Files
PaperClipAI/packages/db/src/migrations/0236_remove_cheap_model_profiles.sql
T
DottaandPaperclip 4b6de5327e Remove cheap model profiles (#12683)
## Thinking Path

> - Paperclip manages agents that use different model providers and
adapters.
> - Paperclip must keep agent execution rules clear and predictable.
> - The cheap-model profile added a second execution mode across
adapters, task recovery, APIs, and the UI.
> - That mode increased configuration and recovery complexity.
> - This pull request removes the cheap-model profile as a product
feature.
> - The benefit is one model-selection path for normal work and recovery
work.

## Linked Issues or Issue Description

**What existing behavior does this improve?**

This change simplifies model selection across agent configuration, task
execution, recovery, and adapter capabilities.

**Current behavior**

Paperclip exposes cheap-model profiles in adapter metadata, agent
runtime configuration, task overrides, recovery rules, APIs, and the
board UI. Recovery work can select a different model profile from the
agent's configured model.

**Proposed behavior**

Paperclip uses the agent's configured model for normal work and recovery
work. Status-only recovery stays limited to coordination work. The API
rejects legacy model-profile configuration. A migration removes stored
model-profile values from existing agent, issue, and historical revision
records.

**Reason and benefit**

One model path reduces configuration, API, UI, and recovery complexity.
It also prevents status recovery from becoming a separate product-level
model-routing feature.

**Breaking changes**

This change removes model-profile fields and adapter capability
metadata. Existing stored model-profile values are removed by an
idempotent migration. The validators reject new legacy profile values
with clear errors.

## What Changed

- Removed model-profile types, adapter capabilities, API fields, and
model selection logic.
- Removed cheap-model controls from agent and task UI surfaces.
- Kept status-only recovery limited to coordination context while normal
continuations use the configured agent model.
- Added an idempotent migration that removes stored model-profile values
from agents, issues, and configuration revisions without changing issue
update timestamps.
- Updated tests and product documentation for the single-model behavior.

## Verification

- `pnpm check:token-gates` passes.
- `pnpm -r typecheck` passes.
- `pnpm build` passes.
- `pnpm test:run` completed with 5,607 passing tests and 8
environment-sensitive failures in unrelated fixed-port and
database-deadlock suites. The same failures repeated in an isolated
rerun. CI is the final clean-room result.

## Risks

- This is an intentional breaking change for clients that send
model-profile fields.
- The migration changes legacy agent, issue, and configuration-revision
JSON. It is idempotent and preserves unrelated fields and issue update
timestamps.
- The change is cross-cutting because the removed feature existed in
adapters, shared contracts, the server, plugins, and the UI.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- OpenAI Codex with `gpt-5`. Reasoning and tool use were enabled. The
runtime did not expose the context-window size.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [ ] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-09-01 14:57:38 -05:00

109 lines
3.2 KiB
SQL

CREATE INDEX IF NOT EXISTS "agents_remove_model_profiles_idx"
ON "agents" USING btree ("id")
WHERE "runtime_config" ? 'modelProfiles';--> statement-breakpoint
DO $$
DECLARE
updated_count integer;
BEGIN
LOOP
WITH batch AS MATERIALIZED (
SELECT "id"
FROM "agents"
WHERE "runtime_config" ? 'modelProfiles'
ORDER BY "id"
LIMIT 1000
)
UPDATE "agents" AS agent
SET "runtime_config" = agent."runtime_config" - 'modelProfiles',
"updated_at" = now()
FROM batch
WHERE agent."id" = batch."id";
GET DIAGNOSTICS updated_count = ROW_COUNT;
EXIT WHEN updated_count = 0;
END LOOP;
END $$;--> statement-breakpoint
DROP INDEX IF EXISTS "agents_remove_model_profiles_idx";--> statement-breakpoint
-- paperclip:migration-safety-ignore large-create-index-not-concurrently: This temporary partial index covers only revision snapshots with the retired JSON key and is dropped after the bounded cleanup.
CREATE INDEX IF NOT EXISTS "agent_config_revisions_remove_model_profiles_idx"
ON "agent_config_revisions" USING btree ("id")
WHERE ("before_config" #> '{runtimeConfig}') ? 'modelProfiles'
OR ("after_config" #> '{runtimeConfig}') ? 'modelProfiles';--> statement-breakpoint
DO $$
DECLARE
updated_count integer;
BEGIN
LOOP
WITH batch AS MATERIALIZED (
SELECT "id"
FROM "agent_config_revisions"
WHERE ("before_config" #> '{runtimeConfig}') ? 'modelProfiles'
OR ("after_config" #> '{runtimeConfig}') ? 'modelProfiles'
ORDER BY "id"
LIMIT 1000
)
UPDATE "agent_config_revisions" AS revision
SET "before_config" = CASE
WHEN (revision."before_config" #> '{runtimeConfig}') ? 'modelProfiles'
THEN jsonb_set(
revision."before_config",
'{runtimeConfig}',
(revision."before_config" #> '{runtimeConfig}') - 'modelProfiles'
)
ELSE revision."before_config"
END,
"after_config" = CASE
WHEN (revision."after_config" #> '{runtimeConfig}') ? 'modelProfiles'
THEN jsonb_set(
revision."after_config",
'{runtimeConfig}',
(revision."after_config" #> '{runtimeConfig}') - 'modelProfiles'
)
ELSE revision."after_config"
END
FROM batch
WHERE revision."id" = batch."id";
GET DIAGNOSTICS updated_count = ROW_COUNT;
EXIT WHEN updated_count = 0;
END LOOP;
END $$;--> statement-breakpoint
DROP INDEX IF EXISTS "agent_config_revisions_remove_model_profiles_idx";--> statement-breakpoint
-- paperclip:migration-safety-ignore large-create-index-not-concurrently: This temporary partial index covers only rows with the retired JSON key and is dropped after the bounded cleanup.
CREATE INDEX IF NOT EXISTS "issues_remove_model_profile_idx"
ON "issues" USING btree ("id")
WHERE "assignee_adapter_overrides" ? 'modelProfile';--> statement-breakpoint
DO $$
DECLARE
updated_count integer;
BEGIN
LOOP
WITH batch AS MATERIALIZED (
SELECT "id"
FROM "issues"
WHERE "assignee_adapter_overrides" ? 'modelProfile'
ORDER BY "id"
LIMIT 1000
)
UPDATE "issues" AS issue
SET "assignee_adapter_overrides" = NULLIF(
issue."assignee_adapter_overrides" - 'modelProfile',
'{}'::jsonb
)
FROM batch
WHERE issue."id" = batch."id";
GET DIAGNOSTICS updated_count = ROW_COUNT;
EXIT WHEN updated_count = 0;
END LOOP;
END $$;--> statement-breakpoint
DROP INDEX IF EXISTS "issues_remove_model_profile_idx";