Commit Graph
2691 Commits
Author SHA1 Message Date
Charles YaoandClaude Opus 4.8 ba7692e2e9 feat(dify-builder): log build_nodes empty/failed generation and starved resource sources
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:48 -07:00
Charles YaoandClaude Opus 4.8 6f27a709ba feat(dify-builder): log llm-agent model-resolution failure once per advance
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:48 -07:00
Charles YaoandClaude Opus 4.8 133e8fdc0c refactor(dify-builder): remove unused propose_build_repair from agent Protocol
It was stubbed to [] in LlmBuilderAgent, canned in PlaceholderAgent, and never
called by any handler — the Build failure path reuses Fix cognition (diagnose +
propose_repair). Removed from the DifyBuilderAgent Protocol, both implementations,
and all test doubles.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:48 -07:00
Charles YaoandClaude Opus 4.8 d2cfaf7f72 fix(dify_builder): narrow input-failure signals, fix build delete/create id collision
Final-review fix wave for the testdata-gate + start-selector slice:

- I1 (Important): is_input_failure's signal list included the bare
  "required" (and generic "variable not found"), which also fire on
  config/runtime faults unrelated to test inputs -- misrouting those
  failures to the *_AWAIT_TESTDATA gate, where the diagnosed auto-repair
  is never offered and re-running just loops at the gate. Narrowed
  _INPUT_FAILURE_SIGNALS to ("file variable", "not provided", "missing
  input"), favoring precision per the spec's ambiguous-failure ->
  config-repair safe default. The real file-input E2E error ("File
  variable not found for selector: [...]") still matches via "file
  variable".

- M2 (Minor, latent): handle_plan_approval's from-scratch delete-then-
  create-filter path could drop a generator create_node/connect that
  reuses a just-deleted placeholder start's id, since _already_present
  compared against the PRE-delete existing_node_ids/existing_edges --
  delete with no re-create, silently vanishing the node. Deleted ids are
  now excluded from that comparison set; the loop-back path (no deletes)
  is unaffected.

- Cleanups: state.py's Build/Edit state-count comments (14->15, 9->10,
  verified against the actual enum members), FormCard's docstring now
  lists the "testdata" variant, and handle_plan_approval binds
  current_graph's nodes to one local instead of calling .get() 3x and
  documents the delete-placeholder branch.

