Troubleshooting
The likely cause is that your relationship facts have left SpicyChat’s active context, or its saved memory is missing or contradictory. Start by enabling memory, saving a concise relationship fact in Memory Manager, and pinning it—not by changing generation settings or upgrading immediately. Memory Manager is paid-tier functionality; Free users can use a reviewed recap to restart. [0,1,4] [1] [2] [5]
Checked 2026-10-02 · 15 sources · reviewed before publication
Try these in order
-
1. Enable memory in the affected conversation
Open the three dots at the top right of the affected chat. If the menu says Enable Memory, select it; Disable Memory means memory is already enabled. Then open Memory Manager. It requires a few messages in the conversation and a Get A Taste, True Supporter, or I’m All In subscription. The documentation gives no exact minimum message count. If you are on Free, use the reviewed recap procedure in Step 6 instead. [0,1] [1] [2]
-
2. Save and pin one concise relationship fact
In Memory Manager, select + at the top right, enter the relationship fact, and select Add. Each entry is limited to 250 characters. Open that memory’s three dots → Pin Memory. [1]
Suggested approach: state the current relationship, its duration, and one essential shared circumstance rather than a scene-by-scene history. Use the copy-ready example below as a template. Support says pinned memories remain available after their original messages leave active context, but too many pins can interfere with recalling other memories; it gives no numeric pin limit. [0] [1] [2]
-
3. Remove contradictions from memory, not just the chat
Inspect the saved memories for conflicting relationship information. To correct one, use its three dots → Edit Memory → change the text → Save. To remove it, use three dots → Delete Memory. Deletion is irreversible and does not rewrite existing chat messages. [1]
Do not stop after correcting the visible conversation: editing or deleting a chat message does not automatically update its associated semantic memory. Correct that memory separately. [2] [2] [3]
-
4. Check identity and competing context
Under My Personas, check the intended persona and its name and highlights. The persona guide recommends one or two sentences of highlights; deleting a persona makes its conversation revert to the default profile. [3]
Suggested separation: keep your identity and role in persona highlights, and this conversation’s relationship history in its pinned memory. If you control the character setup, shorten unnecessary background: setup, instructions, messages, and replies share the context window. The notice “Chats beyond this point are no longer factored in” means older chat has left active context—not that it was deleted. Dismissing it changes nothing. [4,5] [4] [5] [6]
-
5. Inspect the model; treat generation tweaks as optional
To inspect models, use chat three dots → Generation Settings → Inference Model → Change Model. Larger subscription allowances remain constrained by the selected model; see the context caveat below. [10]
For optional drift adjustments, enter Generation Settings. Documented defaults are Temperature 0.7 and Top-P 0.7. Support recommends starting from defaults and trying lower values in increments of 0.05–0.1. Suggested method: change one value at a time. These controls address generation behavior, not restoration of missing facts. [8,11]
Access is unresolved: dedicated generation guides name True Supporter and I’m All In, while the plan matrix marks these adjustments as I’m All In only. Check actual account access before purchasing for them. [7,8,11] [8] [9] [11] [12]
-
6. Recover from a clean point if corrections do not hold
If the conversation has drifted badly, cloning can preserve the original while branching from an earlier point. For partial cloning, select messages from top to bottom; find clones under View saved chats. The available documentation does not provide the complete button-by-button cloning workflow. [12]
The fully documented restart alternative is to send: /cmd go out of character and create a summary of the entire chat so far. Copy and tidy the summary, start a new chat, and paste it as the first message beginning “This is what happened earlier:”. [13]
Suggested safeguard: verify the relationship facts yourself before pasting. An “entire chat” summary should not be assumed complete when early messages have already left active context. [4] [5] [13] [14]
Choose a tier for the memory feature you actually need
Free has a documented 4,096-token context window but no Memory Manager or automatic Semantic Memory 2.0. Get A Taste adds manual Memory Manager, but does not add automatic Semantic Memory 2.0 or enlarge that context window. True Supporter includes Memory Manager, automatic Semantic Memory 2.0, and an 8,192-token context window. I’m All In also includes both memory features, but its context allowance is disputed across official pages. [1,2,4,7]
Suggested decision: if the missing information is one stable relationship fact, try manual memory correction before paying for a larger context window. Choose Get A Taste for manual memory access; consider True Supporter or I’m All In if you specifically want automatic Semantic Memory 2.0—not because automatic retrieval guarantees recall. [2] [3] [5] [8]
Do not buy an upgrade on an assumed 32K limit
Support lists I’m All In at 16,384 context tokens; live guides advertise up to 32,768, depending on the model. The AI Models guide says effective context is the lower of the subscription limit and model maximum. It lists Default at 32K, Stheno at 8K, and SpicyXL at 16K, while warning that its model list may be outdated. Use the in-chat selector described in Step 5 to inspect current availability; do not assume every I’m All In model provides 32K. Public documentation does not establish rollout for your account. [0,4,7,9,10]
Increasing reply length is not a memory fix: the reply ceiling does not enlarge the context window or guarantee a longer response. [8] [1] [5] [8] [9] [10] [11]
Example to adapt
A cleaner instruction
Suggested pinned memory—replace the names and facts before saving: Alex and Morgan are established partners. They have been together for two years and share a home. Their relationship is ongoing.
