-to-Specialist Mapping
 

package/src/instructions/zeus-timeout-retry.instructions.md

@@ -126,39 +126,14 @@ ANY NO  → full task (IMPL artifact + Themis review mandatory)
 3. **No Themis dependency** — output doesn't feed into a phase that requires review
 
 ## Subtask Return Format
-Expect a `subtask_summary` response with:
-```
-## subtask_summary
-**files_changed:** [paths]
-**summary:** What was done
-**tests:** ✅ or N/A
-**status:** complete | partial | escalated
-```
+Return the standard `## subtask_summary` defined in `## Agent Return Format` (files_changed, summary, tests, coverage, tokens, status, blockers).
 
 ## Timeout Parcial (Partial Results)
 
-Timeout parcial is ONLY for read-only, independent agents:
-- ✅ @apollo — can return partial file list ("found 7 of 12 files before timeout")
-- ✅ @gaia — can return partial literature findings
-
-- ✅ @talos — can confirm progress if hotfix times out
-- ❌ Never for implementers or reviewers — must complete or fail
-
-When dispatching with partial-OK, set expectation:
-```
-@apollo Search for auth files. Timeout parcial OK — return whatever you have.
-```
+Only agents marked ✅ in the Timeout Behavior table above may return partial results: @apollo (partial file list, e.g. "found 7 of 12 files before timeout"), @gaia (partial literature findings) and @talos (confirm progress if a hotfix times out). Never for implementers or reviewers — they must complete or fail. When dispatching with partial-OK, set the expectation: `@apollo Search for auth files. Timeout parcial OK — return whatever you have.`
 
 ---
 
 # 📊 TIMEOUT TRACKING
 
-Maintain awareness of in-flight delegations:
-
-| Agent | Timeout | Status | Partial OK? |
-|-------|---------|--------|-------------|
-| @apollo | 60s | ✅ complete | ✅ |
-| @hermes | 180s | ⏳ in progress | ❌ |
-| @themis | 120s | ⏳ in progress | ❌ |
-
-Log timeouts to `/memories/session/timeout-log.md` for later analysis.
+Track in-flight delegations against the Timeout Behavior table above. Log timeouts to `/memories/session/timeout-log.md` for later analysis.

package/src/mcp/toon_codec.py

@@ -9,7 +9,7 @@ absent/fails.
 Only the standard library (``json`` + ``re``) — prohibited: external
 gateway, generative embedding.
 
-Encoding rules (mirrored byte-for-byte by ``src/pantheon/toon-codec.ts``):
+Encoding rules:
 
 - Scalars: ``None``/``True``/``False`` → ``null``/``true``/``false``;
   numbers → shortest form; strings bare when unambiguous, else
@@ -20,8 +20,7 @@ Encoding rules (mirrored byte-for-byte by ``src/pantheon/toon-codec.ts``):
 - Lists of scalars: ``- item`` lines; empty list → ``[]``.
 - Lists of dicts with uniform keys: ``@table k1|k2`` header + ``v1|v2``
   rows (savings are per payload class — ~11% on content-dominated board
-  records up to ~47% on large tabular checkpoints — see
-  ``docs/ws3-token-opt-measurements.md`` for the reproducible table).
+  records up to ~47% on large tabular checkpoints).
 - Dict values never need quoting for ``:`` (split is on the FIRST colon);
   list items / top-level scalars that look like ``key: ...`` are quoted.
 """
@@ -471,7 +470,6 @@ def toon_size_report(value: Any) -> dict[str, Any]:
     Reports BOTH chars and tokens: token ratios on tiny payloads suffer
     ceiling bias (``ceil`` rounds 161→41 vs 143→36), so the char columns are
     the honest basis and the token columns show what metering will debit.
-    Per-class numbers: see ``docs/ws3-token-opt-measurements.md``.
     """
     compact_json = json.dumps(value, ensure_ascii=False, separators=(",", ":"))
     toon = toon_encode(value)

package/src/pantheon/background-job-board.ts

@@ -2,7 +2,7 @@
  * Background Job Board — state machine for tracking background agent jobs.
  *
  * Tracks jobs through a state machine (running → completed/error/cancelled → reconciled),
- * supports alias generation per session, persistence via adapter, auto-wake signal files,
+ * supports alias generation per session, persistence via adapter, wake signal files,
  * and terminal state listeners (persist-before-notify write-ahead-log pattern).
  *
  * Pure TypeScript — zero external dependencies beyond Node.js builtins (fs/path).
@@ -123,7 +123,7 @@ export interface BoardOptions {
   /** Maximum completed jobs kept per agent for reuse (default: 3). */
   maxReusablePerAgent?: number
   /**
-   * Directory for auto-wake signal files.
+   * Directory for wake signal files.
    * When set, a `.signal.json` file is atomically written on every terminal transition.
    * When null or undefined, no signal files are written.
    */
@@ -175,7 +175,7 @@ function getAgentPrefix(agent: string): string {
  * - Strict state machine with validated transitions
  * - Per-session, per-agent alias generation (apo-1, her-2, …)
  * - Optional persistence via injected PersistenceAdapter
- * - Optional auto-wake signal files on terminal transitions
+ * - Optional wake signal files on terminal transitions
  * - Terminal state listeners with persist-before-notify guarantee
  * - expire/prune helpers for session lifecycle management
  */
@@ -652,7 +652,7 @@ export class BackgroundJobBoard {
   }
 
   /**
-   * Delete the auto-wake signal file for an alias (`<alias>.signal.json`).
+   * Delete the wake signal file for an alias (`<alias>.signal.json`).
    * No-op (false) when no signalDir is configured or the file is absent.
    * The delegate manager calls this on the spot right after auto-reconcile.
    */