update progress.md file

PROGRESS.md

@@ -51,7 +51,7 @@ Verified against code before logging. Severity: **critical** / important / nice-
 | R9 | **`extra="ignore"`** in `settings.py:15` (currently `allow` → typo'd env vars silently swallowed); require Azure keys in prod. | nice-to-have | B | `[ ]` |
 | R10 | **Read-only enforcement is session-state, not a server role.** `REPO_CONTEXT.md` counts "read-only DB credentials" as a defense layer but nothing requests/verifies a read-only role. Either request read-only creds at registration (verify via `SELECT current_setting(...)`) or drop the claim. | important | DB | `[ ]` |
 | R11 | **De-duplicate** `_PLACEHOLDER_RE` (`task_runner.py:31` vs validator) and `_DATA_ACCESS_TOOLS` (invoker vs planner registry) — import one from the other; comments aren't a sync mechanism. | nice-to-have | agent/tool | `[ ]` |
-| R12 | **Doc/process hygiene** — gitignored canonical docs (`AGENT_ARCHITECTURE_CONTEXT_new.md`, `PROJECT_SUMMARY.md`) are cited by code docstrings but absent on disk; `CLAUDE.md` lists deleted modules (enricher, `pipeline/orchestrator.py`); `main` is 38 commits behind on a dead architecture. | nice-to-have | agent | `[ ]` |
+| R12 | **Doc/process hygiene** — some code docstrings cite internal design specs that are not committed to the repo (design docs are kept out of version control), so the references dangle for anyone but the author; `CLAUDE.md` lists deleted modules (enricher, `pipeline/orchestrator.py`); `main` is 38 commits behind on a dead architecture. | nice-to-have | agent | `[ ]` |
 | R13 | **Pre-existing test failure** (found during R2, NOT caused by it): `tests/query/planner/test_prompt.py::test_render_catalog_with_sources` fails — `query/planner/prompt.py::render_catalog` now renders stable IDs (`src_test_db`) the test asserts are absent. Old query-planner path; confirmed failing on a clean tree. | nice-to-have | DB | `[ ]` |
 
 **Architecture verdict:** fundamentally sound (catalog-driven IR + deterministic compiler
@@ -167,8 +167,8 @@ across all of them.
 
 ## What just shipped (2026-06-08 — KM-626: slow-path agent layer)
 
-The rest of the slow path after the Planner (KM-567), from
-`AGENT_ARCHITECTURE_CONTEXT_new.md` §7.4 / §7.5 / §8.2–8.4. Built and tested against
+The rest of the slow path after the Planner (KM-567) — TaskRunner, Assembler, and
+the coordinator. Built and tested against
 mocks; **not yet wired into the live `ChatHandler`** (waits on the tool team's real
 `ToolInvoker` + a real `BusinessContext`). Fast path untouched.
 
@@ -177,9 +177,9 @@ The slow-path **workers** live in **`agents/slow_path/`** — deliberately NOT n
 "orchestrator".
 
 **Files added** (`src/agents/slow_path/`):
-- `schemas.py` — `TaskResult`, `RunState` (§8.2); `TaskSummary`, `AnalysisRecord`,
-  `AssembledOutput`, `AssemblerNarrative` (§8.3). Reuses `ToolOutput`.
-- `invoker.py` — `ToolInvoker` Protocol only (§8.4); the tool team owns the impl (KM-418).
+- `schemas.py` — `TaskResult`, `RunState`; `TaskSummary`, `AnalysisRecord`,
+  `AssembledOutput`, `AssemblerNarrative`. Reuses `ToolOutput`.
+- `invoker.py` — `ToolInvoker` Protocol only; the tool team owns the impl (KM-418).
 - `errors.py` — `SlowPathError`, `AssemblerError`.
 - `task_runner.py` — deterministic, 0 LLM: wave-based execution, `${t<id>}` placeholder
   resolution, internal `validate_args`, never-throw invoke, status labeling,
@@ -208,7 +208,7 @@ Team decisions after the teammate pushed KM-624 (`src/tools/analytics/`):
 - **Composite tools, not atomic.** v1 uses **composite "family" tools** (`analyze_*`),
   not the atomic `compute_*` set the earlier draft assumed. One `analyze_*` call does a
   whole analytical job (e.g. `analyze_descriptive` subsumes median/mode/stddev/percentile;
-  `analyze_trend` subsumes `date_trunc`). Arch doc §9.3/§9.4 + decisions table updated.
+  `analyze_trend` subsumes `date_trunc`). Tool-taxonomy decision recorded.
 - **Tool team owns ALL tools** — compute, data-access (`query_structured`,
   `retrieve_documents`, `list_sources`, `describe_source`), the wrapper/invoker layer
   (KM-418), and **all tool tests**. The agent team owns nothing below the registry contract.
@@ -232,7 +232,7 @@ then Orchestrator slow-path wiring. Stubs still to retire on integration: `contr
 
