Commit Graph
21 Commits
Author SHA1 Message Date
Charles YaoandClaude Opus 5 fe3f8154b5 feat(dify-builder): carry node usage rules on the Builder-only directive
Meeting item 9 asked for per-node usage detail in the generator prompts.
Those prompts are shared with cmd+K, so the detail rides the channel the
Builder already owns instead: _WORKFLOW_TOPOLOGY_DIRECTIVE, prepended to
every generator instruction at build.py:377 and invisible to cmd+K. That
mechanism is proven -- it is why workflow mode never gets 'answer' nodes.

The rules added are the ones that broke real builds: tool nodes expose
text/files/json and not 'result' (ESQ1-296, ESQ1-289), document-extractor
needs a file input, container children belong inside the container
(ESQ1-288), if-else operators must match the variable's type
(ESQ1-285/290), and http-request inputs belong on the start node
(ESQ1-286).

Deliberately does NOT restate the node whitelist: the generator's shared
system prompt already carries it, and duplicating it would burn planner
output budget that ESQ1-300 already implicates.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-20 23:08:27 -07:00
Charles YaoandClaude Opus 5 f12d8f4e0f feat(dify-builder): plan in Dify node vocabulary, not business language
propose_plan_v1's system prompt was two sentences with no node vocabulary,
so it planned in business language -- "Send a Feishu notification",
"Connect to the database". Those steps became the generator's
"# User instruction" verbatim, asking it to map work onto nodes that do
not exist, and the failure only surfaced at build-generate-graph, minutes
after the user had approved the plan (ESQ1-279).

The generator already knows the node types: its SHARED system prompt
carries the whitelist. The gap was upstream, in the Builder's own planner.
Naming the vocabulary here makes that existing whitelist sufficient.

Builder-only: nothing under core/workflow/generator/ is touched, so the
cmd+K /create and /refine features are unaffected.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-20 23:05:34 -07:00
Charles YaoandClaude Opus 5 69ccf2ad15 fix(dify-builder): wire resource readiness into recommender/gap prompts
Three minor whole-branch-review fixups:

- ResourceOption.readiness ("ready"/"missing_config") was computed but never
  shown to the model: discover_resources's recommender prompt listed ids and
  labels only, so it could recommend an unauthorized tool; _GAP_SYSTEM showed
  readiness in the listing (assess_capability_gap) but never defined what
  missing_config means. Both prompts now show readiness and state that
  missing_config is installed-but-not-authorized, i.e. not usable -- pinned
  with tests asserting the literal "missing_config" in the constructed
  prompts.
- strings.py: dropped three orphaned catalogue entries ("Here's the initial
  plan.", "Ask each time", "Prefer audited") -- the conflict-policy concept
  they backed was removed end to end; nothing in the handlers emits them.
- core/workflow/generator/tool_catalogue.py: provider.need_credentials was
  read OUTSIDE the per-provider try/except that already guards
  get_tools()/tool parsing. This module is shared with the cmd+K /create and
  /refine flows, so a provider whose property raised would break those too,
  not just the Builder. Moved the read inside the try/except so a bad
  provider is skipped like any other.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-20 16:41:52 -07:00
Charles YaoandClaude Opus 5 f1bf2fb318 feat(dify-builder): say when the workspace cannot cover the plan
Add assess_capability_gap: one plain sentence naming a plan step nothing
installed can perform, or "" when the plan is covered. Grounded only in
installed resources -- there is no marketplace lookup, so it names a missing
CAPABILITY, never a product to install. A missing_config tool (installed but
unauthorized, from the prior task's real readiness) doesn't count as
covering a step either, since the model is shown each option's readiness
alongside its label and kind.

Wired through the full agent seam: the DifyBuilderAgent protocol, the real
LlmBuilderAgent (delegates to build.assess_capability_gap), and the
PlaceholderAgent test double (returns ""). handlers_build.py calls it
after discover_resources and, when non-empty, appends a NoticeItem beside
the existing empty-resources notice -- the two are independent and can
both fire.

