From 4e77b8397e0303ae61d89a5e7a1cb3183b99a49e Mon Sep 17 00:00:00 2001 From: CREDO23 Date: Wed, 1 Jul 2026 00:11:04 +0200 Subject: [PATCH] docs(revamp): reshape Orchestration into Phase 7 --- plans/backend/revamp/07-orchestration.md | 150 ++++++++++++++--------- 1 file changed, 89 insertions(+), 61 deletions(-) diff --git a/plans/backend/revamp/07-orchestration.md b/plans/backend/revamp/07-orchestration.md index 81116a591..13e8f4654 100644 --- a/plans/backend/revamp/07-orchestration.md +++ b/plans/backend/revamp/07-orchestration.md @@ -1,95 +1,123 @@ -# Domain ⑥ — Orchestration / Conversation (the CI-expert subagent) (CI pivot revamp · WIP) +# Phase 7 — Orchestration / Conversation (the CI-expert subagent) -> **WIP design doc.** Part of the Phase 4 → end revamp. This is the **human-facing brain** that turns -> Decision-0 ("natural language is the only surface", `02-access.md`) into a real deliverable. +> **Phase 7** of the CI-pivot revamp — the **human-facing brain** that turns "natural language is the only +> surface" (`04b`, Decision 0) into a real deliverable. **Build last** — it sits atop `04`–`06`. +> **Depends on** all prior phases: `04a` verbs, `04b` doors + `deliverable_wait`, `05a`/`05b` Tracker + +> Timeline, `06` refresh triggers. > **Scope guardrail:** the multi-agent chat **runtime** (deepagents, subagent dispatch, streaming, > citation middleware, `deliverable_wait`) is SHIPPED/FIXED. What's **net-new here** is one builtin > subagent + its tools + its prompt. We *plug into* the runtime; we don't rebuild it. -## Why this is a first-class deliverable +## Objective -The intent router + verb-composition + Tracker-crafting are where "user-friendly" is won or lost. Treating -the agent prompt/tooling as plumbing would make the product feel rigid. So the orchestration layer gets -designed, not assumed. +Ship the **`intelligence_agent`** — a net-new builtin CI-expert subagent — so users get the whole product +through plain conversation: intent routing (one-shot vs standing concern), verb composition, Tracker +crafting, and decision-grounded answering. The intent router + verb-composition + Tracker-crafting are +where "user-friendly" is won or lost, so the orchestration layer is **designed, not assumed**. -## The pattern we reuse (verbatim) +## Current state (cited) -Builtin subagents live at `subagents/builtins//`: -``` -agent.py build_subagent(...) → pack_subagent(name, description, system_prompt, tools, ruleset, …) -tools/index.py NAME · RULESET · load_tools(dependencies) -description.md one-liner the router uses to delegate -system_prompt.md the playbook -(middleware) e.g. citation_state -``` -`research/tools/scrape_webpage.py` already shows the **tool = capability executor + access door + 03c -billing** shape: it calls `WebCrawlerConnector.crawl_url`, bills via the turn accumulator -(`get_current_accumulator()` + `WebCrawlCreditService`), returns a typed dict. Our capability/CI tools -follow this exactly. +- **Builtin subagent pattern** — `subagents/builtins//`: `agent.py` (`build_subagent(...)` → + `pack_subagent(name, description, system_prompt, tools, ruleset, …)`), `tools/index.py` + (`NAME · RULESET · load_tools(dependencies)`), `description.md` (router one-liner), `system_prompt.md` + (the playbook), optional middleware (e.g. `citation_state`). Peers: `research`, `deliverables`. +- **Tool shape** — `research/tools/scrape_webpage.py` already demonstrates **tool = capability executor + + access door + 03c billing**: calls `WebCrawlerConnector.crawl_url`, bills via the turn accumulator + (`get_current_accumulator()` + `WebCrawlCreditService`), returns a typed dict. CI tools follow this exactly. +- **Slow-job path** — `deliverable_wait` poll-until-terminal + the podcast-style live card (`04b`). -## What's new — the `intelligence_agent` subagent (CI expert) +## Target design -A new builtin `subagents/builtins/intelligence_agent/` (the competitive-intelligence specialist), -peer to `research`/`deliverables`. The **main agent delegates** to it whenever the request is -CI-flavored (research a competitor, watch something, analyze a place's reviews); `description.md` is -what makes that routing happen. +### The `intelligence_agent` subagent (CI expert) -It owns the **CI playbook** in `system_prompt.md`: +A new builtin `subagents/builtins/intelligence_agent/` (the competitive-intelligence specialist), peer to +`research`/`deliverables`. The **main agent