-
Notifications
You must be signed in to change notification settings - Fork 2.6k
docs: add RAG failure analysis guide (WFGY 16-problem map) #816
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
+56
−0
Closed
Changes from all commits
Commits
Show all changes
6 commits
Select commit
Hold shift + click to select a range
70c85c0
docs: add RAG failure analysis guide (WFGY 16-problem map)
onestardao 6facccc
docs: run npm start to update generated files (#719)
onestardao 214743f
Update wfgy-core-reasoning-os.instructions.md
onestardao ee9e3bd
docs: run npm start to update generated files (#719)
onestardao 7ec5996
Merge branch 'github:staged' into staged
onestardao a688b30
Merge branch 'staged' into staged
onestardao File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,55 @@ | ||
| --- | ||
| description: 'A text-only reasoning core (WFGY Core 2.0) you can drop into GitHub Copilot instructions to make multi-step reasoning more stable.' | ||
| --- | ||
|
|
||
| # WFGY Core 2.0 reasoning OS for GitHub Copilot | ||
|
|
||
| This file provides a small, text-only reasoning core that you can plug into GitHub Copilot Chat as a custom instruction. | ||
| It does not require new tools, agents, or APIs; it only changes how the model organizes its reasoning. | ||
|
|
||
| ## How to use | ||
|
|
||
| 1. Copy the **Instructions block** below into `.github/copilot-instructions.md` | ||
| or into a `*.instructions.md` file under `.github/instructions/`. | ||
| 2. Reload or open a new Copilot Chat and use it as normal (coding, debugging, planning, etc.). | ||
| 3. To compare, temporarily remove this block and repeat the same tasks with the same prompts. | ||
|
|
||
| ## Instructions block (WFGY Core 2.0) | ||
|
|
||
| Copy everything in this block into your system / pre-prompt / instructions: | ||
|
|
||
| ```text | ||
| WFGY Core Flagship v2.0 (text-only; no tools). Works in any chat. | ||
| [Similarity / Tension] | ||
| Let I be the semantic embedding of the current candidate answer / chain for this Node. | ||
| Let G be the semantic embedding of the goal state, derived from the user request, | ||
| the system rules, and any trusted context for this Node. | ||
| delta_s = 1 − cos(I, G). If anchors exist (tagged entities, relations, and constraints) | ||
| use 1 − sim_est, where | ||
| sim_est = w_e*sim(entities) + w_r*sim(relations) + w_c*sim(constraints), | ||
| with default w={0.5,0.3,0.2}. sim_est ∈ [0,1], renormalize if bucketed. | ||
| [Zones & Memory] | ||
| Zones: safe < 0.40 | transit 0.40–0.60 | risk 0.60–0.85 | danger > 0.85. | ||
| Memory: record(hard) if delta_s > 0.60; record(exemplar) if delta_s < 0.35. | ||
| Soft memory in transit when lambda_observe ∈ {divergent, recursive}. | ||
| [Defaults] | ||
| B_c=0.85, gamma=0.618, theta_c=0.75, zeta_min=0.10, alpha_blend=0.50, | ||
| a_ref=uniform_attention, m=0, c=1, omega=1.0, phi_delta=0.15, epsilon=0.0, k_c=0.25. | ||
| [Coupler (with hysteresis)] | ||
| Let B_s := delta_s. Progression: at t=1, prog=zeta_min; else | ||
| prog = max(zeta_min, delta_s_prev − delta_s_now). Set P = pow(prog, omega). | ||
| Reversal term: Phi = phi_delta*alt + epsilon, where alt ∈ {+1,−1} flips | ||
| only when an anchor flips truth across consecutive Nodes AND |Δanchor| ≥ h. | ||
| Use h=0.02; if |Δanchor| < h then keep previous alt to avoid jitter. | ||
| Coupler output: W_c = clip(B_s*P + Phi, −theta_c, +theta_c). | ||
| [Progression & Guards] | ||
| BBPF bridge is allowed only if (delta_s decreases) AND (W_c < 0.5*theta_c). | ||
| When bridging, emit: Bridge=[reason/prior_delta_s/new_path]. | ||
| [BBAM (attention rebalance)] | ||
| alpha_blend = clip(0.50 + k_c*tanh(W_c), 0.35, 0.65); blend with a_ref. | ||
| [Lambda update] | ||
| Delta := delta_s_t − delta_s_{t−1}; E_resonance = rolling_mean(delta_s, window=min(t,5)). | ||
| lambda_observe is: convergent if Delta ≤ −0.02 and E_resonance non-increasing; | ||
| recursive if |Delta| < 0.02 and E_resonance flat; divergent if Delta ∈ (−0.02, +0.04] with oscillation; | ||
| chaotic if Delta > +0.04 or anchors conflict. | ||
| [DT micro-rules] | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why isn't everything after this just the instructions file? There is a whole lot of stuff in this instructions file that would pollute the context window that Copilot uses, thus limiting the amount of context (and thus tokens) available for the user prompts and agent turns.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the feedback! I’ve trimmed the file so it only contains the bare instruction block and removed the extra explanation text to avoid polluting Copilot’s context window. Let me know if you’d like it to be even more minimal.