Like its sibling cognition functions, it degrades to "" (never raises) on
no model, an LLM error, or an unparseable reply: a gap that can't be
assessed isn't a gap worth inventing. The sentence is LLM-generated prose
already in the user's language (json_language_instruction), not a
catalogue entry, so no static string was added.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-20 16:13:02 -07:00
Charles YaoandClaude Opus 5 e8b14b50ff refactor(dify-builder): drop the resource conflict policy
The resource-recommendation step made the user pick a "conflict
policy" that never decided anything. Remove it end to end: the
ConflictPolicyOption card option, ResourceSelectCard's
conflict_policy_options field, the third bind_resources() parameter
across the port/placeholder/LLM-agent implementations, and the dead
conflict_policy field on the (unused) ResourcesPayload contract type.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-20 14:10:34 -07:00
Charles YaoandClaude Opus 5 d3087cbe34 fix(dify-builder): stop recommending the whole workspace when nothing matches
discover_resources initialised its selection to the entire tenant inventory and
only replaced it when the model returned a non-empty pick, so three paths -- no
model, a model that picked nothing, a failed call -- recommended everything. On
a workspace with 57 resources that is not merely noisy: the client pre-checks
every recommendation and submits them all by default, and bind_resources then
appends all 57 labels to the last plan item, which is the text fed to the graph
generator.

Recommending nothing is the honest answer when there is no signal. The card is
still emitted so the confirm gate keeps its active interaction and a later pass
cannot inherit a stale one, and a notice says why rather than leaving a blank
card. The conflict-policy control no longer renders over an empty list.

The test that should have caught this used a one-resource catalog, where "all"
and "none" are indistinguishable; it now uses 57.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 20:09:18 -07:00
Charles YaoandClaude Opus 5 aa2b4fe4ab feat(dify-builder): name apps from their prompt, and turn gate actions into card options
Two App Builder spec changes that share the Builder session contract.

Naming (spec N1-N3): an app created from the homepage prompt is no longer named
by the user. core/dify_builder/naming.py cuts the prompt's opening clause at
create time -- instant and infallible, since it runs inside POST /apps -- and
CreateAppPayload.name becomes optional alongside a new prompt field. The Builder
then refines that name once during goal analysis, where a model and the detected
reply language are already in hand, so the judgement calls that are
English-shaped in pure Python (dropping an imperative lead-in, spotting a
contentless prompt) work in any language. Plan approval freezes the name.

Card options: SessionView gains a Decision carrying the gate's choice as options
inside the card plus a fixed confirm/cancel pair, replacing a button row whose
shape changed at every state. Option ids are the old action ids untouched, so
resolve_action_kind and the per-state legality check are unchanged, and
SessionView.actions keeps being populated -- the deployed web client goes on
working until it reads decision instead.

The regenerated console OpenAPI doc also picks up ErrorCard.diagnostics, missed
when cc9ca8b1dd landed.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 17:55:38 -07:00
Charles YaoandClaude Opus 5 cc9ca8b1dd feat(dify-builder): carry generation diagnostics into the exported debug log
api pods lose their logs on restart, so a failed build's real cause
("Workflow generator: structural validation failed: ...") could only be read
from a pod log that may already be gone. Session 01a08fd0 hit exactly that.

Carry the generator's own diagnostics back with the result instead:
BuildNodesResult and ErrorCard gain a ``diagnostics`` list, and build_nodes
records one entry per failed generation attempt -- initial AND the corrective
retry, so an error that changes between attempts stays visible -- plus the
all-rejected and exception paths.

Each entry holds a server-side UTC ``at`` (so the surviving pod-log window can
be searched around it), ``source``, ``attempt``, the generator's ``message``
(the same text the server logs), its ``codes``, and the full structured
``errors`` including ``node_id``. That is strictly more than the log line
carries: for an UNRESOLVED_REFERENCE the export now names the offending node.

The list rides in the ErrorCard's item payload, which is what the streamed
conversation item -- and therefore the exported debug log -- preserves. It is
not rendered in the UI. Retries that eventually succeed keep their breadcrumbs.