Tests: extended test_is_input_failure_matches_input_signals's sibling
with a config "required" case (red before the signal-list fix, green
after), and added a plan_approval test where the generator's create_node
reuses the deleted placeholder start's id (red before the id-exclusion
fix -- a dangling connect ValueError -- green after).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:48 -07:00
Charles YaoandClaude Opus 4.8 db150d1a43 feat(dify-builder): Edit live test reuses prepared input, routes input-failures to testdata gate
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:47 -07:00
Charles YaoandClaude Opus 4.8 ef88f6532c feat(dify-builder): EDIT_AWAIT_TESTDATA gate + run_affected_tests routing
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:47 -07:00
Charles YaoandClaude Opus 4.8 cea65957bb feat(dify-builder): Build live test reuses prepared input, routes input-failures to testdata gate
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:47 -07:00
Charles YaoandClaude Opus 4.8 4f6a5f07b7 feat(dify-builder): BUILD_AWAIT_TESTDATA gate + run_test routing
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:47 -07:00
Charles YaoandClaude Opus 4.8 1dda1d3326 feat(dify-builder): is_input_failure + testdata_form_fields core helpers
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:47 -07:00
Charles YaoandClaude Opus 4.8 20d932177c fix(dify-builder): drop draft placeholder start on from-scratch build
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:47 -07:00
Charles YaoandClaude Opus 4.8 86341638df fix(dify-builder): keep generator node ids in graph_translate (no start rename)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-30 10:03:47 -07:00
twwu 433046e0de Merge branch 'main' into feat/dify-builder 2026-08-30 14:25:22 +08:00
Charles YaoandClaude Opus 4.8 8b640e44de Fix Dify Builder live-test escape paths to reset stale test inputs
Clear fc.test_input_ref and fc.verify_run_id on the four re-plan/revert
escape branches in Build and Edit (handle_review's continue_adjusting
and handle_reverted's retry_after_revert) so a rebuild+retest
regenerates fresh schema-shaped mock inputs instead of reusing the
first build's stale ones -- the approve_repair retest path is left
untouched since it must fairly retest against the same failing case.
Also corrects three doc/comment mismatches (llm_agent's 12->13 method
count, an await_repair docstring describing a branch that doesn't
exist, and state.py's Build state-count banner), and adds tests for
the run_draft-raises degrade path and Build/Edit pass-path canvas
event symmetry.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 19:26:48 -07:00
Charles YaoandClaude Opus 4.8 53f805dbf7 test(dify-builder): restore canvas + summary-variant assertions on Edit test pass path
Task B2 review found that removing the old canned test_test_affected_paths_
emits_result_and_reaches_review test dropped two pass-path assertions that
none of the 4 replacement tests reproduced: that the success path fires both
the mark_test_success and mark_review_ready canvas events, and that the
emitted SummaryCard's variant is "review". Restore both onto
test_edit_test_pass_goes_to_review_with_real_run so a regression on either
point is caught again.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 19:11:20 -07:00
Charles YaoandClaude Opus 4.8 b3e9f1df3d feat(dify-builder): live Edit test via run_draft, fail routes to repair gate
Rewrite handle_test_affected_paths from a canned always-success stub to a
live handler mirroring Build's handle_test_and_repair (A5): derive mock
inputs once via start_schema/generate_mock_inputs and persist a TestInput
(reused on retest), run run_draft (degrading to a synthesized failed Run on
exception), and mint a real immutable Run. Pass -> edit.review with a green
TestResultCard + summary. Fail -> real diagnose/propose_repair, stage
fc.diagnosis/staged_repair/risk, emit a red TestResultCard + ErrorCard (+
ChangeSetCard when intents are proposed) -> edit.await_repair (the B1 gate).
No auto-apply; apply_repair still runs only inside handle_await_repair's
approve_repair branch.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 19:04:29 -07:00
Charles YaoandClaude Opus 4.8 ac5f48a765 feat(dify-builder): EDIT_AWAIT_REPAIR gate + handler
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 18:53:09 -07:00
Charles YaoandClaude Opus 4.8 f6d822a2db test(dify-builder): cover fail-path card assembly and no-repair branch
Extends the fail-routes-to-await-repair test to assert card content
(error tone, diagnosis body/node_id, change_set presence, mark_test_error
canvas event) and adds a dedicated test for the no-proposed-intents fail
branch, plus a light card-shape check on the pass path. Closes the
test-coverage gaps left by removing the old canned-arc tests in the A5
live-test rewrite.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 18:43:12 -07:00
Charles YaoandClaude Opus 4.8 badb67c720 feat(dify-builder): live Build test via run_draft, fail routes to repair gate
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 18:33:32 -07:00
Charles YaoandClaude Opus 4.8 26fdde78c2 feat(dify-builder): BUILD_AWAIT_REPAIR gate + handler
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 18:20:29 -07:00
Charles YaoandClaude Opus 4.8 d3584d3e12 test(dify-builder): live-run FakeBuildDifyPort.run_draft (pass/fail toggle)
Upgrade FakeBuildDifyPort.run_draft from canned stub to real fail-then-pass fake. Add mutable verify_pass flag (default True) and run_draft_inputs tracking, mirroring FakeDifyPort behavior. Emits node events and returns Run with per_node (succeeded when verify_pass, else failed node with error). FakeEditDifyPort inherits the live behavior automatically since it only overrides __init__.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 18:08:32 -07:00
Charles YaoandClaude Opus 4.8 bbbf2ff457 feat(dify-builder): real schema-shaped generate_mock_inputs
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 18:01:16 -07:00
Charles YaoandClaude Opus 4.8 e2b9e3aba3 feat(dify-builder): start_schema core helper (start node variables)
Implement start_schema(graph: Graph) -> StartSchema that reads the start
node's declared input variables from graph.nodes[].data.variables into
{"variables": [...]}. Pure dict access — stays in core without importing
services. Returns {"variables": []} when there is no start node or it
declares no variables.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 17:52:36 -07:00
Weike Zhang 02f9b3ca7c refactor: pass db.session explicitly in instruction_modify_workflow (#37403) (#40827) 2026-08-30 00:48:00 +00:00
Charles YaoandClaude Opus 4.8 cd5fb6bbf0 fix(dify-builder): ground model on all model-bearing nodes, carry branch handles, clean test lint
Final consolidated fix wave from whole-branch review of the Real Build +
Edit Cognition slice:

- _ground now overwrites the model dict on ANY create_node whose config
  carries a model dict (llm, question-classifier, parameter-extractor),
  not just "llm", so a drifted/hallucinated provider/name on those other
  node types no longer flows through ungrounded.
- to_intents now carries a generator edge's sourceHandle/targetHandle
  into the connect intent's args (source_handle/target_handle) so
  branching nodes (if-else, question-classifier) wire onto the correct
  port instead of collapsing onto the default handle; edges without
  handles still produce bare {from_node, to_node} args.
- Cleared the 17 ruff errors (PT018/E302/E306/E501) across the slice's
  test files by splitting composite asserts, adding missing blank
  lines, and wrapping long lines -- no assertions weakened, no noqa.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 14:22:19 -07:00
Charles YaoandClaude Opus 4.8 27be3de30a feat(dify-builder): wire real Edit cognition into LlmBuilderAgent
analyze_impact/propose_edit_plan/build_edit_intents now call
services.dify_builder.agent.edit.* via _model_or_none() instead of
delegating to the canned PlaceholderAgent. 9 of the Protocol's 14
Build/Edit/Fix methods now use real LLM cognition; only
generate_mock_inputs and propose_build_repair (returns []) remain
deferred pending the live-test step.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 14:00:58 -07:00
Charles YaoandClaude Opus 4.8 f801481fdc fix(dify-builder): guard analyze_impact target_node_ids; drop ARG noqa in edit tests
analyze_impact could raise on a non-list target_node_ids from the LLM (no
isinstance guard, unlike fields/values) -- violated the never-crash
contract. Guard it the same way. Also collapse the fake models' invoke_llm
signatures to **_kwargs (underscore-prefixed, no noqa) per the ARG lint
constraint, and pin two more malformed-shape degrade paths
(build_edit_intents non-list intents, propose_edit_plan non-list plan).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 13:54:08 -07:00
Charles YaoandClaude Opus 4.8 f5458e16b3 feat(dify-builder): real Edit cognition (impact/plan/intents via Fix pattern)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 13:41:59 -07:00
Charles YaoandClaude Opus 4.8 ac2523beb6 feat(dify-builder): goal-shaped Edit rules form from cognition output
analyze_impact now returns {fields, values, target_node_ids} instead of a
flat edit_rules dict, mirroring Build's goal-shaped form (A2). Rewire
handle_capability_check to read fc.form_fields/edit_rules/edit_target_node_ids
from that shape and render the FormCard via build_form_fields;
handle_impact_analysis merges the submitted payload on the dynamic
fc.form_fields keys instead of a fixed key tuple; handle_review's re_fix
branch re-renders the form the same way. Delete the now-dead
_EDIT_RULE_FIELDS/_EDIT_RULE_KEYS constants. PlaceholderAgent.analyze_impact
returns the new shape (the old fields become canned fields/values), so both
it and the LLM agent (which still delegates to canned) are shape-uniform.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 13:28:30 -07:00
Charles YaoandClaude Opus 4.8 cbb1487d6a fix(dify-builder): sync cards manifest to attached cards, cover remaining Build wirings
handle_test_and_repair's AssistantTurnItem.cards was unconditional even
though error/change_set cards are now only appended when
propose_build_repair returns intents -- the manifest claimed cards that
were never attached in the neutral (empty-repair) path. Make cards
conditional to match what's actually appended, and assert it in both
branches.