 ## What just shipped (2026-06-05 — Phase 3: Planner agent)
 
-First slow-path agent from `AGENT_ARCHITECTURE_CONTEXT_new.md` §7.3. A single LLM
+First slow-path agent (the Planner). A single LLM
 call turns BusinessContext + Catalog + ToolRegistry + question + Constraints into a
 validated, **static** `TaskList` (DAG of fully-specified tool-call chains). No
 replanning (INV-6); tool-agnostic against a registry contract (INV-7). Fast path
@@ -240,9 +240,9 @@ replanning (INV-6); tool-agnostic against a registry contract (INV-7). Fast path
 
 **Files added** (`src/agents/planner/`):
 - `contracts.py` — **STUB** Pydantic contracts pending reconciliation: `BusinessContext`
-  (+KeyTerm/DataTableNote/DataColumnNote, lead's §7.1), `ToolSpec`/`ToolRegistry` (tool
-  team KM-608, §9.2), `ToolOutput` envelope (§8.1).
-- `schemas.py` — `CrispStage`, `ToolCall`, `Task`, `TaskList` (§7.3). No replan schemas.
+  (+KeyTerm/DataTableNote/DataColumnNote, lead's), `ToolSpec`/`ToolRegistry` (tool
+  team KM-608), `ToolOutput` envelope.
+- `schemas.py` — `CrispStage`, `ToolCall`, `Task`, `TaskList`. No replan schemas.
 - `inputs.py` — `CatalogSummary` (condensed, PII `sample_values` nulled, `from_catalog`
   builder + `render`) and `Constraints` (max_tasks=5, modeling_allowed=False).
 - `registry.py` — **STUB** v1 P0 registry: query_structured, retrieve_documents,
@@ -252,7 +252,7 @@ replanning (INV-6); tool-agnostic against a registry contract (INV-7). Fast path
   per-call human content (context + catalog + tools + constraints + few-shots + question).
 - `examples.py` — two few-shots (A exploratory revenue-by-category; B descriptive
   monthly-trend-by-region with date_trunc), built from the real `TaskList` schema.
-- `validator.py` — `PlannerValidator` running the 8 checks (§7.3); reuses the existing
+- `validator.py` — `PlannerValidator` running the 8 checks; reuses the existing
   `IRValidator` for inline `query_structured` IRs.
 - `service.py` — `PlannerService` + `plan_analysis(...)`: chain (mirrors
   `query/planner/service.py`) + validate-and-retry loop (max 3, mirrors `QueryService`).
@@ -264,8 +264,8 @@ replanning (INV-6); tool-agnostic against a registry contract (INV-7). Fast path
 
 **Open follow-ups (not blockers):** reconcile `BusinessContext` with the lead and
 `ToolRegistry`/`ToolSpec` + real tools with teammate (KM-608); "GPT mini" currently uses
-the configured 4o deployment (swap `azure_deployment` when a mini deployment exists). Next
-per the architecture doc: Orchestrator slow-path expansion + TaskRunner + Assembler.
+the configured 4o deployment (swap `azure_deployment` when a mini deployment exists). Next:
+Orchestrator slow-path expansion + TaskRunner + Assembler.
 
 ---
 
@@ -378,7 +378,7 @@ per the architecture doc: Orchestrator slow-path expansion + TaskRunner + Assemb
 
 ### Tools — slow-path "Tools" component (TAB)
 
-New scope after the original 42-item table; added as the tool layer landed (KM-608/624–631). All TAB-owned (`src/tools/`), all never-throw (§8.4).
+New scope after the original 42-item table; added as the tool layer landed (KM-608/624–631). All TAB-owned (`src/tools/`), all never-throw.
 
 | # | Item | Owner | Status | Notes |
 |---|---|---|---|---|