delegates** to it whenever the request is CI-flavored (research +a competitor, watch something, analyze a place's reviews); `description.md` is what makes that routing +happen. It owns the **CI playbook** in `system_prompt.md`: -1. **Intent routing (A vs B)** — the Decision-0 rule, in-prompt: one-shot ("compare/find/what is") - → call verbs & answer; standing concern ("watch/track/notify when/weekly") → run the crafting flow; - ambiguous → ask the single clarifying question. +1. **Intent routing (A vs B)** — the Decision-0 rule, in-prompt: one-shot ("compare/find/what is") → call + verbs & answer; standing concern ("watch/track/notify when/weekly") → run the crafting flow; ambiguous → + ask the single clarifying question. 2. **Verb composition** — the chains: `web.discover → web.scrape`, `maps.search → maps.place → maps.reviews`; infer URLs/queries/locations from context so the user never supplies them by hand. -3. **Tracker crafting** (the "crafting" you flagged) — the conversational schema-design flow from `03`: - sample-fetch → propose `field_schema` + materiality + identity → user validates & locks → versioned. -4. **Decision-grounded answering** — read the Timeline (`04`) to answer "what changed / is X pulling +3. **Tracker crafting** — the conversational schema-design flow from `05b`: sample-fetch → propose + `field_schema` + materiality + identity → user validates & locks → versioned. +4. **Decision-grounded answering** — read the Timeline (`05a`) to answer "what changed / is X pulling ahead?" from stored deltas, not by re-deriving from chat history. -## The toolset (what `load_tools` returns) +### The toolset (what `load_tools` returns) | Tool | Wraps | Mode | Billing | |------|-------|------|---------| -| capability verbs (`web.scrape`, `web.discover`, `maps.search`, `maps.place`, `maps.reviews`) | Domain ① executors | inline-or-job (slow → `deliverable_wait`) | `03c` turn accumulator (as `scrape_webpage` already does) | -| `craft_tracker(decision, binding)` | `03` schema-design agent | inline (does the sample-fetch + proposes) | sample crawl billed | -| `lock_tracker(draft)` / `update_tracker` | `03` Tracker persistence | inline | — | -| `refresh_tracker(tracker_id)` | `03` `refresh(tracker)` | job → `deliverable_wait` | per capability call | -| `query_timeline(tracker_id, …)` | `04` read API | inline | — | -| `list_trackers()` | `04`/`03` read | inline | — | +| capability verbs (`web.scrape`, `web.discover`, `maps.search`, `maps.place`, `maps.reviews`) | `04a` executors | inline-or-job (slow → `deliverable_wait`) | `03c` turn accumulator (as `scrape_webpage` already does) | +| `craft_tracker(decision, binding)` | `05b` schema-design agent | inline (sample-fetch + proposes) | sample crawl billed | +| `lock_tracker(draft)` / `update_tracker` | `05b` Tracker persistence | inline | — | +| `refresh_tracker(tracker_id)` | `05b` `refresh(tracker)` (via `06`) | job → `deliverable_wait` | per capability call | +| `query_timeline(tracker_id, …)` | `05a` read API | inline | — | +| `list_trackers()` | `05a`/`05b` read | inline | — | -- **Capability verbs are a shared tool module** (generated from the Domain ① registry) — `research` - can load the same ones; the `intelligence_agent` additionally loads the Tracker/Timeline tools + the CI prompt. +- **Capability verbs are a shared tool module** (generated from the `04a` registry) — `research` can load + the same ones; the `intelligence_agent` additionally loads the Tracker/Timeline tools + the CI prompt. (`scrape_webpage` is the seed; generalize it into the registry-backed set.) - **Slow verbs** (`maps.search`, multi-URL `web.scrape`, `refresh_tracker`) dispatch a job and use the - existing `deliverable_wait` poll-until-terminal + live-card path (`02-access.md`). + existing `deliverable_wait` poll-until-terminal + live-card path (`04b`). -## Boundaries +### Boundaries -- **Orchestration ≠ Intelligence.** The `intelligence_agent` *drives* `03`/`04` via tools; the hot loop, - materiality, and Timeline writes live in `03`/`04`, callable headless (so REST/MCP and Triggers reach - the same logic with no agent in the loop). +- **Orchestration ≠ Intelligence.** The `intelligence_agent` *drives* `05a`/`05b` via tools; the hot loop, + materiality, and Timeline writes live in `05a`/`05b`, callable headless (so REST/MCP and Triggers reach the + same logic with no agent in the loop). - **Humans get the agent; machines get raw verbs.