Remove three noqa comments added in the prior commit that suppressed
ARG001/ARG005 on new test code (the global constraint disallows noqa
for non-enabled rules); switch the genuinely-unused monkeypatch
args/lambda params to underscore-prefixed names instead, and drop a
build_nodes monkeypatch that exercised nothing. Add
test_remaining_build_methods_thread_model_and_tenant_args to cover
propose_plan_v1/discover_resources/bind_resources/build_nodes/
learn_from_build's model/tenant_id/model_config threading, matching
the existing analyze_goal coverage.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 13:14:08 -07:00
Charles YaoandClaude Opus 4.8 8683e6517c feat(dify-builder): wire real Build cognition + neutral empty test-repair
LlmBuilderAgent's 6 Build methods (analyze_goal, propose_plan_v1,
discover_resources, bind_resources, build_nodes, learn_from_build) now
delegate to services.dify_builder.agent.build instead of the canned
PlaceholderAgent. propose_build_repair returns [] -- there's no real
failure signal to diagnose until the live test step is de-canned.

handle_test_and_repair now conditions the error card + apply_repair on
a non-empty propose_build_repair result: placeholder mode keeps today's
"found and fixed" arc, while real cognition (which never reports a
failure yet) emits a neutral "no issues found" review summary instead
of a fake error/fix on a hardcoded node id that real build_nodes
wouldn't have generated anyway.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 12:25:14 -07:00
Charles YaoandClaude Opus 4.8 02edd73204 fix(dify-builder): stop fabricating llm completion_params, dedupe dataset_ids grounding
Grounding only overwrites provider+name on an llm node's model dict now,
preserving whatever mode/completion_params the generator produced instead
of synthesizing a temperature when none was present. knowledge-retrieval
grounding now assigns each node its own dataset_ids list copy instead of
aliasing one shared list across every KB node in the graph.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 12:15:08 -07:00
Charles YaoandClaude Opus 4.8 dc85ea51a2 feat(dify-builder): build_nodes via WorkflowGenerator with model+dataset grounding
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 12:04:58 -07:00
Charles YaoandClaude Opus 4.8 0ba1f932a9 fix(dify-builder): address review findings for build.py cognition
- Fix S110: replace bare except-pass with explicit degrade behavior
- Fix E501: wrap long function signatures to <=120 chars
- Fix I001: sort imports in test file (resources to top)
- Fix PT018: split composite assertions into separate statements
- Add _BoomInstance for provider-error testing
- Add 5 degrade tests (analyze_goal, propose_plan_v1 x2, discover_resources, learn_from_build)
- Remove unused _KIND_BY_PREFIX dict
- Add noqa comments for test mock arguments

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 11:50:40 -07:00
Charles YaoandClaude Opus 4.8 2e77396d39 feat(dify-builder): real Build light cognition (analyze/plan/discover/bind/learn)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 11:40:05 -07:00
Charles YaoandClaude Opus 4.8 bcd0f59100 fix(dify-builder): prevent duplicate start node ids on multiple starts
Only map the first start-type node to canonical 'start'; additional starts
retain their original ids to prevent collisions and ambiguous intents.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 11:36:02 -07:00
Charles YaoandClaude Opus 4.8 4ec3e5bfe7 feat(dify-builder): translate generator graph into build intents
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 11:30:08 -07:00
Charles YaoandClaude Opus 4.8 a5f8d71eb7 fix(dify-builder): dataset visibility + normalization guard + test coverage
FINDING 1 (dataset visibility): DatasetService.get_datasets requires user
parameter and silently omits ONLY_ME/PARTIAL_TEAM datasets on RBAC tenants.
Query Dataset model directly by tenant_id for complete grounding inventory.

FINDING 2 (normalization guard): Move fetch+normalize inside _safe to prevent
malformed records from raising after _safe returns. Use lambda builders to wrap
complete resource transformation including record normalization.