If this still does not fix it
Pinned memories are not a guarantee of consistent relationship recall. Semantic Memory 2.0 uses summaries and relevance-based retrieval, not unlimited access to every past message. These procedures come from public documentation, not hands-on testing or measured recall results. [0,2]
Services with a relevant feature
Shown because the current provider record matches this need. Check the exact plan and limitation before paying.
SpicyChat
Checked 2026-10-02
The documentation provides actionable workflows for paid editable memory, JSON/PNG character import and free-text identity/persona context. Lyra V4 documents French and Japanese support at True Supporter or above, but language-menu options, current account availability and language quality remain unverified. Friendship, romance and pronouns can be expressed as written context, not verified dedicated controls. This is a documentation review, not evidence of tested behavior.
- Editable or persistent memory
- Character-card or character import
- Documented French chat setup
- Documented Japanese chat setup
Why it matches: Add, edit, delete and pin chat memories. First check the chat menu: select Enable Memory if shown; Disable Memory means memory is already enabled. Open chat three-dot menu → Memory Manager. To add a memory, select + → enter text → Add. To revise one, use the memory’s three-dot menu → Edit Memory → Save; Delete Memory and Pin Memory are available in that same menu. Each memory is limited to 250 characters. Manual Memory Manager requires Get A Taste, True Supporter or I’m All In; automatic Semantic Memory 2.0 requires True Supporter or I’m All In. Neither is included on Free. Deleted memories cannot be restored, and deletion does not rewrite messages already referencing them. Editing or deleting a chat message does not automatically update its associated semantic memory. Pinning too many memories can prevent retrieval of others; memory retrieval does not preserve every past message in active context or guarantee adherence.
Candy AI
Checked 2026-10-02
The documentation provides actionable French and Japanese chat setup, lists 20 memory slots for Premium Plus, and documents persona customization. Both language procedures require a reset that does not fully preserve long-term conversation memory. Memory editing, external character-card import, dedicated pronoun controls and selectable Friend/Romantic modes remain unverified. The evidence documents setup and entitlement details, not tested recall reliability or language adherence.
- Editable or persistent memory
- Character-card or character import
- Documented French chat setup
- Documented Japanese chat setup
Why it matches: Premium Plus includes 20 documented memory slots. The retrieved documentation does not explain how to add, edit or delete entries, their character limits or their current scope. Older indexed text describes 20 custom slots per character, but the current article does not reconfirm per-character scope. Free and ordinary paid-plan allocations and editing access were not established.
Lovescape
Checked 2026-10-02
The supplied public documentation supports conversational memory correction, last-response regeneration, general relationship-type configuration, and character-profile editing. Friend and Romantic partner roles are documented, but their exact selectors and behavior are not. Memory is documented on all plans, while free character creation has subscription-dependent character counts; neither establishes equal performance or role-specific entitlements. Buyers needing a dedicated memory editor, character-card import, French/Japanese text-chat setup, or pronoun controls should treat those requirements as unverified, not proven unavailable. This is a documentation review, not a hands-on test.
- Editable or persistent memory
- User persona / profile controls
- Friendship / platonic relationship setting
- Romantic relationship setting
Why it matches: Correct an incorrect memory by stating the correction in chat. Alternatively, regenerate the character’s last response and retain the preferred reply as part of the shared history. Memory is documented as per character and included on every plan, including free, without an expanded-recall add-on. A dedicated memory list, direct fact editor, individual-memory deletion control, and editing arbitrary older replies are not documented. All-plan availability does not establish equal recall performance; the limitations guide warns of missed topics and inconsistency in long conversations.
Sources
Checked 2026-10-02
- Why characters forget things (tokens and context) : SpicyChat
- "Chats beyond this point are no longer factored in" : SpicyChat
- Lorebooks : SpicyChat
- Plans and what's included : SpicyChat
- Premium Features | SpicyChat
- Generation settings — Temperature, Top-P and Top-K : SpicyChat
- Cloning a conversation : SpicyChat
- Starting a fresh chat but keeping the story : SpicyChat
Provider documentation tells us what a service describes. Unless a page explicitly says otherwise, we are not presenting it as a hands-on performance test.