Deliberately not mirroring the "structural validation failed" prefix: build.py
cannot tell structural failures from the rest without duplicating the
generator's code taxonomy, which would go stale.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 15:16:10 -07:00
Charles YaoandClaude Opus 4.8 e59389776d fix(dify-builder): surface the specific reason in build-fail error card
When build-generate-graph failed at plan-approval, the error card always
showed one hardcoded generic message regardless of the actual cause
(UNRESOLVED_REFERENCE, non-object JSON, credit_balance_exhausted, ...).

Root cause: build_nodes() returned only list[MutationIntent]; on failure it
returned [], so the reason was logged internally but never reached the
handler, which had nothing to show but a fallback string.

Thread the reason out: build_nodes now returns BuildNodesResult{intents,
error}. _generation_error_text() extracts the best reason (top-level error
-> joined errors[].detail/message/code -> generic fallback), and every
failure path populates .error (generator error, all-intents-rejected, and
the except path via str(exc) so provider errors surface verbatim).
handle_plan_approval builds the ErrorCard body from build_result.error when
present, keeping the generic sentence only as a genuine fallback.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-09-10 21:00:47 -07:00
Charles YaoandClaude Opus 4.8 2a574c7f74 fix(dify-builder): ground built workflow nodes to the user-selected model
Build wrote the Builder's session/cognition model (e.g. deepseek) into every
generated node's model block, ignoring the model the user picked at resource
confirmation (e.g. gpt). _ground always used the generation model, and the
selected model resource only reached the plan as label text (bind_resources) —
so a workflow got a model with no runtime credentials -> ModelNotExistError ->
instant test failure.

Thread the selected resource_ids from resource_selection through
agent.build_nodes into build.build_nodes, resolve the selected MODEL resource
(id is `{provider}/{name}`) via _selected_workflow_model, and ground node model
blocks to it — falling back to the session/generator model when the user
selected no model. The generator still runs on the session model (cognition);
only the built workflow's runtime model follows the user's choice.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-09-10 19:18:36 -07:00
Charles YaoandClaude Opus 4.8 9a87125231 feat(dify-builder): instruct agent to reply in the user's language (M1)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-09-10 15:02:42 -07:00
twwu ac7db51302 fix(dify-builder): align form schema types with values 2026-09-04 16:10:22 +08:00
twwu 4893c5e621 refactor(dify-builder): separate reasoning from execution progress 2026-09-04 13:43:16 +08:00
twwu eb25c2d8ee feat(dify-builder): add live progress and conversation streaming 2026-09-04 10:16:50 +08:00
Charles YaoandClaude Opus 4.8 e7e14ab888 fix(dify_builder): stop empty/mode-mismatched builds silently emptying the canvas
A build for a workflow app whose goal reads like a chatbot produced an empty
canvas while the assistant reported "Workflow built on the canvas.": the plan
was chatbot-shaped, build_nodes fed it to the generator (mode="workflow"), the
LLM emitted a chatflow graph (answer node / no end node), the generator
rejected it as MISSING_TERMINAL -- a class it does NOT retry -- and build_nodes
swallowed the error into []. handle_plan_approval then treated [] as a
successful build: it deleted the placeholder start and advanced to
build.execution, leaving nothing on the canvas.

Two parts:

1. build_nodes now prepends an explicit workflow-topology directive (one
   start + >=1 end node, no answer nodes) to the generator instruction, and
   retries ONCE on an error/empty result with the specific error fed back as
   a corrective nudge -- covering the terminal-node failure the shared
   generator skips.

2. handle_plan_approval refuses to fake success: when build_nodes yields zero
   create_node intents it surfaces an honest error and stays in
   build.plan_approval (retryable) without deleting the placeholder, instead
   of emptying the canvas and claiming a build. A loop-back re-approve still
   returns the fixed create intents (only filtered as already-present), so
   zero create intents unambiguously means a genuine generation failure.

Adds regression tests for both. Note: part 1 improves LLM reliability
(verifiable live); part 2 is the deterministic guarantee against the
false-success empty canvas.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-09-02 14:39:56 -07:00
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 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 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