FINDING 3 (test coverage): Add test_mixed_failure_partial_success (one source
fails, others succeed) and test_malformed_tool_record_degrades (missing
tool_name key gracefully degrades).

Minor: compute model id once and reuse for both id and label fields; ensure
E302 two blank lines between test functions.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 11:24:56 -07:00
Charles YaoandClaude Opus 4.8 d976f9bf66 feat(dify-builder): tenant resource inventory (models/datasets/tools)
Implement resources.py with list_tenant_resources() to normalize tenant's
configured models, datasets, and tools to ResourceRef(id, label, meta,
readiness). Each source degrades to empty list on failure for graceful
degradation.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 11:15:57 -07:00
Charles YaoandClaude Opus 4.8 14bd9425d6 feat(dify-builder): goal-shaped Build requirements form from cognition output
analyze_goal now returns {fields, values} instead of a flat requirements
dict, so the Build capability-check form renders whatever fields the
agent (placeholder or LLM) proposes rather than a hardcoded 6-field
constant. handlers_fix.build_form_fields whitelists/coerces the agent's
raw field specs into FormField (unknown type -> text). handle_goal_analysis
now merges submitted values against the dynamic fc.form_fields keys
instead of the deleted _REQUIREMENT_KEYS constant.

Also updates test_placeholder_agent.py's analyze_goal shape assertion,
which broke as a direct consequence of the new {fields, values} contract.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 11:06:47 -07:00
Charles YaoandClaude Opus 4.8 28a4dad58f feat(dify-builder): persist goal-shaped form_fields on context
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 10:54:36 -07:00
jjj-n 09054169c4 refactor(models): pass session into Workflow accessors (#41464) 2026-08-29 14:28:15 +00:00
Asuka Minato 0f3cde8120 test: migrate application DSL sessions and ORM models to SQLite (#40554) 2026-08-29 14:06:07 +00:00
Asuka Minato 2bdcbe96c5 test: enforce centralized config overrides (#40869) 2026-08-29 14:05:35 +00:00
Asuka Minato 3824323fe7 test: centralize core and service config overrides (#40868) 2026-08-29 14:05:34 +00:00
Charles YaoandClaude Opus 4.8 e44ab9bb57 fix(dify-builder): broaden filter_applicable's except, fix stale docstring + typo
filter_applicable's per-intent try/except only caught (ValueError, TypeError),
so a hallucinated insert_between with a non-dict edge arg raised an uncaught
AttributeError and crashed the whole advance instead of being rejected by the
dry-run. Broaden to except Exception (ruff does not flag it, so no noqa is
added). Add a regression test for the string-edge case.

Also update llm_agent.py's stale module docstring (Fix cognition is now real,
not delegated; Protocol has 14 methods, not 13) and fix a stray closing paren
in a test_handlers_fix.py comment.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 02:39:08 -07:00
Charles YaoandClaude Opus 4.8 d5a8f5021f feat(dify-builder): explain the no-automatic-fix outcome in handle_propose
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 02:23:08 -07:00
Charles YaoandClaude Opus 4.8 8a1f0382d3 feat(dify-builder): wire LlmBuilderAgent Fix methods to real cognition
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 02:12:46 -07:00
Charles YaoandClaude Opus 4.8 8078f5c169 fix(dify-builder): resolve connect-intent endpoint types in _touched_node_types
_touched_node_types looked up connect intents via a nonexistent node_id key,
always resolving to "" and missing the external-side-effect type of either
endpoint. Branch connect on from_node/to_node instead, and add a test proving
the external risk floor fires on a non-structural set_node_config against an
http-request node.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 02:03:59 -07:00
Charles YaoandClaude Opus 4.8 024c76f032 feat(dify-builder): real Fix propose_repair with dry-run validation + risk floor
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 01:56:13 -07:00
Charles YaoandClaude Opus 4.8 a84491071f feat(dify-builder): real Fix diagnose + diagnose_checklist cognition
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-29 01:46:55 -07:00