** REST/MCP callers (devs/external agents) skip this - subagent entirely and call Domain ① verbs directly — they *want* explicitness. + subagent entirely and call `04a` verbs directly — they *want* explicitness. -## MVP cut vs north star +## Work items -- **MVP:** the `intelligence_agent` subagent + description/prompt · capability verb tools (registry-backed) · - `craft_tracker`/`lock_tracker`/`refresh_tracker`/`query_timeline`/`list_trackers` · intent routing in-prompt. -- **North star (deferred):** richer multi-step CI playbooks (auto competitor discovery → multi-Tracker - setup), proactive "you should watch this" suggestions, cross-Tracker synthesis. +1. **Subagent scaffold**: `subagents/builtins/intelligence_agent/` with `agent.py` / `tools/index.py` / + `description.md` / `system_prompt.md`, packed via `pack_subagent`. +2. **CI playbook prompt**: intent routing (A/B + one clarifying question), verb chains, crafting flow, + decision-grounded answering. +3. **Shared verb tool module**: registry-backed (`04a`) capability tools, reusable by `research` too. +4. **Tracker/Timeline tools**: `craft_tracker` / `lock_tracker` / `update_tracker` / `refresh_tracker` / + `query_timeline` / `list_trackers`. +5. **Slow-verb wiring**: route job-mode tools through `deliverable_wait` + the live card. +6. **Router registration**: `description.md` so the main agent delegates CI-flavored requests here. -## Locked decisions +## Tests -1. CI orchestration is a **net-new builtin subagent** (`intelligence_agent`) on the existing - runtime — not a runtime rebuild. +- **Delegation**: a CI-flavored request routes to `intelligence_agent`; a non-CI request does not. +- **One-shot**: "compare X and Y" composes verbs and answers in plain language, persisting nothing. +- **Standing concern**: "watch X weekly" runs the crafting flow → lock → (refresh via `06`). +- **Crafting**: `craft_tracker` does a real sample-fetch and proposes a schema; `lock_tracker` versions it. +- **Answering**: `query_timeline` answers "what changed?" from stored deltas, not chat history. +- **Slow verb**: a multi-URL scrape surfaces a live card and returns terminal results. + +## Risks / trade-offs + +- **Prompt quality is the product**: intent-router/composition quality is a first-class deliverable, not + plumbing — budget iteration on the prompt. +- **One-shot ownership**: whether `research` keeps generic scraping or the `intelligence_agent` owns all + CI-flavored calls (lean: shared verb tools, CI agent owns the *playbook*). +- **Pre-frontend lock UX**: "review & lock" must render in pure chat for MVP (ties to `05b`'s open Q). + +## Resolved decisions + +1. CI orchestration is a **net-new builtin subagent** (`intelligence_agent`) on the existing runtime — not + a runtime rebuild. 2. Tools follow the `scrape_webpage` shape: capability executor + access door + `03c` billing. -3. Capability verbs are a **shared, registry-generated** tool module; the `intelligence_agent` adds Tracker/Timeline - tools + the CI prompt. -4. Intent routing (A vs B) lives **in the subagent prompt**; the headless logic stays in `03`/`04`. +3. Capability verbs are a **shared, registry-generated** tool module; the `intelligence_agent` adds + Tracker/Timeline tools + the CI prompt. +4. Intent routing (A vs B) lives **in the subagent prompt**; the headless logic stays in `05a`/`05b`. 5. Slow verbs reuse `deliverable_wait`; nothing new for chat-async. +## Out of scope (hand-offs) + +- **The verbs, doors, engine, state, and triggers** → `04`/`05`/`06` (this phase only *orchestrates* them). +- **Richer multi-step CI playbooks** (auto competitor discovery → multi-Tracker setup), proactive "you + should watch this" suggestions, cross-Tracker synthesis → north star (deferred). +- **Frontend CI surfaces** (cards, dashboards) → frontend umbrella. + ## Open questions (carry forward) -- Does CI one-shot scraping stay in `research`, or does the `intelligence_agent` own all CI-flavored calls (lean: - shared verb tools, `intelligence_agent` owns the *CI playbook*). -- How `craft_tracker`'s "review & lock" renders pre-frontend (pure-chat confirmation — ties to `03`'s open Q). +- Does CI one-shot scraping stay in `research`, or does the `intelligence_agent` own all CI-flavored calls + (lean: shared verb tools, `intelligence_agent` owns the *CI playbook*). +- How `craft_tracker`'s "review & lock" renders pre-frontend (pure-chat confirmation — ties to `05b`'s open Q).